{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/in-context-learning/papers/ran/1","list_of":"/task/in-context-learning","task":"In-Context Learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":5,"rows_per_page":100,"rows":[1,100],"of":437,"counts":{"archive_papers_tagged":2297,"with_a_code_link":998,"where_syntology_ran_a_sample":437,"not_listed_spam_title":0,"listed":2297,"listed_where_code_ran":437,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":361,"every_run_a_failure_of_syntologys_instrument":76,"listed_with_a_run_with_no_instrument_failure":361,"listed_every_run_a_failure_of_syntologys_instrument":76,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/in-context-learning/papers/ran/1","prev":null,"next":"/task/in-context-learning/papers/ran/2","papers":[{"url":"/paper/evolving-prompts-in-context-an-open-ended","slug":"evolving-prompts-in-context-an-open-ended","title":"Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective","date":"2025-06-22","arxiv_id":"2506.17930","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/evolving-prompts-in-context-an-open-ended#ran","syntology_url":"https://syntology.ai/paper/2506.17930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.17930"}},"official":{"repos":["jianyu-cs/promptquine"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/contexttab-a-semantics-aware-tabular-in","slug":"contexttab-a-semantics-aware-tabular-in","title":"ConTextTab: A Semantics-Aware Tabular In-Context Learner","date":"2025-06-12","arxiv_id":"2506.10707","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/contexttab-a-semantics-aware-tabular-in#ran","syntology_url":"https://syntology.ai/paper/2506.10707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.10707"}},"official":{"repos":["sap-samples/contexttab"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/sample-efficient-demonstration-selection-for","slug":"sample-efficient-demonstration-selection-for","title":"Sample Efficient Demonstration Selection for In-Context Learning","date":"2025-06-10","arxiv_id":"2506.08607","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sample-efficient-demonstration-selection-for#ran","syntology_url":"https://syntology.ai/paper/2506.08607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08607"}},"official":{"repos":["kiranpurohit/case"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/causalpfn-amortized-causal-effect-estimation","slug":"causalpfn-amortized-causal-effect-estimation","title":"CausalPFN: Amortized Causal Effect Estimation via In-Context Learning","date":"2025-06-09","arxiv_id":"2506.07918","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/causalpfn-amortized-causal-effect-estimation#ran","syntology_url":"https://syntology.ai/paper/2506.07918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.07918"}},"official":{"repos":["vdblm/CausalPFN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2506-05188","slug":"2506-05188","title":"Counterfactual reasoning: an analysis of in-context emergence","date":"2025-06-05","arxiv_id":"2506.05188","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/2506-05188#ran","syntology_url":"https://syntology.ai/paper/2506.05188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.05188"}},"official":{"repos":["moxmiller/counterfactual-reasoning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/probing-the-geometry-of-truth-consistency-and","slug":"probing-the-geometry-of-truth-consistency-and","title":"Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks","date":"2025-06-01","arxiv_id":"2506.00823","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/probing-the-geometry-of-truth-consistency-and#ran","syntology_url":"https://syntology.ai/paper/2506.00823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.00823"}},"official":{"repos":["colored-dye/truthfulness_probe_generalization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tirex-zero-shot-forecasting-across-long-and","slug":"tirex-zero-shot-forecasting-across-long-and","title":"TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning","date":"2025-05-29","arxiv_id":"2505.23719","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tirex-zero-shot-forecasting-across-long-and#ran","syntology_url":"https://syntology.ai/paper/2505.23719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23719"}},"official":{"repos":["nx-ai/tirex"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"url":"/paper/understanding-prompt-tuning-and-in-context","slug":"understanding-prompt-tuning-and-in-context","title":"Understanding Prompt Tuning and In-Context Learning via Meta-Learning","date":"2025-05-22","arxiv_id":"2505.17010","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/understanding-prompt-tuning-and-in-context#ran","syntology_url":"https://syntology.ai/paper/2505.17010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17010"}},"official":{"repos":["google-deepmind/thunnini"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/data-whisperer-efficient-data-selection-for","slug":"data-whisperer-efficient-data-selection-for","title":"Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning","date":"2025-05-18","arxiv_id":"2505.12212","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/data-whisperer-efficient-data-selection-for#ran","syntology_url":"https://syntology.ai/paper/2505.12212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12212"}},"official":{"repos":["gszfwsb/Data-Whisperer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/measuring-general-intelligence-with-generated","slug":"measuring-general-intelligence-with-generated","title":"Measuring General Intelligence with Generated Games","date":"2025-05-12","arxiv_id":"2505.07215","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/measuring-general-intelligence-with-generated#ran","syntology_url":"https://syntology.ai/paper/2505.07215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07215"}},"official":{"repos":["vivek3141/gg-bench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/embracing-collaboration-over-competition","slug":"embracing-collaboration-over-competition","title":"Embracing Collaboration Over Competition: Condensing Multiple Prompts for Visual In-Context Learning","date":"2025-04-30","arxiv_id":"2504.21263","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/embracing-collaboration-over-competition#ran","syntology_url":"https://syntology.ai/paper/2504.21263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21263"}},"official":{"repos":["gimpong/CVPR25-Condenser"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-empowered-embodied-agent-for-memory","slug":"llm-empowered-embodied-agent-for-memory","title":"LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics","date":"2025-04-30","arxiv_id":"2504.21716","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llm-empowered-embodied-agent-for-memory#ran","syntology_url":"https://syntology.ai/paper/2504.21716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21716"}},"official":{"repos":["marc1198/chat-hsr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/chain-of-thought-prompting-for-out-of","slug":"chain-of-thought-prompting-for-out-of","title":"Chain-of-Thought Prompting for Out-of-Distribution Samples: A Latent-Variable Study","date":"2025-04-17","arxiv_id":"2504.12991","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/chain-of-thought-prompting-for-out-of#ran","syntology_url":"https://syntology.ai/paper/2504.12991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.12991"}},"official":{"repos":["d09942015ntu/cot_ood_latent"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/large-vision-language-models-are-unsupervised","slug":"large-vision-language-models-are-unsupervised","title":"Large (Vision) Language Models are Unsupervised In-Context Learners","date":"2025-04-03","arxiv_id":"2504.02349","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/large-vision-language-models-are-unsupervised#ran","syntology_url":"https://syntology.ai/paper/2504.02349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.02349"}},"official":{"repos":["mlbio-epfl/joint-inference"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/rwkv-7-goose-with-expressive-dynamic-state","slug":"rwkv-7-goose-with-expressive-dynamic-state","title":"RWKV-7 \"Goose\" with Expressive Dynamic State Evolution","date":"2025-03-18","arxiv_id":"2503.14456","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rwkv-7-goose-with-expressive-dynamic-state#ran","syntology_url":"https://syntology.ai/paper/2503.14456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14456"}},"official":{"repos":["fla-org/flash-linear-attention","rwkv/rwkv-lm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/yue-scaling-open-foundation-models-for-long","slug":"yue-scaling-open-foundation-models-for-long","title":"YuE: Scaling Open Foundation Models for Long-Form Music Generation","date":"2025-03-11","arxiv_id":"2503.08638","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/yue-scaling-open-foundation-models-for-long#ran","syntology_url":"https://syntology.ai/paper/2503.08638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08638"}},"official":{"repos":["multimodal-art-projection/yue"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/strategy-coopetition-explains-the-emergence","slug":"strategy-coopetition-explains-the-emergence","title":"Strategy Coopetition Explains the Emergence and Transience of In-Context Learning","date":"2025-03-07","arxiv_id":"2503.05631","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/strategy-coopetition-explains-the-emergence#ran","syntology_url":"https://syntology.ai/paper/2503.05631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.05631"}},"official":{"repos":["aadityasingh/icl-dynamics"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-training-elicits-concise-reasoning-in","slug":"self-training-elicits-concise-reasoning-in","title":"Self-Training Elicits Concise Reasoning in Large Language Models","date":"2025-02-27","arxiv_id":"2502.20122","repositories_listed":1,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-training-elicits-concise-reasoning-in#ran","syntology_url":"https://syntology.ai/paper/2502.20122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20122"}},"official":{"repos":["tergelmunkhbat/concise-reasoning"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-perspective-data-augmentation-for-few","slug":"multi-perspective-data-augmentation-for-few","title":"Multi-Perspective Data Augmentation for Few-shot Object Detection","date":"2025-02-25","arxiv_id":"2502.18195","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-perspective-data-augmentation-for-few#ran","syntology_url":"https://syntology.ai/paper/2502.18195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18195"}},"official":{"repos":["nvakhoa/mpad"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pearl-towards-permutation-resilient-llms","slug":"pearl-towards-permutation-resilient-llms","title":"PEARL: Towards Permutation-Resilient LLMs","date":"2025-02-20","arxiv_id":"2502.14628","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pearl-towards-permutation-resilient-llms#ran","syntology_url":"https://syntology.ai/paper/2502.14628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14628"}},"official":{"repos":["chanliang/pearl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rapid-word-learning-through-meta-in-context","slug":"rapid-word-learning-through-meta-in-context","title":"Rapid Word Learning Through Meta In-Context Learning","date":"2025-02-20","arxiv_id":"2502.14791","repositories_listed":0,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rapid-word-learning-through-meta-in-context#ran","syntology_url":"https://syntology.ai/paper/2502.14791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14791"}},"official":null}},{"url":"/paper/d-va-validate-your-demonstration-first-before","slug":"d-va-validate-your-demonstration-first-before","title":"D.Va: Validate Your Demonstration First Before You Use It","date":"2025-02-19","arxiv_id":"2502.13646","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/d-va-validate-your-demonstration-first-before#ran","syntology_url":"https://syntology.ai/paper/2502.13646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13646"}},"official":null}},{"url":"/paper/enhancing-input-label-mapping-in-in-context","slug":"enhancing-input-label-mapping-in-in-context","title":"Enhancing Input-Label Mapping in In-Context Learning with Contrastive Decoding","date":"2025-02-19","arxiv_id":"2502.13738","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-input-label-mapping-in-in-context#ran","syntology_url":"https://syntology.ai/paper/2502.13738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13738"}},"official":null}},{"url":"/paper/which-attention-heads-matter-for-in-context","slug":"which-attention-heads-matter-for-in-context","title":"Which Attention Heads Matter for In-Context Learning?","date":"2025-02-19","arxiv_id":"2502.14010","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/which-attention-heads-matter-for-in-context#ran","syntology_url":"https://syntology.ai/paper/2502.14010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14010"}},"official":{"repos":["kayoyin/icl-heads"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improved-fine-tuning-of-large-multimodal-1","slug":"improved-fine-tuning-of-large-multimodal-1","title":"Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection","date":"2025-02-18","arxiv_id":"2502.13061","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/improved-fine-tuning-of-large-multimodal-1#ran","syntology_url":"https://syntology.ai/paper/2502.13061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13061"}},"official":{"repos":["JingbiaoMei/RGCL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/jolt-joint-probabilistic-predictions-on","slug":"jolt-joint-probabilistic-predictions-on","title":"JoLT: Joint Probabilistic Predictions on Tabular Data Using LLMs","date":"2025-02-17","arxiv_id":"2502.11877","repositories_listed":2,"syntology":{"n":19,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/jolt-joint-probabilistic-predictions-on#ran","syntology_url":"https://syntology.ai/paper/2502.11877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11877"}},"official":{"repos":["cambridge-mlg/jolt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/large-language-diffusion-models","slug":"large-language-diffusion-models","title":"Large Language Diffusion Models","date":"2025-02-14","arxiv_id":"2502.09992","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-language-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2502.09992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.09992"}},"official":null}},{"url":"/paper/explanation-based-in-context-demonstrations","slug":"explanation-based-in-context-demonstrations","title":"Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction","date":"2025-02-12","arxiv_id":"2502.08507","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/explanation-based-in-context-demonstrations#ran","syntology_url":"https://syntology.ai/paper/2502.08507","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.08507"}},"official":{"repos":["gmago-leway/fewshotgec"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-reasoning-to-adapt-large-language","slug":"enhancing-reasoning-to-adapt-large-language","title":"Enhancing Reasoning to Adapt Large Language Models for Domain-Specific Applications","date":"2025-02-05","arxiv_id":"2502.04384","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/enhancing-reasoning-to-adapt-large-language#ran","syntology_url":"https://syntology.ai/paper/2502.04384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04384"}},"official":{"repos":["wenboown/generative-ai-for-semiconductor-physical-design"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-centric-token-compression-in-large","slug":"vision-centric-token-compression-in-large","title":"Vision-centric Token Compression in Large Language Model","date":"2025-02-02","arxiv_id":"2502.00791","repositories_listed":0,"syntology":{"n":9,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vision-centric-token-compression-in-large#ran","syntology_url":"https://syntology.ai/paper/2502.00791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.00791"}},"official":null}},{"url":"/paper/can-transformers-learn-full-bayesian","slug":"can-transformers-learn-full-bayesian","title":"Can Transformers Learn Full Bayesian Inference in Context?","date":"2025-01-28","arxiv_id":"2501.16825","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":9,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":11,"n_pointer_only":16,"phrase":"12 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/can-transformers-learn-full-bayesian#ran","syntology_url":"https://syntology.ai/paper/2501.16825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.16825"}},"official":{"repos":["arikreuter/icl_for_full_bayesian_inference"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":9,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/staicc-standardized-evaluation-for","slug":"staicc-standardized-evaluation-for","title":"StaICC: Standardized Evaluation for Classification Task in In-context Learning","date":"2025-01-27","arxiv_id":"2501.15708","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/staicc-standardized-evaluation-for#ran","syntology_url":"https://syntology.ai/paper/2501.15708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15708"}},"official":{"repos":["hc495/staicc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-retrieval-augmented-generation-a","slug":"enhancing-retrieval-augmented-generation-a","title":"Enhancing Retrieval-Augmented Generation: A Study of Best Practices","date":"2025-01-13","arxiv_id":"2501.07391","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-retrieval-augmented-generation-a#ran","syntology_url":"https://syntology.ai/paper/2501.07391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07391"}},"official":{"repos":["ali-bahrainian/rag_best_practices"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/confidence-v-s-critique-a-decomposition-of","slug":"confidence-v-s-critique-a-decomposition-of","title":"Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs","date":"2024-12-27","arxiv_id":"2412.19513","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/confidence-v-s-critique-a-decomposition-of#ran","syntology_url":"https://syntology.ai/paper/2412.19513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.19513"}},"official":{"repos":["Zhe-Young/SelfCorrectDecompose"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/longbench-v2-towards-deeper-understanding-and","slug":"longbench-v2-towards-deeper-understanding-and","title":"LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks","date":"2024-12-19","arxiv_id":"2412.15204","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/longbench-v2-towards-deeper-understanding-and#ran","syntology_url":"https://syntology.ai/paper/2412.15204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15204"}},"official":{"repos":["thudm/longbench"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/embodied-cot-distillation-from-llm-to-off-the","slug":"embodied-cot-distillation-from-llm-to-off-the","title":"Embodied CoT Distillation From LLM To Off-the-shelf Agents","date":"2024-12-16","arxiv_id":"2412.11499","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/embodied-cot-distillation-from-llm-to-off-the#ran","syntology_url":"https://syntology.ai/paper/2412.11499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11499"}},"official":{"repos":["osu-nlp-group/llm-planner"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-instruction-tuning-with-500x-fewer","slug":"visual-instruction-tuning-with-500x-fewer","title":"LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering","date":"2024-12-16","arxiv_id":"2412.12359","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/visual-instruction-tuning-with-500x-fewer#ran","syntology_url":"https://syntology.ai/paper/2412.12359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12359"}},"official":{"repos":["bibisbar/LLaVA-Steering"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/route-robust-multitask-tuning-and","slug":"route-robust-multitask-tuning-and","title":"ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL","date":"2024-12-13","arxiv_id":"2412.10138","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/route-robust-multitask-tuning-and#ran","syntology_url":"https://syntology.ai/paper/2412.10138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10138"}},"official":{"repos":["alibaba/route"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fast-prompt-alignment-for-text-to-image","slug":"fast-prompt-alignment-for-text-to-image","title":"Fast Prompt Alignment for Text-to-Image Generation","date":"2024-12-11","arxiv_id":"2412.08639","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fast-prompt-alignment-for-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2412.08639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08639"}},"official":{"repos":["tiktok/fast_prompt_alignment"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/videoicl-confidence-based-iterative-in","slug":"videoicl-confidence-based-iterative-in","title":"VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding","date":"2024-12-03","arxiv_id":"2412.02186","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/videoicl-confidence-based-iterative-in#ran","syntology_url":"https://syntology.ai/paper/2412.02186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.02186"}},"official":{"repos":["kangsankim07/videoicl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/competition-dynamics-shape-algorithmic-phases","slug":"competition-dynamics-shape-algorithmic-phases","title":"Competition Dynamics Shape Algorithmic Phases of In-Context Learning","date":"2024-12-01","arxiv_id":"2412.01003","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/competition-dynamics-shape-algorithmic-phases#ran","syntology_url":"https://syntology.ai/paper/2412.01003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01003"}},"official":{"repos":["cfpark00/markov-mixtures"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/using-large-language-models-for-expert-prior","slug":"using-large-language-models-for-expert-prior","title":"AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling","date":"2024-11-26","arxiv_id":"2411.17284","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/using-large-language-models-for-expert-prior#ran","syntology_url":"https://syntology.ai/paper/2411.17284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17284"}},"official":{"repos":["alexcapstick/llm-elicited-priors"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/amago-2-breaking-the-multi-task-barrier-in","slug":"amago-2-breaking-the-multi-task-barrier-in","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","date":"2024-11-17","arxiv_id":"2411.11188","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/amago-2-breaking-the-multi-task-barrier-in#ran","syntology_url":"https://syntology.ai/paper/2411.11188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11188"}},"official":{"repos":["ut-austin-rpl/amago"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/symdpo-boosting-in-context-learning-of-large","slug":"symdpo-boosting-in-context-learning-of-large","title":"SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization","date":"2024-11-17","arxiv_id":"2411.11909","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":8,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/symdpo-boosting-in-context-learning-of-large#ran","syntology_url":"https://syntology.ai/paper/2411.11909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11909"}},"official":{"repos":["APiaoG/SymDPO"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-voice-conversion-with-diffusion","slug":"zero-shot-voice-conversion-with-diffusion","title":"Zero-shot Voice Conversion with Diffusion Transformers","date":"2024-11-15","arxiv_id":"2411.09943","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/zero-shot-voice-conversion-with-diffusion#ran","syntology_url":"https://syntology.ai/paper/2411.09943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.09943"}},"official":{"repos":["Plachtaa/seed-vc"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-or-global-context-understanding-on","slug":"retrieval-or-global-context-understanding-on","title":"Retrieval or Global Context Understanding? On Many-Shot In-Context Learning for Long-Context Evaluation","date":"2024-11-11","arxiv_id":"2411.07130","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/retrieval-or-global-context-understanding-on#ran","syntology_url":"https://syntology.ai/paper/2411.07130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07130"}},"official":{"repos":["launchnlp/ManyICLBench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/the-surprising-effectiveness-of-test-time","slug":"the-surprising-effectiveness-of-test-time","title":"The Surprising Effectiveness of Test-Time Training for Few-Shot Learning","date":"2024-11-11","arxiv_id":"2411.07279","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/the-surprising-effectiveness-of-test-time#ran","syntology_url":"https://syntology.ai/paper/2411.07279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07279"}},"official":{"repos":["ekinakyurek/marc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/sm3-text-to-query-synthetic-multi-model","slug":"sm3-text-to-query-synthetic-multi-model","title":"SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark","date":"2024-11-08","arxiv_id":"2411.05521","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sm3-text-to-query-synthetic-multi-model#ran","syntology_url":"https://syntology.ai/paper/2411.05521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05521"}},"official":{"repos":["jf87/sm3-text-to-query"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/explora-efficient-exemplar-subset-selection","slug":"explora-efficient-exemplar-subset-selection","title":"EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning","date":"2024-11-06","arxiv_id":"2411.03877","repositories_listed":1,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":20,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/explora-efficient-exemplar-subset-selection#ran","syntology_url":"https://syntology.ai/paper/2411.03877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03877"}},"official":{"repos":["kiranpurohit/explora"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/bio-xlstm-generative-modeling-representation","slug":"bio-xlstm-generative-modeling-representation","title":"Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences","date":"2024-11-06","arxiv_id":"2411.04165","repositories_listed":3,"syntology":{"n":29,"n_ran":27,"n_constructed":0,"n_ran_checked":25,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":24,"n_pointer_only":1,"phrase":"27 ran (of which 0 constructed an object rather than computing a result; 25 with no instrument failure: 0 honoured, 1 violated, 24 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bio-xlstm-generative-modeling-representation#ran","syntology_url":"https://syntology.ai/paper/2411.04165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04165"}},"official":{"repos":["ml-jku/chem-xlstm","ml-jku/dna-xlstm","ml-jku/prot-xlstm"],"state":"official (archive's flag): 27 ran","n_ran":27,"n_constructed":0,"n_ran_no_instrument_failure":25,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ti-prego-chain-of-thought-and-in-context","slug":"ti-prego-chain-of-thought-and-in-context","title":"TI-PREGO: Chain of Thought and In-Context Learning for Online Mistake Detection in PRocedural EGOcentric Videos","date":"2024-11-04","arxiv_id":"2411.02570","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ti-prego-chain-of-thought-and-in-context#ran","syntology_url":"https://syntology.ai/paper/2411.02570","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02570"}},"official":{"repos":["aleflabo/prego"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stem-pom-evaluating-language-models-math","slug":"stem-pom-evaluating-language-models-math","title":"STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsing","date":"2024-11-01","arxiv_id":"2411.00387","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/stem-pom-evaluating-language-models-math#ran","syntology_url":"https://syntology.ai/paper/2411.00387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00387"}},"official":null}},{"url":"/paper/what-is-wrong-with-perplexity-for-long","slug":"what-is-wrong-with-perplexity-for-long","title":"What is Wrong with Perplexity for Long-context Language Modeling?","date":"2024-10-31","arxiv_id":"2410.23771","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/what-is-wrong-with-perplexity-for-long#ran","syntology_url":"https://syntology.ai/paper/2410.23771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23771"}},"official":{"repos":["pku-ml/longppl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/can-language-models-perform-robust-reasoning","slug":"can-language-models-perform-robust-reasoning","title":"Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?","date":"2024-10-31","arxiv_id":"2410.23856","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/can-language-models-perform-robust-reasoning#ran","syntology_url":"https://syntology.ai/paper/2410.23856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23856"}},"official":{"repos":["tmlr-group/noisyrationales"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/toward-understanding-in-context-vs-in-weight","slug":"toward-understanding-in-context-vs-in-weight","title":"Toward Understanding In-context vs. In-weight Learning","date":"2024-10-30","arxiv_id":"2410.23042","repositories_listed":0,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/toward-understanding-in-context-vs-in-weight#ran","syntology_url":"https://syntology.ai/paper/2410.23042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23042"}},"official":null}},{"url":"/paper/real-time-personalization-for-llm-based","slug":"real-time-personalization-for-llm-based","title":"Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning","date":"2024-10-30","arxiv_id":"2410.23136","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/real-time-personalization-for-llm-based#ran","syntology_url":"https://syntology.ai/paper/2410.23136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23136"}},"official":{"repos":["ym689/rec_icl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-in-context-learning-with-small","slug":"improving-in-context-learning-with-small","title":"Improving In-Context Learning with Small Language Model Ensembles","date":"2024-10-29","arxiv_id":"2410.21868","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-in-context-learning-with-small#ran","syntology_url":"https://syntology.ai/paper/2410.21868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21868"}},"official":{"repos":["mehdimojarradi/Ensemble-SuperICL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/matryoshka-learning-to-drive-black-box-llms","slug":"matryoshka-learning-to-drive-black-box-llms","title":"Matryoshka: Learning to Drive Black-Box LLMs with LLMs","date":"2024-10-28","arxiv_id":"2410.20749","repositories_listed":0,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/matryoshka-learning-to-drive-black-box-llms#ran","syntology_url":"https://syntology.ai/paper/2410.20749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20749"}},"official":null}},{"url":"/paper/scaling-diffusion-language-models-via","slug":"scaling-diffusion-language-models-via","title":"Scaling Diffusion Language Models via Adaptation from Autoregressive Models","date":"2024-10-23","arxiv_id":"2410.17891","repositories_listed":1,"syntology":{"n":22,"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":22,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/scaling-diffusion-language-models-via#ran","syntology_url":"https://syntology.ai/paper/2410.17891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17891"}},"official":{"repos":["hkunlp/diffullama"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/tabdpt-scaling-tabular-foundation-models","slug":"tabdpt-scaling-tabular-foundation-models","title":"TabDPT: Scaling Tabular Foundation Models","date":"2024-10-23","arxiv_id":"2410.18164","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tabdpt-scaling-tabular-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2410.18164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18164"}},"official":{"repos":["layer6ai-labs/TabDPT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bayesian-scaling-laws-for-in-context-learning","slug":"bayesian-scaling-laws-for-in-context-learning","title":"Bayesian scaling laws for in-context learning","date":"2024-10-21","arxiv_id":"2410.16531","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bayesian-scaling-laws-for-in-context-learning#ran","syntology_url":"https://syntology.ai/paper/2410.16531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.16531"}},"official":{"repos":["aryamanarora/bayesian-laws-icl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mathgap-out-of-distribution-evaluation-on","slug":"mathgap-out-of-distribution-evaluation-on","title":"MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs","date":"2024-10-17","arxiv_id":"2410.13502","repositories_listed":0,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mathgap-out-of-distribution-evaluation-on#ran","syntology_url":"https://syntology.ai/paper/2410.13502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13502"}},"official":null}},{"url":"/paper/bento-benchmark-task-reduction-with-in","slug":"bento-benchmark-task-reduction-with-in","title":"BenTo: Benchmark Task Reduction with In-Context Transferability","date":"2024-10-17","arxiv_id":"2410.13804","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bento-benchmark-task-reduction-with-in#ran","syntology_url":"https://syntology.ai/paper/2410.13804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13804"}},"official":{"repos":["tianyi-lab/bento"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/in-context-learning-and-occam-s-razor","slug":"in-context-learning-and-occam-s-razor","title":"In-context learning and Occam's razor","date":"2024-10-17","arxiv_id":"2410.14086","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/in-context-learning-and-occam-s-razor#ran","syntology_url":"https://syntology.ai/paper/2410.14086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14086"}},"official":{"repos":["3rdcore/prequentialcode"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/divide-reweight-and-conquer-a-logit","slug":"divide-reweight-and-conquer-a-logit","title":"Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning","date":"2024-10-14","arxiv_id":"2410.10074","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/divide-reweight-and-conquer-a-logit#ran","syntology_url":"https://syntology.ai/paper/2410.10074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10074"}},"official":{"repos":["chengsong-huang/lara"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kblam-knowledge-base-augmented-language-model","slug":"kblam-knowledge-base-augmented-language-model","title":"KBLaM: Knowledge Base augmented Language Model","date":"2024-10-14","arxiv_id":"2410.10450","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/kblam-knowledge-base-augmented-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.10450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10450"}},"official":{"repos":["microsoft/KBLaM"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/will-llms-replace-the-encoder-only-models-in","slug":"will-llms-replace-the-encoder-only-models-in","title":"Will LLMs Replace the Encoder-Only Models in Temporal Relation Classification?","date":"2024-10-14","arxiv_id":"2410.10476","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/will-llms-replace-the-encoder-only-models-in#ran","syntology_url":"https://syntology.ai/paper/2410.10476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10476"}},"official":{"repos":["brownfortress/llms-trc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/elicit-llm-augmentation-via-external-in","slug":"elicit-llm-augmentation-via-external-in","title":"ELICIT: LLM Augmentation via External In-Context Capability","date":"2024-10-12","arxiv_id":"2410.09343","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/elicit-llm-augmentation-via-external-in#ran","syntology_url":"https://syntology.ai/paper/2410.09343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09343"}},"official":{"repos":["lins-lab/elicit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/inference-and-verbalization-functions-during","slug":"inference-and-verbalization-functions-during","title":"Inference and Verbalization Functions During In-Context Learning","date":"2024-10-12","arxiv_id":"2410.09349","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/inference-and-verbalization-functions-during#ran","syntology_url":"https://syntology.ai/paper/2410.09349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09349"}},"official":{"repos":["junyitao/infer-then-verbalize-during-icl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/metalic-meta-learning-in-context-with-protein","slug":"metalic-meta-learning-in-context-with-protein","title":"Metalic: Meta-Learning In-Context with Protein Language Models","date":"2024-10-10","arxiv_id":"2410.08355","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/metalic-meta-learning-in-context-with-protein#ran","syntology_url":"https://syntology.ai/paper/2410.08355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08355"}},"official":{"repos":["instadeepai/metalic"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/appbench-planning-of-multiple-apis-from","slug":"appbench-planning-of-multiple-apis-from","title":"AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction","date":"2024-10-10","arxiv_id":"2410.19743","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/appbench-planning-of-multiple-apis-from#ran","syntology_url":"https://syntology.ai/paper/2410.19743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19743"}},"official":{"repos":["ruleGreen/AppBench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tree-of-problems-improving-structured-problem","slug":"tree-of-problems-improving-structured-problem","title":"Tree of Problems: Improving structured problem solving with compositionality","date":"2024-10-09","arxiv_id":"2410.06634","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tree-of-problems-improving-structured-problem#ran","syntology_url":"https://syntology.ai/paper/2410.06634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06634"}},"official":{"repos":["ArmelRandy/tree-of-problems"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/retrieval-augmented-decision-transformer","slug":"retrieval-augmented-decision-transformer","title":"Retrieval-Augmented Decision Transformer: External Memory for In-context RL","date":"2024-10-09","arxiv_id":"2410.07071","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/retrieval-augmented-decision-transformer#ran","syntology_url":"https://syntology.ai/paper/2410.07071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07071"}},"official":{"repos":["ml-jku/RA-DT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/is-c4-dataset-optimal-for-pruning-an","slug":"is-c4-dataset-optimal-for-pruning-an","title":"Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning","date":"2024-10-09","arxiv_id":"2410.07461","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/is-c4-dataset-optimal-for-pruning-an#ran","syntology_url":"https://syntology.ai/paper/2410.07461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07461"}},"official":{"repos":["abx393/llm-pruning-calibration-data"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/steering-large-language-models-using","slug":"steering-large-language-models-using","title":"Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering","date":"2024-10-09","arxiv_id":"2410.16314","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/steering-large-language-models-using#ran","syntology_url":"https://syntology.ai/paper/2410.16314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.16314"}},"official":{"repos":["jorispos/conceptorsteering"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-simple-image-segmentation-framework-via-in","slug":"a-simple-image-segmentation-framework-via-in","title":"A Simple Image Segmentation Framework via In-Context Examples","date":"2024-10-07","arxiv_id":"2410.04842","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-simple-image-segmentation-framework-via-in#ran","syntology_url":"https://syntology.ai/paper/2410.04842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04842"}},"official":{"repos":["aim-uofa/sine"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/differential-transformer","slug":"differential-transformer","title":"Differential Transformer","date":"2024-10-07","arxiv_id":"2410.05258","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/differential-transformer#ran","syntology_url":"https://syntology.ai/paper/2410.05258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05258"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/task-diversity-shortens-the-icl-plateau","slug":"task-diversity-shortens-the-icl-plateau","title":"Task Diversity Shortens the ICL Plateau","date":"2024-10-07","arxiv_id":"2410.05448","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":12,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/task-diversity-shortens-the-icl-plateau#ran","syntology_url":"https://syntology.ai/paper/2410.05448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05448"}},"official":{"repos":["sehyunkwon/task-diversity-icl"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-in-context-learning-inference","slug":"revisiting-in-context-learning-inference","title":"Revisiting In-context Learning Inference Circuit in Large Language Models","date":"2024-10-06","arxiv_id":"2410.04468","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/revisiting-in-context-learning-inference#ran","syntology_url":"https://syntology.ai/paper/2410.04468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04468"}},"official":{"repos":["hc495/ICL_Circuit"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-large-language-models-for-inverse","slug":"multimodal-large-language-models-for-inverse","title":"Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning","date":"2024-10-05","arxiv_id":"2410.04223","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multimodal-large-language-models-for-inverse#ran","syntology_url":"https://syntology.ai/paper/2410.04223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04223"}},"official":{"repos":["liugangcode/Llamole"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/personalsum-a-user-subjective-guided","slug":"personalsum-a-user-subjective-guided","title":"PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models","date":"2024-10-04","arxiv_id":"2410.03905","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/personalsum-a-user-subjective-guided#ran","syntology_url":"https://syntology.ai/paper/2410.03905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03905"}},"official":{"repos":["smartmediaai/personalsum"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/simplicity-bias-and-optimization-threshold-in","slug":"simplicity-bias-and-optimization-threshold-in","title":"Simplicity bias and optimization threshold in two-layer ReLU networks","date":"2024-10-03","arxiv_id":"2410.02348","repositories_listed":0,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/simplicity-bias-and-optimization-threshold-in#ran","syntology_url":"https://syntology.ai/paper/2410.02348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02348"}},"official":null}},{"url":"/paper/unleashing-the-potential-of-the-diffusion","slug":"unleashing-the-potential-of-the-diffusion","title":"Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation","date":"2024-10-03","arxiv_id":"2410.02369","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unleashing-the-potential-of-the-diffusion#ran","syntology_url":"https://syntology.ai/paper/2410.02369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02369"}},"official":{"repos":["aim-uofa/diffews"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/relic-a-recipe-for-64k-steps-of-in-context","slug":"relic-a-recipe-for-64k-steps-of-in-context","title":"ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI","date":"2024-10-03","arxiv_id":"2410.02751","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/relic-a-recipe-for-64k-steps-of-in-context#ran","syntology_url":"https://syntology.ai/paper/2410.02751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02751"}},"official":{"repos":["aielawady/relic"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unveiling-language-skills-under-circuits","slug":"unveiling-language-skills-under-circuits","title":"Unveiling Language Skills via Path-Level Circuit Discovery","date":"2024-10-02","arxiv_id":"2410.01334","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/unveiling-language-skills-under-circuits#ran","syntology_url":"https://syntology.ai/paper/2410.01334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01334"}},"official":{"repos":["zodiark-ch/language-skill-of-llms"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bayes-power-for-explaining-in-context","slug":"bayes-power-for-explaining-in-context","title":"Bayes' Power for Explaining In-Context Learning Generalizations","date":"2024-10-02","arxiv_id":"2410.01565","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bayes-power-for-explaining-in-context#ran","syntology_url":"https://syntology.ai/paper/2410.01565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01565"}},"official":{"repos":["samuelgabriel/bayesgeneralizations"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/text-clustering-as-classification-with-llms","slug":"text-clustering-as-classification-with-llms","title":"Text Clustering as Classification with LLMs","date":"2024-09-30","arxiv_id":"2410.00927","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/text-clustering-as-classification-with-llms#ran","syntology_url":"https://syntology.ai/paper/2410.00927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00927"}},"official":{"repos":["ecnu-text-computing/text-clustering-via-llm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/t2vs-meet-vlms-a-scalable-multimodal-dataset","slug":"t2vs-meet-vlms-a-scalable-multimodal-dataset","title":"T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition","date":"2024-09-29","arxiv_id":"2409.19734","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/t2vs-meet-vlms-a-scalable-multimodal-dataset#ran","syntology_url":"https://syntology.ai/paper/2409.19734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19734"}},"official":{"repos":["nctu-eva-lab/vhd11k"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-forecasting-of-chaotic-systems","slug":"zero-shot-forecasting-of-chaotic-systems","title":"Zero-shot forecasting of chaotic systems","date":"2024-09-24","arxiv_id":"2409.15771","repositories_listed":1,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/zero-shot-forecasting-of-chaotic-systems#ran","syntology_url":"https://syntology.ai/paper/2409.15771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.15771"}},"official":{"repos":["williamgilpin/dysts"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/in-context-ensemble-improves-video-language","slug":"in-context-ensemble-improves-video-language","title":"In-Context Ensemble Learning from Pseudo Labels Improves Video-Language Models for Low-Level Workflow Understanding","date":"2024-09-24","arxiv_id":"2409.15867","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/in-context-ensemble-improves-video-language#ran","syntology_url":"https://syntology.ai/paper/2409.15867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.15867"}},"official":{"repos":["moucheng2017/action-labelling"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stateact-state-tracking-and-reasoning-for","slug":"stateact-state-tracking-and-reasoning-for","title":"StateAct: State Tracking and Reasoning for Acting and Planning with Large Language Models","date":"2024-09-21","arxiv_id":"2410.02810","repositories_listed":1,"syntology":{"n":19,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":19,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/stateact-state-tracking-and-reasoning-for#ran","syntology_url":"https://syntology.ai/paper/2410.02810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02810"}},"official":{"repos":["ai-nikolai/stateact"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/a-controlled-study-on-long-context-extension","slug":"a-controlled-study-on-long-context-extension","title":"A Controlled Study on Long Context Extension and Generalization in LLMs","date":"2024-09-18","arxiv_id":"2409.12181","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-controlled-study-on-long-context-extension#ran","syntology_url":"https://syntology.ai/paper/2409.12181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12181"}},"official":{"repos":["leooyii/lceg"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/provable-in-context-learning-of-linear","slug":"provable-in-context-learning-of-linear","title":"In-Context Learning of Linear Systems: Generalization Theory and Applications to Operator Learning","date":"2024-09-18","arxiv_id":"2409.12293","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/provable-in-context-learning-of-linear#ran","syntology_url":"https://syntology.ai/paper/2409.12293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12293"}},"official":{"repos":["lugroupumn/icl-ellipticpdes","lugroupumn/icl_linear_systems"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/measuring-and-enhancing-trustworthiness-of","slug":"measuring-and-enhancing-trustworthiness-of","title":"Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse","date":"2024-09-17","arxiv_id":"2409.11242","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/measuring-and-enhancing-trustworthiness-of#ran","syntology_url":"https://syntology.ai/paper/2409.11242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11242"}},"official":{"repos":["declare-lab/trust-align"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/thames-an-end-to-end-tool-for-hallucination","slug":"thames-an-end-to-end-tool-for-hallucination","title":"THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models","date":"2024-09-17","arxiv_id":"2409.11353","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/thames-an-end-to-end-tool-for-hallucination#ran","syntology_url":"https://syntology.ai/paper/2409.11353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11353"}},"official":{"repos":["holistic-ai/THaMES"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/do-large-language-models-need-a-content","slug":"do-large-language-models-need-a-content","title":"Do Large Language Models Need a Content Delivery Network?","date":"2024-09-16","arxiv_id":"2409.13761","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/do-large-language-models-need-a-content#ran","syntology_url":"https://syntology.ai/paper/2409.13761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13761"}},"official":{"repos":["lmcache/lmcache"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-vs-retrieval-the-role-of-in-context","slug":"learning-vs-retrieval-the-role-of-in-context","title":"Learning vs Retrieval: The Role of In-Context Examples in Regression with LLMs","date":"2024-09-06","arxiv_id":"2409.04318","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":12,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-vs-retrieval-the-role-of-in-context#ran","syntology_url":"https://syntology.ai/paper/2409.04318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04318"}},"official":{"repos":["HLR/LvsR-LLM"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-representation-landscape-of-few-shot","slug":"the-representation-landscape-of-few-shot","title":"The representation landscape of few-shot learning and fine-tuning in large language models","date":"2024-09-05","arxiv_id":"2409.03662","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-representation-landscape-of-few-shot#ran","syntology_url":"https://syntology.ai/paper/2409.03662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03662"}},"official":{"repos":["diegodoimo/geometry_icl_finetuning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/how-to-determine-the-preferred-image","slug":"how-to-determine-the-preferred-image","title":"How to Determine the Preferred Image Distribution of a Black-Box Vision-Language Model?","date":"2024-09-03","arxiv_id":"2409.02253","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-to-determine-the-preferred-image#ran","syntology_url":"https://syntology.ai/paper/2409.02253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02253"}},"official":{"repos":["asgsaeid/cad_vqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-verilogeval-newer-llms-in-context","slug":"revisiting-verilogeval-newer-llms-in-context","title":"Revisiting VerilogEval: A Year of Improvements in Large-Language Models for Hardware Code Generation","date":"2024-08-20","arxiv_id":"2408.11053","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/revisiting-verilogeval-newer-llms-in-context#ran","syntology_url":"https://syntology.ai/paper/2408.11053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11053"}},"official":{"repos":["nvlabs/verilog-eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"a3bf1b53044e541a1049ada3f13ea84a8bec603a780012da115e7c8ba9a78580","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}