{"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":"/method/base/papers/ran/2","list_of":"/method/base","method":"BASE","archive":{"snapshot":"2025-07-28"},"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 isolate this method inside it.","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":2,"pages_in_order":7,"rows_per_page":100,"rows":[101,200],"of":621,"counts":{"archive_papers_tagged":5784,"with_a_code_link":1913,"where_syntology_ran_a_sample":621,"not_listed_spam_title":0,"listed":5784,"listed_where_code_ran":621,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":523,"every_run_a_failure_of_syntologys_instrument":98,"listed_with_a_run_with_no_instrument_failure":523,"listed_every_run_a_failure_of_syntologys_instrument":98,"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":"/method/base/papers/ran/1","prev":"/method/base/papers/ran/1","next":"/method/base/papers/ran/3","papers":[{"paper":"/paper/zoomeye-enhancing-multimodal-llms-with-human","slug":"zoomeye-enhancing-multimodal-llms-with-human","title":"ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration","date":"2024-11-25","arxiv_id":"2411.16044","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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) · 0 unverified","official":{"repos":["om-ai-lab/ZoomEye"],"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"]}}},{"paper":"/paper/preference-optimization-for-reasoning-with","slug":"preference-optimization-for-reasoning-with","title":"Preference Optimization for Reasoning with Pseudo Feedback","date":"2024-11-25","arxiv_id":"2411.16345","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"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","official":null}},{"paper":"/paper/tulu-3-pushing-frontiers-in-open-language","slug":"tulu-3-pushing-frontiers-in-open-language","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","date":"2024-11-22","arxiv_id":"2411.15124","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["allenai/open-instruct"],"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"]}}},{"paper":"/paper/insight-v-exploring-long-chain-visual","slug":"insight-v-exploring-long-chain-visual","title":"Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models","date":"2024-11-21","arxiv_id":"2411.14432","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":0,"n_instrument":5,"unverified":5,"pointer_only":10,"phrase":"5 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; 5 where Syntology's instrument failed) · 5 unverified","official":{"repos":["dongyh20/insight-v"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/perfcodegen-improving-performance-of-llm","slug":"perfcodegen-improving-performance-of-llm","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","date":"2024-11-18","arxiv_id":"2412.03578","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["SalesforceAIResearch/perfcodegen"],"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"]}}},{"paper":"/paper/llava-o1-let-vision-language-models-reason","slug":"llava-o1-let-vision-language-models-reason","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","date":"2024-11-15","arxiv_id":"2411.10440","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["PKU-YuanGroup/LLaVA-CoT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/dynamic-rewarding-with-prompt-optimization","slug":"dynamic-rewarding-with-prompt-optimization","title":"Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models","date":"2024-11-13","arxiv_id":"2411.08733","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":1,"n_instrument":1,"unverified":4,"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) · 4 unverified","official":{"repos":["Singla17/DRPO"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-limited-impact-of-medical-adaptation-of","slug":"the-limited-impact-of-medical-adaptation-of","title":"The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models","date":"2024-11-13","arxiv_id":"2411.08870","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"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","official":{"repos":["taekb/eval-medical-dapt"],"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"]}}},{"paper":"/paper/dpu-dynamic-prototype-updating-for-multimodal","slug":"dpu-dynamic-prototype-updating-for-multimodal","title":"DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection","date":"2024-11-12","arxiv_id":"2411.08227","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lili0415/dpu-ood-detection"],"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":["listed","official"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"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","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"]}}},{"paper":"/paper/controllable-context-sensitivity-and-the-knob","slug":"controllable-context-sensitivity-and-the-knob","title":"Controllable Context Sensitivity and the Knob Behind It","date":"2024-11-11","arxiv_id":"2411.07404","n_code_links":1,"syntology":{"ran":16,"of":24,"n_ran_checked":16,"n_instrument":0,"unverified":8,"pointer_only":24,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["kdu4108/context-vs-prior-finetuning"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/rethinking-bradley-terry-models-in-preference","slug":"rethinking-bradley-terry-models-in-preference","title":"Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives","date":"2024-11-07","arxiv_id":"2411.04991","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["holarissun/rewardmodelingbeyondbradleyterry"],"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"]}}},{"paper":"/paper/both-text-and-images-leaked-a-systematic","slug":"both-text-and-images-leaked-a-systematic","title":"Both Text and Images Leaked! A Systematic Analysis of Multimodal LLM Data Contamination","date":"2024-11-06","arxiv_id":"2411.03823","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":1,"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","official":{"repos":["MLLM-Data-Contamination/MM-Detect"],"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"]}}},{"paper":"/paper/medical-adaptation-of-large-language-and","slug":"medical-adaptation-of-large-language-and","title":"Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?","date":"2024-11-06","arxiv_id":"2411.04118","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"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","official":{"repos":["taekb/eval-medical-dapt"],"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"]}}},{"paper":"/paper/language-models-are-hidden-reasoners","slug":"language-models-are-hidden-reasoners","title":"Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding","date":"2024-11-06","arxiv_id":"2411.04282","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["salesforceairesearch/latro"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/inference-optimal-vlms-need-only-one-visual","slug":"inference-optimal-vlms-need-only-one-visual","title":"Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters","date":"2024-11-05","arxiv_id":"2411.03312","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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","official":{"repos":["locuslab/llava-token-compression"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/zipfian-whitening","slug":"zipfian-whitening","title":"Zipfian Whitening","date":"2024-11-01","arxiv_id":"2411.00680","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cl-tohoku/zipfian-whitening"],"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"]}}},{"paper":"/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","n_code_links":2,"syntology":{"ran":10,"of":11,"n_ran_checked":5,"n_instrument":5,"unverified":1,"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","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"]}}},{"paper":"/paper/imov3d-learning-open-vocabulary-point-clouds","slug":"imov3d-learning-open-vocabulary-point-clouds","title":"ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D Images","date":"2024-10-31","arxiv_id":"2410.24001","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":4,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["yangtiming/imov3d"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/hidden-persuaders-llms-political-leaning-and","slug":"hidden-persuaders-llms-political-leaning-and","title":"Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters","date":"2024-10-31","arxiv_id":"2410.24190","n_code_links":1,"syntology":{"ran":2,"of":11,"n_ran_checked":2,"n_instrument":0,"unverified":9,"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) · 9 unverified","official":{"repos":["sunblaze-ucb/political_leaning_RepE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/selfcodealign-self-alignment-for-code","slug":"selfcodealign-self-alignment-for-code","title":"SelfCodeAlign: Self-Alignment for Code Generation","date":"2024-10-31","arxiv_id":"2410.24198","n_code_links":2,"syntology":{"ran":30,"of":37,"n_ran_checked":22,"n_instrument":8,"unverified":7,"pointer_only":0,"phrase":"30 ran (of which 3 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified","official":{"repos":["bigcode-project/selfcodealign"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["community","listed","official"]}}},{"paper":"/paper/consistency-diffusion-bridge-models","slug":"consistency-diffusion-bridge-models","title":"Consistency Diffusion Bridge Models","date":"2024-10-30","arxiv_id":"2410.22637","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":5,"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) · 1 unverified","official":null}},{"paper":"/paper/vpo-leveraging-the-number-of-votes-in","slug":"vpo-leveraging-the-number-of-votes-in","title":"VPO: Leveraging the Number of Votes in Preference Optimization","date":"2024-10-30","arxiv_id":"2410.22891","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":{"repos":["ku-dmlab/vpo"],"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"]}}},{"paper":"/paper/flowllm-flow-matching-for-material-generation","slug":"flowllm-flow-matching-for-material-generation","title":"FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions","date":"2024-10-30","arxiv_id":"2410.23405","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["facebookresearch/flowmm"],"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"]}}},{"paper":"/paper/pk-yolo-pretrained-knowledge-guided-yolo-for","slug":"pk-yolo-pretrained-knowledge-guided-yolo-for","title":"PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slices","date":"2024-10-29","arxiv_id":"2410.21822","n_code_links":1,"syntology":{"ran":16,"of":34,"n_ran_checked":7,"n_instrument":9,"unverified":18,"pointer_only":34,"phrase":"16 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 9 where Syntology's instrument failed) · 18 unverified","official":{"repos":["mkang315/pk-yolo"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":1,"n_ran_no_instrument_failure":7,"n_unverified":18,"ran_from_kinds":["official"]}}},{"paper":"/paper/retrieval-retro-retrieval-based-inorganic","slug":"retrieval-retro-retrieval-based-inorganic","title":"Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert Knowledge","date":"2024-10-28","arxiv_id":"2410.21341","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":9,"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) · 0 unverified","official":{"repos":["heewoongnoh/retrieval-retro"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/absorb-escape-overcoming-single-model","slug":"absorb-escape-overcoming-single-model","title":"Absorb & Escape: Overcoming Single Model Limitations in Generating Genomic Sequences","date":"2024-10-28","arxiv_id":"2410.21345","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["Zehui127/Absorb-Escape"],"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"]}}},{"paper":"/paper/llama-scope-extracting-millions-of-features","slug":"llama-scope-extracting-millions-of-features","title":"Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders","date":"2024-10-27","arxiv_id":"2410.20526","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"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) · 0 unverified","official":{"repos":["openmoss/language-model-saes"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/practical-bayesian-algorithm-execution-via","slug":"practical-bayesian-algorithm-execution-via","title":"Practical Bayesian Algorithm Execution via Posterior Sampling","date":"2024-10-27","arxiv_id":"2410.20596","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["RaulAstudillo06/PSBAX"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/openwebvoyager-building-multimodal-web-agents","slug":"openwebvoyager-building-multimodal-web-agents","title":"OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization","date":"2024-10-25","arxiv_id":"2410.19609","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"11 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["minorjerry/openwebvoyager"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/3d-adapter-geometry-consistent-multi-view","slug":"3d-adapter-geometry-consistent-multi-view","title":"3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation","date":"2024-10-24","arxiv_id":"2410.18974","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["Lakonik/MVEdit"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/conditional-diffusions-for-neural-posterior","slug":"conditional-diffusions-for-neural-posterior","title":"Conditional diffusions for amortized neural posterior estimation","date":"2024-10-24","arxiv_id":"2410.19105","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":{"repos":["tianyucodings/cdiff"],"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","unlocated"]}}},{"paper":"/paper/fast-graph-sharpness-aware-minimization-for","slug":"fast-graph-sharpness-aware-minimization-for","title":"Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification","date":"2024-10-22","arxiv_id":"2410.16845","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"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","official":{"repos":["draym28/fgsam_neurips24"],"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"]}}},{"paper":"/paper/multi-if-benchmarking-llms-on-multi-turn-and","slug":"multi-if-benchmarking-llms-on-multi-turn-and","title":"Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following","date":"2024-10-21","arxiv_id":"2410.15553","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":{"repos":["facebookresearch/Multi-IF"],"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"]}}},{"paper":"/paper/gradient-rewiring-for-editable-graph-neural","slug":"gradient-rewiring-for-editable-graph-neural","title":"Gradient Rewiring for Editable Graph Neural Network Training","date":"2024-10-21","arxiv_id":"2410.15556","n_code_links":1,"syntology":{"ran":3,"of":9,"n_ran_checked":3,"n_instrument":0,"unverified":6,"pointer_only":8,"phrase":"3 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; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["zhimengj0326/gradient_rewiring_editing"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/ipo-interpretable-prompt-optimization-for","slug":"ipo-interpretable-prompt-optimization-for","title":"IPO: Interpretable Prompt Optimization for Vision-Language Models","date":"2024-10-20","arxiv_id":"2410.15397","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":3,"n_instrument":6,"unverified":2,"pointer_only":11,"phrase":"9 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; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["lmsdss/IPO"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/evaluating-deep-unlearning-in-large-language","slug":"evaluating-deep-unlearning-in-large-language","title":"Evaluating Deep Unlearning in Large Language Models","date":"2024-10-19","arxiv_id":"2410.15153","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":0,"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) · 3 unverified","official":{"repos":["wrh14/deep_unlearning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-the-role-of-attention-heads-in-large","slug":"on-the-role-of-attention-heads-in-large","title":"On the Role of Attention Heads in Large Language Model Safety","date":"2024-10-17","arxiv_id":"2410.13708","n_code_links":1,"syntology":{"ran":16,"of":24,"n_ran_checked":8,"n_instrument":8,"unverified":8,"pointer_only":24,"phrase":"16 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; 8 where Syntology's instrument failed) · 8 unverified","official":{"repos":["ydyjya/safetyheadattribution"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/expand-and-compress-exploring-tuning","slug":"expand-and-compress-exploring-tuning","title":"Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting","date":"2024-10-16","arxiv_id":"2410.12593","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 3 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; every one of the 3 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/improving-instruction-following-in-language-1","slug":"improving-instruction-following-in-language-1","title":"Improving Instruction-Following in Language Models through Activation Steering","date":"2024-10-15","arxiv_id":"2410.12877","n_code_links":0,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":null}},{"paper":"/paper/lolcats-on-low-rank-linearizing-of-large","slug":"lolcats-on-low-rank-linearizing-of-large","title":"LoLCATs: On Low-Rank Linearizing of Large Language Models","date":"2024-10-14","arxiv_id":"2410.10254","n_code_links":1,"syntology":{"ran":23,"of":32,"n_ran_checked":13,"n_instrument":10,"unverified":9,"pointer_only":0,"phrase":"23 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 10 where Syntology's instrument failed) · 9 unverified","official":{"repos":["hazyresearch/lolcats"],"state":"official (archive's flag): 23 ran","n_ran":23,"n_constructed":9,"n_ran_no_instrument_failure":13,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/locking-down-the-finetuned-llms-safety","slug":"locking-down-the-finetuned-llms-safety","title":"Locking Down the Finetuned LLMs Safety","date":"2024-10-14","arxiv_id":"2410.10343","n_code_links":1,"syntology":{"ran":12,"of":21,"n_ran_checked":6,"n_instrument":6,"unverified":9,"pointer_only":21,"phrase":"12 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; 6 where Syntology's instrument failed) · 9 unverified","official":{"repos":["zhu-minjun/safetylock"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-reliable-verification-of-unauthorized","slug":"towards-reliable-verification-of-unauthorized","title":"Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models","date":"2024-10-14","arxiv_id":"2410.10437","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["antigonerandy/siren"],"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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":8,"n_instrument":3,"unverified":1,"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","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"]}}},{"paper":"/paper/sampa-sharpness-aware-minimization","slug":"sampa-sharpness-aware-minimization","title":"SAMPa: Sharpness-aware Minimization Parallelized","date":"2024-10-14","arxiv_id":"2410.10683","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["lions-epfl/sampa"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/large-scale-3d-medical-image-pre-training","slug":"large-scale-3d-medical-image-pre-training","title":"Large-Scale 3D Medical Image Pre-training with Geometric Context Priors","date":"2024-10-13","arxiv_id":"2410.09890","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":9,"n_instrument":2,"unverified":2,"pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["luffy03/large-scale-medical"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/rethinking-data-selection-at-scale-random","slug":"rethinking-data-selection-at-scale-random","title":"Rethinking Data Selection at Scale: Random Selection is Almost All You Need","date":"2024-10-12","arxiv_id":"2410.09335","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":10,"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) · 4 unverified","official":{"repos":["xiatingyu/sft-dataselection-at-scale"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/generative-subgraph-retrieval-for-knowledge","slug":"generative-subgraph-retrieval-for-knowledge","title":"Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation","date":"2024-10-12","arxiv_id":"2410.09350","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"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","official":{"repos":["mlvlab/dialoggsr"],"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"]}}},{"paper":"/paper/ctrlora-an-extensible-and-efficient-framework","slug":"ctrlora-an-extensible-and-efficient-framework","title":"CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation","date":"2024-10-12","arxiv_id":"2410.09400","n_code_links":1,"syntology":{"ran":13,"of":22,"n_ran_checked":10,"n_instrument":3,"unverified":9,"pointer_only":3,"phrase":"13 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","official":{"repos":["xyfjason/ctrlora"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["community","official","unlocated"]}}},{"paper":"/paper/vlfeedback-a-large-scale-ai-feedback-dataset","slug":"vlfeedback-a-large-scale-ai-feedback-dataset","title":"VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment","date":"2024-10-12","arxiv_id":"2410.09421","n_code_links":0,"syntology":{"ran":5,"of":7,"n_ran_checked":0,"n_instrument":5,"unverified":2,"pointer_only":1,"phrase":"5 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; 5 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/context-aware-adapter-tuning-for-few-shot","slug":"context-aware-adapter-tuning-for-few-shot","title":"Context-Aware Adapter Tuning for Few-Shot Relation Learning in Knowledge Graphs","date":"2024-10-11","arxiv_id":"2410.09123","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"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) · 0 unverified","official":{"repos":["liuran998/RelAdapter"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/mathcoder2-better-math-reasoning-from","slug":"mathcoder2-better-math-reasoning-from","title":"MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code","date":"2024-10-10","arxiv_id":"2410.08196","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":8,"n_instrument":1,"unverified":2,"pointer_only":11,"phrase":"9 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mathllm/mathcoder2"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/itercomp-iterative-composition-aware-feedback","slug":"itercomp-iterative-composition-aware-feedback","title":"IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation","date":"2024-10-09","arxiv_id":"2410.07171","n_code_links":2,"syntology":{"ran":11,"of":18,"n_ran_checked":8,"n_instrument":3,"unverified":7,"pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","official":{"repos":["yangling0818/itercomp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/pad-personalized-alignment-at-decoding-time","slug":"pad-personalized-alignment-at-decoding-time","title":"PAD: Personalized Alignment of LLMs at Decoding-Time","date":"2024-10-05","arxiv_id":"2410.04070","n_code_links":0,"syntology":{"ran":4,"of":8,"n_ran_checked":4,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":null}},{"paper":"/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","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"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","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"]}}},{"paper":"/paper/geometric-representation-condition-improves","slug":"geometric-representation-condition-improves","title":"Geometric Representation Condition Improves Equivariant Molecule Generation","date":"2024-10-04","arxiv_id":"2410.03655","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":8,"n_instrument":3,"unverified":2,"pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 4 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["GraphPKU/GeoRCG"],"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"]}}},{"paper":"/paper/oscillatory-state-space-models","slug":"oscillatory-state-space-models","title":"Oscillatory State-Space Models","date":"2024-10-04","arxiv_id":"2410.03943","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":1,"n_instrument":3,"unverified":4,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 4 unverified","official":null}},{"paper":"/paper/llm-topla-efficient-llm-ensemble-by","slug":"llm-topla-efficient-llm-ensemble-by","title":"LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity","date":"2024-10-04","arxiv_id":"2410.03953","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":8,"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) · 3 unverified","official":{"repos":["git-disl/llm-topla"],"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":["official"]}}},{"paper":"/paper/understanding-and-mitigating-miscalibration","slug":"understanding-and-mitigating-miscalibration","title":"Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models","date":"2024-10-03","arxiv_id":"2410.02681","n_code_links":1,"syntology":{"ran":4,"of":9,"n_ran_checked":1,"n_instrument":3,"unverified":5,"pointer_only":6,"phrase":"4 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; 3 where Syntology's instrument failed) · 5 unverified","official":null}},{"paper":"/paper/helmet-how-to-evaluate-long-context-language","slug":"helmet-how-to-evaluate-long-context-language","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","date":"2024-10-03","arxiv_id":"2410.02694","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":4,"n_instrument":2,"unverified":4,"pointer_only":2,"phrase":"6 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["princeton-nlp/helmet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-simple-but-strong-baseline-for-sounding","slug":"a-simple-but-strong-baseline-for-sounding","title":"A Simple but Strong Baseline for Sounding Video Generation: Effective Adaptation of Audio and Video Diffusion Models for Joint Generation","date":"2024-09-26","arxiv_id":"2409.17550","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":4,"n_instrument":4,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 3 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sonyresearch/svg_baseline"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/zero-shot-detection-of-llm-generated-text","slug":"zero-shot-detection-of-llm-generated-text","title":"Zero-Shot Detection of LLM-Generated Text using Token Cohesiveness","date":"2024-09-25","arxiv_id":"2409.16914","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"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","official":{"repos":["shixuan-ma/tocsin"],"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"]}}},{"paper":"/paper/neural-symbolic-collaborative-distillation","slug":"neural-symbolic-collaborative-distillation","title":"Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks","date":"2024-09-20","arxiv_id":"2409.13203","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":7,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["xnhyacinth/nesycd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":7,"n_instrument":4,"unverified":3,"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","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"]}}},{"paper":"/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","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"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","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"]}}},{"paper":"/paper/kolmogorov-arnold-transformer","slug":"kolmogorov-arnold-transformer","title":"Kolmogorov-Arnold Transformer","date":"2024-09-16","arxiv_id":"2409.10594","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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","official":{"repos":["Adamdad/kat"],"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"]}}},{"paper":"/paper/operator-learning-with-gaussian-processes","slug":"operator-learning-with-gaussian-processes","title":"Operator Learning with Gaussian Processes","date":"2024-09-06","arxiv_id":"2409.04538","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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","official":{"repos":["bostanabad-research-group/gp-for-operator-learning"],"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"]}}},{"paper":"/paper/sparse-rewards-can-self-train-dialogue-agents","slug":"sparse-rewards-can-self-train-dialogue-agents","title":"Sparse Rewards Can Self-Train Dialogue Agents","date":"2024-09-06","arxiv_id":"2409.04617","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"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","official":{"repos":["asappresearch/josh-llm-simulation-training"],"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"]}}},{"paper":"/paper/language-adaptation-on-a-tight-academic","slug":"language-adaptation-on-a-tight-academic","title":"Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough","date":"2024-08-28","arxiv_id":"2408.15793","n_code_links":1,"syntology":{"ran":13,"of":19,"n_ran_checked":12,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"13 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; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["konstantinjdobler/tight-budget-llm-adaptation"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/wait-that-s-not-an-option-llms-robustness","slug":"wait-that-s-not-an-option-llms-robustness","title":"Wait, that's not an option: LLMs Robustness with Incorrect Multiple-Choice Options","date":"2024-08-27","arxiv_id":"2409.00113","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":{"repos":["gracjangoral/when-all-options-are-wrong"],"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"]}}},{"paper":"/paper/agentmove-predicting-human-mobility-anywhere","slug":"agentmove-predicting-human-mobility-anywhere","title":"AgentMove: Predicting Human Mobility Anywhere Using Large Language Model based Agentic Framework","date":"2024-08-26","arxiv_id":"2408.13986","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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","official":{"repos":["tsinghua-fib-lab/agentmove"],"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"]}}},{"paper":"/paper/learning-unknowns-from-unknowns-diversified","slug":"learning-unknowns-from-unknowns-diversified","title":"Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognition","date":"2024-08-23","arxiv_id":"2408.13373","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":1,"n_instrument":1,"unverified":4,"pointer_only":2,"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) · 4 unverified","official":{"repos":["icgy96/dnpg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/critique-out-loud-reward-models","slug":"critique-out-loud-reward-models","title":"Critique-out-Loud Reward Models","date":"2024-08-21","arxiv_id":"2408.11791","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"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","official":{"repos":["zankner/cloud"],"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"]}}},{"paper":"/paper/selective-prompt-anchoring-for-code","slug":"selective-prompt-anchoring-for-code","title":"Selective Prompt Anchoring for Code Generation","date":"2024-08-17","arxiv_id":"2408.09121","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":3,"n_instrument":4,"unverified":4,"pointer_only":1,"phrase":"7 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; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["magic-yuantian/selective-prompt-anchoring"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/xgen-mm-blip-3-a-family-of-open-large","slug":"xgen-mm-blip-3-a-family-of-open-large","title":"xGen-MM (BLIP-3): A Family of Open Large Multimodal Models","date":"2024-08-16","arxiv_id":"2408.08872","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"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","official":null}},{"paper":"/paper/i-sheep-self-alignment-of-llm-from-scratch","slug":"i-sheep-self-alignment-of-llm-from-scratch","title":"I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm","date":"2024-08-15","arxiv_id":"2408.08072","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":8,"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) · 2 unverified","official":{"repos":["multimodal-art-projection/I-SHEEP"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/controlnext-powerful-and-efficient-control","slug":"controlnext-powerful-and-efficient-control","title":"ControlNeXt: Powerful and Efficient Control for Image and Video Generation","date":"2024-08-12","arxiv_id":"2408.06070","n_code_links":1,"syntology":{"ran":4,"of":9,"n_ran_checked":3,"n_instrument":1,"unverified":5,"pointer_only":2,"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) · 5 unverified","official":{"repos":["dvlab-research/controlnext"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/2408-02900","slug":"2408-02900","title":"MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine","date":"2024-08-06","arxiv_id":"2408.02900","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":5,"n_instrument":3,"unverified":0,"pointer_only":8,"phrase":"8 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["UCSC-VLAA/MedTrinity-25M"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/2408-03314","slug":"2408-03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","date":"2024-08-06","arxiv_id":"2408.03314","n_code_links":3,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":8,"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) · 3 unverified","official":null}},{"paper":"/paper/2408-01584","slug":"2408-01584","title":"GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS","date":"2024-08-02","arxiv_id":"2408.01584","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["emerge-lab/gpudrive"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/do-llms-really-adapt-to-domains-an-ontology","slug":"do-llms-really-adapt-to-domains-an-ontology","title":"Do LLMs Really Adapt to Domains? An Ontology Learning Perspective","date":"2024-07-29","arxiv_id":"2407.19998","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":7,"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) · 4 unverified","official":{"repos":["boschresearch/llm-vs-gibberish-ontologies"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-training-with-direct-preference","slug":"self-training-with-direct-preference","title":"Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning","date":"2024-07-25","arxiv_id":"2407.18248","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["tianduowang/dpo-st"],"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"]}}},{"paper":"/paper/large-language-model-for-verilog-generation","slug":"large-language-model-for-verilog-generation","title":"Large Language Model for Verilog Generation with Code-Structure-Guided Reinforcement Learning","date":"2024-07-21","arxiv_id":"2407.18271","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"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","official":{"repos":["CatIIIIIIII/veriseek"],"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"]}}},{"paper":"/paper/system-1-x-learning-to-balance-fast-and-slow","slug":"system-1-x-learning-to-balance-fast-and-slow","title":"System-1.x: Learning to Balance Fast and Slow Planning with Language Models","date":"2024-07-19","arxiv_id":"2407.14414","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["swarnaHub/System-1.x"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/catastrophic-goodhart-regularizing-rlhf-with","slug":"catastrophic-goodhart-regularizing-rlhf-with","title":"Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification","date":"2024-07-19","arxiv_id":"2407.14503","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["tkwa/catastrophic-goodhart"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/evaluating-language-models-as-risk-scores","slug":"evaluating-language-models-as-risk-scores","title":"Evaluating language models as risk scores","date":"2024-07-19","arxiv_id":"2407.14614","n_code_links":1,"syntology":{"ran":11,"of":16,"n_ran_checked":11,"n_instrument":0,"unverified":5,"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) · 5 unverified","official":{"repos":["socialfoundations/folktexts"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/adaptive-foundation-models-for-online","slug":"adaptive-foundation-models-for-online","title":"Scalable Exploration via Ensemble++","date":"2024-07-18","arxiv_id":"2407.13195","n_code_links":2,"syntology":{"ran":5,"of":8,"n_ran_checked":3,"n_instrument":2,"unverified":3,"pointer_only":8,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["szrlee/GPT-HyperAgent","szrlee/ensemble_plus_plus"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/agentpoison-red-teaming-llm-agents-via","slug":"agentpoison-red-teaming-llm-agents-via","title":"AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases","date":"2024-07-17","arxiv_id":"2407.12784","n_code_links":1,"syntology":{"ran":16,"of":19,"n_ran_checked":15,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["BillChan226/AgentPoison"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/adalog-post-training-quantization-for-vision","slug":"adalog-post-training-quantization-for-vision","title":"AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer","date":"2024-07-17","arxiv_id":"2407.12951","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["GoatWu/AdaLog"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/lami-detr-open-vocabulary-detection-with","slug":"lami-detr-open-vocabulary-detection-with","title":"LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction","date":"2024-07-16","arxiv_id":"2407.11335","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eternaldolphin/lami-detr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/optimizing-kv-cache-eviction-in-llms-adaptive","slug":"optimizing-kv-cache-eviction-in-llms-adaptive","title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","date":"2024-07-16","arxiv_id":"2407.11550","n_code_links":2,"syntology":{"ran":1,"of":5,"n_ran_checked":0,"n_instrument":1,"unverified":4,"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) · 4 unverified","official":{"repos":["ffy0/adakv","NVIDIA/kvpress"],"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"]}}},{"paper":"/paper/xedgeai-a-human-centered-industrial","slug":"xedgeai-a-human-centered-industrial","title":"XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach","date":"2024-07-16","arxiv_id":"2407.11771","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":11,"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","official":{"repos":["analytics-everywhere-lab/vqixai"],"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"]}}},{"paper":"/paper/enhancing-retrieval-and-managing-retrieval-a","slug":"enhancing-retrieval-and-managing-retrieval-a","title":"Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems","date":"2024-07-15","arxiv_id":"2407.10670","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ancientshi/erm4"],"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"]}}},{"paper":"/paper/paligemma-a-versatile-3b-vlm-for-transfer","slug":"paligemma-a-versatile-3b-vlm-for-transfer","title":"PaliGemma: A versatile 3B VLM for transfer","date":"2024-07-10","arxiv_id":"2407.07726","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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","official":{"repos":["google-research/big_vision"],"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"]}}},{"paper":"/paper/efficientqat-efficient-quantization-aware","slug":"efficientqat-efficient-quantization-aware","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","date":"2024-07-10","arxiv_id":"2407.11062","n_code_links":1,"syntology":{"ran":4,"of":9,"n_ran_checked":2,"n_instrument":2,"unverified":5,"pointer_only":2,"phrase":"4 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; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["opengvlab/efficientqat"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/inversecoder-unleashing-the-power-of","slug":"inversecoder-unleashing-the-power-of","title":"InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct","date":"2024-07-08","arxiv_id":"2407.05700","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":11,"n_instrument":0,"unverified":0,"pointer_only":11,"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) · 0 unverified","official":{"repos":["wyt2000/InverseCoder"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mamba-fscil-dynamic-adaptation-with-selective","slug":"mamba-fscil-dynamic-adaptation-with-selective","title":"Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning","date":"2024-07-08","arxiv_id":"2407.06136","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":3,"n_instrument":1,"unverified":4,"pointer_only":8,"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) · 4 unverified","official":{"repos":["xiaojieli0903/mamba-fscil"],"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"]}}},{"paper":"/paper/me-myself-and-ai-the-situational-awareness","slug":"me-myself-and-ai-the-situational-awareness","title":"Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs","date":"2024-07-05","arxiv_id":"2407.04694","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"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","official":{"repos":["lrudl/sad"],"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"]}}},{"paper":"/paper/are-large-language-models-consistent-over","slug":"are-large-language-models-consistent-over","title":"Are Large Language Models Consistent over Value-laden Questions?","date":"2024-07-03","arxiv_id":"2407.02996","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":{"repos":["jlcmoore/ValueConsistency"],"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"]}}},{"paper":"/paper/hrsam-efficiently-segment-anything-in-high","slug":"hrsam-efficiently-segment-anything-in-high","title":"HRSAM: Efficient Interactive Segmentation in High-Resolution Images","date":"2024-07-02","arxiv_id":"2407.02109","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":10,"phrase":"8 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["youhuang67/high-resolution-segment-anything"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"220604024b309fb84fe44d0ffb1e2b36bc342f95f319718a543ed0a16a4e31a9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}