{"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/language-modeling/papers/ran/1","list_of":"/task/language-modeling","task":"Language Modeling","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":19,"rows_per_page":100,"rows":[1,100],"of":1894,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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/language-modeling/papers/ran/1","prev":null,"next":"/task/language-modeling/papers/ran/2","papers":[{"url":"/paper/open-source-planning-control-system-with","slug":"open-source-planning-control-system-with","title":"Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery","date":"2025-07-09","arxiv_id":"2507.07257","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":0,"n_no_contract":1,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/open-source-planning-control-system-with#ran","syntology_url":"https://syntology.ai/paper/2507.07257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.07257"}},"official":{"repos":["cmbagents/cmbagent"],"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":["community","official"]}}},{"url":"/paper/differential-mamba","slug":"differential-mamba","title":"Differential Mamba","date":"2025-07-08","arxiv_id":"2507.06204","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/differential-mamba#ran","syntology_url":"https://syntology.ai/paper/2507.06204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.06204"}},"official":{"repos":["nadavsc/diff-mamba"],"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/evaluating-morphological-alignment-of","slug":"evaluating-morphological-alignment-of","title":"Evaluating Morphological Alignment of Tokenizers in 70 Languages","date":"2025-07-08","arxiv_id":"2507.06378","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":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","sample_list":"/paper/evaluating-morphological-alignment-of#ran","syntology_url":"https://syntology.ai/paper/2507.06378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.06378"}},"official":{"repos":["catherinearnett/morphscore"],"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/desta2-5-audio-toward-general-purpose-large","slug":"desta2-5-audio-toward-general-purpose-large","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","date":"2025-07-03","arxiv_id":"2507.02768","repositories_listed":2,"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/desta2-5-audio-toward-general-purpose-large#ran","syntology_url":"https://syntology.ai/paper/2507.02768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.02768"}},"official":{"repos":["kehanlu/desta2.5-audio"],"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/sharpzo-hybrid-sharpness-aware-vision","slug":"sharpzo-hybrid-sharpness-aware-vision","title":"SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes","date":"2025-06-26","arxiv_id":"2506.20990","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"6 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; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/sharpzo-hybrid-sharpness-aware-vision#ran","syntology_url":"https://syntology.ai/paper/2506.20990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.20990"}},"official":{"repos":["yifanycc/sharpzo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/agentstealth-reinforcing-large-language-model","slug":"agentstealth-reinforcing-large-language-model","title":"AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text","date":"2025-06-26","arxiv_id":"2506.22508","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_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) · 2 unverified","sample_list":"/paper/agentstealth-reinforcing-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2506.22508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.22508"}},"official":{"repos":["tsinghua-fib-lab/agentstealth"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/language-modeling-by-language-models","slug":"language-modeling-by-language-models","title":"Language Modeling by Language Models","date":"2025-06-25","arxiv_id":"2506.20249","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/language-modeling-by-language-models#ran","syntology_url":"https://syntology.ai/paper/2506.20249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.20249"}},"official":{"repos":["allenai/genesys"],"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/octothinker-mid-training-incentivizes","slug":"octothinker-mid-training-incentivizes","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","date":"2025-06-25","arxiv_id":"2506.20512","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/octothinker-mid-training-incentivizes#ran","syntology_url":"https://syntology.ai/paper/2506.20512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.20512"}},"official":{"repos":["gair-nlp/octothinker"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-community-driven-agents-for-machine","slug":"towards-community-driven-agents-for-machine","title":"Towards Community-Driven Agents for Machine Learning Engineering","date":"2025-06-25","arxiv_id":"2506.20640","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/towards-community-driven-agents-for-machine#ran","syntology_url":"https://syntology.ai/paper/2506.20640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.20640"}},"official":{"repos":["comind-ml/comind"],"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"]}}},{"url":"/paper/sharegpt-4o-image-aligning-multimodal-models","slug":"sharegpt-4o-image-aligning-multimodal-models","title":"ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation","date":"2025-06-22","arxiv_id":"2506.18095","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/sharegpt-4o-image-aligning-multimodal-models#ran","syntology_url":"https://syntology.ai/paper/2506.18095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.18095"}},"official":{"repos":["freedomintelligence/sharegpt-4o-image"],"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"]}}},{"url":"/paper/watermarking-autoregressive-image-generation","slug":"watermarking-autoregressive-image-generation","title":"Watermarking Autoregressive Image Generation","date":"2025-06-19","arxiv_id":"2506.16349","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":5,"n_pointer_only":8,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/watermarking-autoregressive-image-generation#ran","syntology_url":"https://syntology.ai/paper/2506.16349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.16349"}},"official":{"repos":["facebookresearch/wmar"],"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":["found_in_text","official","unlocated"]}}},{"url":"/paper/lmr-bench-evaluating-llm-agent-s-ability-on","slug":"lmr-bench-evaluating-llm-agent-s-ability-on","title":"LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research","date":"2025-06-19","arxiv_id":"2506.17335","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/lmr-bench-evaluating-llm-agent-s-ability-on#ran","syntology_url":"https://syntology.ai/paper/2506.17335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.17335"}},"official":{"repos":["du-nlp-lab/lmr-bench"],"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/ras-eval-a-comprehensive-benchmark-for","slug":"ras-eval-a-comprehensive-benchmark-for","title":"RAS-Eval: A Comprehensive Benchmark for Security Evaluation of LLM Agents in Real-World Environments","date":"2025-06-18","arxiv_id":"2506.15253","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":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","sample_list":"/paper/ras-eval-a-comprehensive-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2506.15253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.15253"}},"official":{"repos":["lanzer-tree/ras-eval"],"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/show-o2-improved-native-unified-multimodal","slug":"show-o2-improved-native-unified-multimodal","title":"Show-o2: Improved Native Unified Multimodal Models","date":"2025-06-18","arxiv_id":"2506.15564","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":5,"phrase":"11 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/show-o2-improved-native-unified-multimodal#ran","syntology_url":"https://syntology.ai/paper/2506.15564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.15564"}},"official":{"repos":["showlab/show-o"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sampling-from-your-language-model-one-byte-at","slug":"sampling-from-your-language-model-one-byte-at","title":"Sampling from Your Language Model One Byte at a Time","date":"2025-06-17","arxiv_id":"2506.14123","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":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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/sampling-from-your-language-model-one-byte-at#ran","syntology_url":"https://syntology.ai/paper/2506.14123","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.14123"}},"official":{"repos":["sewoonglab/byte-sampler"],"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/diffusionblocks-blockwise-training-for","slug":"diffusionblocks-blockwise-training-for","title":"DiffusionBlocks: Blockwise Training for Generative Models via Score-Based Diffusion","date":"2025-06-17","arxiv_id":"2506.14202","repositories_listed":0,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/diffusionblocks-blockwise-training-for#ran","syntology_url":"https://syntology.ai/paper/2506.14202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.14202"}},"official":null}},{"url":"/paper/from-bytes-to-ideas-language-modeling-with","slug":"from-bytes-to-ideas-language-modeling-with","title":"From Bytes to Ideas: Language Modeling with Autoregressive U-Nets","date":"2025-06-17","arxiv_id":"2506.14761","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"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","sample_list":"/paper/from-bytes-to-ideas-language-modeling-with#ran","syntology_url":"https://syntology.ai/paper/2506.14761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.14761"}},"official":{"repos":["facebookresearch/lingua"],"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"]}}},{"url":"/paper/seqpe-transformer-with-sequential-position","slug":"seqpe-transformer-with-sequential-position","title":"SeqPE: Transformer with Sequential Position Encoding","date":"2025-06-16","arxiv_id":"2506.13277","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":5,"n_pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/seqpe-transformer-with-sequential-position#ran","syntology_url":"https://syntology.ai/paper/2506.13277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13277"}},"official":{"repos":["ghrua/seqpe"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vis-shepherd-constructing-critic-for-llm","slug":"vis-shepherd-constructing-critic-for-llm","title":"VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation","date":"2025-06-16","arxiv_id":"2506.13326","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"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","sample_list":"/paper/vis-shepherd-constructing-critic-for-llm#ran","syntology_url":"https://syntology.ai/paper/2506.13326","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13326"}},"official":{"repos":["bopan3/vis-shepherd"],"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"]}}},{"url":"/paper/intent-factored-generation-unleashing-the","slug":"intent-factored-generation-unleashing-the","title":"Intent Factored Generation: Unleashing the Diversity in Your Language Model","date":"2025-06-11","arxiv_id":"2506.09659","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/intent-factored-generation-unleashing-the#ran","syntology_url":"https://syntology.ai/paper/2506.09659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.09659"}},"official":{"repos":["flairox/ifg"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2506-08967","slug":"2506-08967","title":"Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model","date":"2025-06-10","arxiv_id":"2506.08967","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":2,"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/2506-08967#ran","syntology_url":"https://syntology.ai/paper/2506.08967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08967"}},"official":null}},{"url":"/paper/safe-finding-sparse-and-flat-minima-to","slug":"safe-finding-sparse-and-flat-minima-to","title":"SAFE: Finding Sparse and Flat Minima to Improve Pruning","date":"2025-06-07","arxiv_id":"2506.06866","repositories_listed":2,"syntology":{"n":18,"n_ran":10,"n_constructed":1,"n_ran_checked":4,"n_instrument":6,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"10 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/safe-finding-sparse-and-flat-minima-to#ran","syntology_url":"https://syntology.ai/paper/2506.06866","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.06866"}},"official":{"repos":["LOG-postech/safe-torch","log-postech/safe-jax"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/zeroth-order-optimization-finds-flat-minima","slug":"zeroth-order-optimization-finds-flat-minima","title":"Zeroth-Order Optimization Finds Flat Minima","date":"2025-06-05","arxiv_id":"2506.05454","repositories_listed":0,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/zeroth-order-optimization-finds-flat-minima#ran","syntology_url":"https://syntology.ai/paper/2506.05454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.05454"}},"official":null}},{"url":"/paper/magicodec-simple-masked-gaussian-injected","slug":"magicodec-simple-masked-gaussian-injected","title":"MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation","date":"2025-05-31","arxiv_id":"2506.00385","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/magicodec-simple-masked-gaussian-injected#ran","syntology_url":"https://syntology.ai/paper/2506.00385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.00385"}},"official":{"repos":["ereboas/magicodec"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/chameleon-a-flexible-data-mixing-framework","slug":"chameleon-a-flexible-data-mixing-framework","title":"Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning","date":"2025-05-30","arxiv_id":"2505.24844","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":1,"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/chameleon-a-flexible-data-mixing-framework#ran","syntology_url":"https://syntology.ai/paper/2505.24844","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.24844"}},"official":{"repos":["lions-epfl/chameleon"],"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/reasongen-r1-cot-for-autoregressive-image","slug":"reasongen-r1-cot-for-autoregressive-image","title":"ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL","date":"2025-05-30","arxiv_id":"2505.24875","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 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; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/reasongen-r1-cot-for-autoregressive-image#ran","syntology_url":"https://syntology.ai/paper/2505.24875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.24875"}},"official":null}},{"url":"/paper/discriminative-policy-optimization-for-token","slug":"discriminative-policy-optimization-for-token","title":"Discriminative Policy Optimization for Token-Level Reward Models","date":"2025-05-29","arxiv_id":"2505.23363","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"2 ran (of which 1 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/discriminative-policy-optimization-for-token#ran","syntology_url":"https://syntology.ai/paper/2505.23363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23363"}},"official":{"repos":["homzer/q-rm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/uni-mumer-unified-multi-task-fine-tuning-of","slug":"uni-mumer-unified-multi-task-fine-tuning-of","title":"Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition","date":"2025-05-29","arxiv_id":"2505.23566","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":1,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uni-mumer-unified-multi-task-fine-tuning-of#ran","syntology_url":"https://syntology.ai/paper/2505.23566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23566"}},"official":{"repos":["bflameswift/uni-mumer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/actor-critic-based-online-data-mixing-for","slug":"actor-critic-based-online-data-mixing-for","title":"Actor-Critic based Online Data Mixing For Language Model Pre-Training","date":"2025-05-29","arxiv_id":"2505.23878","repositories_listed":0,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/actor-critic-based-online-data-mixing-for#ran","syntology_url":"https://syntology.ai/paper/2505.23878","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23878"}},"official":null}},{"url":"/paper/pretraining-language-models-to-ponder-in","slug":"pretraining-language-models-to-ponder-in","title":"Pretraining Language Models to Ponder in Continuous Space","date":"2025-05-27","arxiv_id":"2505.20674","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"6 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pretraining-language-models-to-ponder-in#ran","syntology_url":"https://syntology.ai/paper/2505.20674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20674"}},"official":{"repos":["lumia-group/ponderinglm"],"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","unlocated"]}}},{"url":"/paper/let-me-think-a-long-chain-of-thought-can-be","slug":"let-me-think-a-long-chain-of-thought-can-be","title":"Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones","date":"2025-05-27","arxiv_id":"2505.21825","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/let-me-think-a-long-chain-of-thought-can-be#ran","syntology_url":"https://syntology.ai/paper/2505.21825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.21825"}},"official":{"repos":["seyedparsa/let-me-think"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/wina-weight-informed-neuron-activation-for","slug":"wina-weight-informed-neuron-activation-for","title":"WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference","date":"2025-05-26","arxiv_id":"2505.19427","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/wina-weight-informed-neuron-activation-for#ran","syntology_url":"https://syntology.ai/paper/2505.19427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19427"}},"official":{"repos":["microsoft/wina"],"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/can-compressed-llms-truly-act-an-empirical","slug":"can-compressed-llms-truly-act-an-empirical","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","date":"2025-05-26","arxiv_id":"2505.19433","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-compressed-llms-truly-act-an-empirical#ran","syntology_url":"https://syntology.ai/paper/2505.19433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19433"}},"official":{"repos":["pprp/acbench"],"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","unlocated"]}}},{"url":"/paper/causal-llava-causal-disentanglement-for","slug":"causal-llava-causal-disentanglement-for","title":"Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models","date":"2025-05-26","arxiv_id":"2505.19474","repositories_listed":1,"syntology":{"n":19,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":11,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"8 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; 4 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/causal-llava-causal-disentanglement-for#ran","syntology_url":"https://syntology.ai/paper/2505.19474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19474"}},"official":{"repos":["ignisavium/causal-llava"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/unifying-multimodal-large-language-model","slug":"unifying-multimodal-large-language-model","title":"Unifying Multimodal Large Language Model Capabilities and Modalities via Model Merging","date":"2025-05-26","arxiv_id":"2505.19892","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/unifying-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2505.19892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19892"}},"official":{"repos":["walkerworldpeace/mllmerging"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/attention-you-vision-language-model-could-be","slug":"attention-you-vision-language-model-could-be","title":"Attention! You Vision Language Model Could Be Maliciously Manipulated","date":"2025-05-26","arxiv_id":"2505.19911","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/attention-you-vision-language-model-could-be#ran","syntology_url":"https://syntology.ai/paper/2505.19911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19911"}},"official":null}},{"url":"/paper/rearank-reasoning-re-ranking-agent-via","slug":"rearank-reasoning-re-ranking-agent-via","title":"REARANK: Reasoning Re-ranking Agent via Reinforcement Learning","date":"2025-05-26","arxiv_id":"2505.20046","repositories_listed":1,"syntology":{"n":18,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":4,"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) · 6 unverified","sample_list":"/paper/rearank-reasoning-re-ranking-agent-via#ran","syntology_url":"https://syntology.ai/paper/2505.20046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20046"}},"official":{"repos":["lezhang7/rearank"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/imgedit-a-unified-image-editing-dataset-and","slug":"imgedit-a-unified-image-editing-dataset-and","title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","date":"2025-05-26","arxiv_id":"2505.20275","repositories_listed":2,"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":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","sample_list":"/paper/imgedit-a-unified-image-editing-dataset-and#ran","syntology_url":"https://syntology.ai/paper/2505.20275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20275"}},"official":{"repos":["pku-yuangroup/imgedit"],"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/chain-of-zoom-extreme-super-resolution-via","slug":"chain-of-zoom-extreme-super-resolution-via","title":"Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment","date":"2025-05-24","arxiv_id":"2505.18600","repositories_listed":0,"syntology":{"n":20,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"12 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; 7 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/chain-of-zoom-extreme-super-resolution-via#ran","syntology_url":"https://syntology.ai/paper/2505.18600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18600"}},"official":null}},{"url":"/paper/partition-generative-modeling-masked-modeling","slug":"partition-generative-modeling-masked-modeling","title":"Partition Generative Modeling: Masked Modeling Without Masks","date":"2025-05-24","arxiv_id":"2505.18883","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":12,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/partition-generative-modeling-masked-modeling#ran","syntology_url":"https://syntology.ai/paper/2505.18883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18883"}},"official":{"repos":["kuleshov-group/mdlm"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/decoupled-visual-interpretation-and","slug":"decoupled-visual-interpretation-and","title":"Decoupled Visual Interpretation and Linguistic Reasoning for Math Problem Solving","date":"2025-05-23","arxiv_id":"2505.17609","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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) · 0 unverified","sample_list":"/paper/decoupled-visual-interpretation-and#ran","syntology_url":"https://syntology.ai/paper/2505.17609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17609"}},"official":{"repos":["guozix/dvlr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/inference-time-decomposition-of-activations","slug":"inference-time-decomposition-of-activations","title":"Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models","date":"2025-05-23","arxiv_id":"2505.17769","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/inference-time-decomposition-of-activations#ran","syntology_url":"https://syntology.ai/paper/2505.17769","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17769"}},"official":{"repos":["pleask/itda"],"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/daily-omni-towards-audio-visual-reasoning","slug":"daily-omni-towards-audio-visual-reasoning","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","date":"2025-05-23","arxiv_id":"2505.17862","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/daily-omni-towards-audio-visual-reasoning#ran","syntology_url":"https://syntology.ai/paper/2505.17862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17862"}},"official":{"repos":["lliar-liar/daily-omni"],"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":["unlocated"]}}},{"url":"/paper/danmakutppbench-a-multi-modal-benchmark-for","slug":"danmakutppbench-a-multi-modal-benchmark-for","title":"DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding","date":"2025-05-23","arxiv_id":"2505.18411","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/danmakutppbench-a-multi-modal-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2505.18411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18411"}},"official":{"repos":["frenkie-chiang/danmakutppbench"],"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":["unlocated"]}}},{"url":"/paper/beyond-prompt-engineering-robust-behavior","slug":"beyond-prompt-engineering-robust-behavior","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","date":"2025-05-23","arxiv_id":"2505.20322","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":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) · 0 unverified","sample_list":"/paper/beyond-prompt-engineering-robust-behavior#ran","syntology_url":"https://syntology.ai/paper/2505.20322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20322"}},"official":{"repos":["zjunlp/steer-target-atoms"],"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/saturn-sat-based-reinforcement-learning-to","slug":"saturn-sat-based-reinforcement-learning-to","title":"SATURN: SAT-based Reinforcement Learning to Unleash Language Model Reasoning","date":"2025-05-22","arxiv_id":"2505.16368","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/saturn-sat-based-reinforcement-learning-to#ran","syntology_url":"https://syntology.ai/paper/2505.16368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16368"}},"official":{"repos":["gtxygyzb/saturn-code"],"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":["community","official"]}}},{"url":"/paper/path-attention-position-encoding-via","slug":"path-attention-position-encoding-via","title":"PaTH Attention: Position Encoding via Accumulating Householder Transformations","date":"2025-05-22","arxiv_id":"2505.16381","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":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/path-attention-position-encoding-via#ran","syntology_url":"https://syntology.ai/paper/2505.16381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16381"}},"official":{"repos":["fla-org/flash-linear-attention","sustcsonglin/flash-linear-attention"],"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/lavida-a-large-diffusion-language-model-for","slug":"lavida-a-large-diffusion-language-model-for","title":"LaViDa: A Large Diffusion Language Model for Multimodal Understanding","date":"2025-05-22","arxiv_id":"2505.16839","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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","sample_list":"/paper/lavida-a-large-diffusion-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2505.16839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16839"}},"official":{"repos":["jacklishufan/lavida"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/dimple-discrete-diffusion-multimodal-large","slug":"dimple-discrete-diffusion-multimodal-large","title":"Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding","date":"2025-05-22","arxiv_id":"2505.16990","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/dimple-discrete-diffusion-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2505.16990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16990"}},"official":{"repos":["yu-rp/dimple"],"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":["unlocated"]}}},{"url":"/paper/lost-in-benchmarks-rethinking-large-language","slug":"lost-in-benchmarks-rethinking-large-language","title":"Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory","date":"2025-05-21","arxiv_id":"2505.15055","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/lost-in-benchmarks-rethinking-large-language#ran","syntology_url":"https://syntology.ai/paper/2505.15055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15055"}},"official":{"repos":["Joe-Hall-Lee/PSN-IRT"],"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/lmgame-bench-how-good-are-llms-at-playing","slug":"lmgame-bench-how-good-are-llms-at-playing","title":"lmgame-Bench: How Good are LLMs at Playing Games?","date":"2025-05-21","arxiv_id":"2505.15146","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":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/lmgame-bench-how-good-are-llms-at-playing#ran","syntology_url":"https://syntology.ai/paper/2505.15146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15146"}},"official":{"repos":["lmgame-org/gamingagent"],"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/trajectory-bellman-residual-minimization-a","slug":"trajectory-bellman-residual-minimization-a","title":"Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning","date":"2025-05-21","arxiv_id":"2505.15311","repositories_listed":0,"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/trajectory-bellman-residual-minimization-a#ran","syntology_url":"https://syntology.ai/paper/2505.15311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15311"}},"official":null}},{"url":"/paper/cad-coder-an-open-source-vision-language","slug":"cad-coder-an-open-source-vision-language","title":"CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation","date":"2025-05-20","arxiv_id":"2505.14646","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":0,"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/cad-coder-an-open-source-vision-language#ran","syntology_url":"https://syntology.ai/paper/2505.14646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14646"}},"official":{"repos":["anniedoris/cad-coder"],"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/the-traitors-deception-and-trust-in-multi","slug":"the-traitors-deception-and-trust-in-multi","title":"The Traitors: Deception and Trust in Multi-Agent Language Model Simulations","date":"2025-05-19","arxiv_id":"2505.12923","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":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) · 0 unverified","sample_list":"/paper/the-traitors-deception-and-trust-in-multi#ran","syntology_url":"https://syntology.ai/paper/2505.12923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12923"}},"official":{"repos":["pedrocurvo/thetraitors"],"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/efficient-speech-language-modeling-via-energy","slug":"efficient-speech-language-modeling-via-energy","title":"Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space","date":"2025-05-19","arxiv_id":"2505.13181","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 ran (of which 3 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) · 0 unverified","sample_list":"/paper/efficient-speech-language-modeling-via-energy#ran","syntology_url":"https://syntology.ai/paper/2505.13181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13181"}},"official":{"repos":["ictnlp/sled-tts"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/r3-robust-rubric-agnostic-reward-models","slug":"r3-robust-rubric-agnostic-reward-models","title":"R3: Robust Rubric-Agnostic Reward Models","date":"2025-05-19","arxiv_id":"2505.13388","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/r3-robust-rubric-agnostic-reward-models#ran","syntology_url":"https://syntology.ai/paper/2505.13388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13388"}},"official":{"repos":["rubricreward/r3"],"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/self-destructive-language-model","slug":"self-destructive-language-model","title":"Self-Destructive Language Model","date":"2025-05-18","arxiv_id":"2505.12186","repositories_listed":0,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/self-destructive-language-model#ran","syntology_url":"https://syntology.ai/paper/2505.12186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12186"}},"official":null}},{"url":"/paper/internal-causal-mechanisms-robustly-predict","slug":"internal-causal-mechanisms-robustly-predict","title":"Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors","date":"2025-05-17","arxiv_id":"2505.11770","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/internal-causal-mechanisms-robustly-predict#ran","syntology_url":"https://syntology.ai/paper/2505.11770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.11770"}},"official":{"repos":["explanare/ood-prediction"],"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"]}}},{"url":"/paper/2505-10861","slug":"2505-10861","title":"Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM","date":"2025-05-16","arxiv_id":"2505.10861","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":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) · 0 unverified","sample_list":"/paper/2505-10861#ran","syntology_url":"https://syntology.ai/paper/2505.10861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.10861"}},"official":{"repos":["duongnhatthang/llamagym"],"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/token-level-uncertainty-estimation-for-large","slug":"token-level-uncertainty-estimation-for-large","title":"Token-Level Uncertainty Estimation for Large Language Model Reasoning","date":"2025-05-16","arxiv_id":"2505.11737","repositories_listed":0,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/token-level-uncertainty-estimation-for-large#ran","syntology_url":"https://syntology.ai/paper/2505.11737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.11737"}},"official":null}},{"url":"/paper/multi-token-prediction-needs-registers","slug":"multi-token-prediction-needs-registers","title":"Multi-Token Prediction Needs Registers","date":"2025-05-15","arxiv_id":"2505.10518","repositories_listed":1,"syntology":{"n":20,"n_ran":18,"n_constructed":0,"n_ran_checked":11,"n_instrument":7,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"18 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; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-token-prediction-needs-registers#ran","syntology_url":"https://syntology.ai/paper/2505.10518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.10518"}},"official":{"repos":["nasosger/mutor"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/guidedquant-large-language-model-quantization","slug":"guidedquant-large-language-model-quantization","title":"GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance","date":"2025-05-11","arxiv_id":"2505.07004","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":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) · 1 unverified","sample_list":"/paper/guidedquant-large-language-model-quantization#ran","syntology_url":"https://syntology.ai/paper/2505.07004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07004"}},"official":{"repos":["snu-mllab/guidedquant"],"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/radio-rate-distortion-optimization-for-large","slug":"radio-rate-distortion-optimization-for-large","title":"Radio: Rate-Distortion Optimization for Large Language Model Compression","date":"2025-05-05","arxiv_id":"2505.03031","repositories_listed":0,"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":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) · 1 unverified","sample_list":"/paper/radio-rate-distortion-optimization-for-large#ran","syntology_url":"https://syntology.ai/paper/2505.03031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.03031"}},"official":null}},{"url":"/paper/adcare-vlm-leveraging-large-vision-language","slug":"adcare-vlm-leveraging-large-vision-language","title":"AdCare-VLM: Leveraging Large Vision Language Model (LVLM) to Monitor Long-Term Medication Adherence and Care","date":"2025-05-01","arxiv_id":"2505.00275","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/adcare-vlm-leveraging-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2505.00275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.00275"}},"official":{"repos":["asad14053/AdCare-VLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/rwkv-x-a-linear-complexity-hybrid-language","slug":"rwkv-x-a-linear-complexity-hybrid-language","title":"RWKV-X: A Linear Complexity Hybrid Language Model","date":"2025-04-30","arxiv_id":"2504.21463","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"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) · 4 unverified","sample_list":"/paper/rwkv-x-a-linear-complexity-hybrid-language#ran","syntology_url":"https://syntology.ai/paper/2504.21463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21463"}},"official":{"repos":["howard-hou/rwkv-x"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/mf-llm-simulating-collective-decision","slug":"mf-llm-simulating-collective-decision","title":"MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework","date":"2025-04-30","arxiv_id":"2504.21582","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":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","sample_list":"/paper/mf-llm-simulating-collective-decision#ran","syntology_url":"https://syntology.ai/paper/2504.21582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21582"}},"official":{"repos":["Miracle1207/Mean-Field-LLM"],"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/reviving-any-subset-autoregressive-models","slug":"reviving-any-subset-autoregressive-models","title":"Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding","date":"2025-04-29","arxiv_id":"2504.20456","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":0,"n_no_contract":1,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/reviving-any-subset-autoregressive-models#ran","syntology_url":"https://syntology.ai/paper/2504.20456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.20456"}},"official":{"repos":["gabeguo/any-order-speculative-decoding"],"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/unidetox-universal-detoxification-of-large","slug":"unidetox-universal-detoxification-of-large","title":"UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation","date":"2025-04-29","arxiv_id":"2504.20500","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/unidetox-universal-detoxification-of-large#ran","syntology_url":"https://syntology.ai/paper/2504.20500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.20500"}},"official":{"repos":["EminLU/UniDetox"],"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/virology-capabilities-test-vct-a-multimodal","slug":"virology-capabilities-test-vct-a-multimodal","title":"Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark","date":"2025-04-21","arxiv_id":"2504.16137","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":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/virology-capabilities-test-vct-a-multimodal#ran","syntology_url":"https://syntology.ai/paper/2504.16137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.16137"}},"official":null}},{"url":"/paper/sotopia-s4-a-user-friendly-system-for","slug":"sotopia-s4-a-user-friendly-system-for","title":"SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation","date":"2025-04-19","arxiv_id":"2504.16122","repositories_listed":0,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/sotopia-s4-a-user-friendly-system-for#ran","syntology_url":"https://syntology.ai/paper/2504.16122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.16122"}},"official":null}},{"url":"/paper/learning-to-attribute-with-attention","slug":"learning-to-attribute-with-attention","title":"Learning to Attribute with Attention","date":"2025-04-18","arxiv_id":"2504.13752","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-attribute-with-attention#ran","syntology_url":"https://syntology.ai/paper/2504.13752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13752"}},"official":{"repos":["madrylab/at2"],"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/perception-encoder-the-best-visual-embeddings","slug":"perception-encoder-the-best-visual-embeddings","title":"Perception Encoder: The best visual embeddings are not at the output of the network","date":"2025-04-17","arxiv_id":"2504.13181","repositories_listed":1,"syntology":{"n":18,"n_ran":14,"n_constructed":0,"n_ran_checked":9,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":2,"phrase":"14 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/perception-encoder-the-best-visual-embeddings#ran","syntology_url":"https://syntology.ai/paper/2504.13181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13181"}},"official":null}},{"url":"/paper/dids-domain-impact-aware-data-sampling-for","slug":"dids-domain-impact-aware-data-sampling-for","title":"DIDS: Domain Impact-aware Data Sampling for Large Language Model Training","date":"2025-04-17","arxiv_id":"2504.13227","repositories_listed":0,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 3 unverified","sample_list":"/paper/dids-domain-impact-aware-data-sampling-for#ran","syntology_url":"https://syntology.ai/paper/2504.13227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13227"}},"official":null}},{"url":"/paper/the-scalability-of-simplicity-empirical","slug":"the-scalability-of-simplicity-empirical","title":"The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer","date":"2025-04-14","arxiv_id":"2504.10462","repositories_listed":1,"syntology":{"n":9,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 7 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/the-scalability-of-simplicity-empirical#ran","syntology_url":"https://syntology.ai/paper/2504.10462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.10462"}},"official":{"repos":["bytedance/sail"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/internvl3-exploring-advanced-training-and","slug":"internvl3-exploring-advanced-training-and","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","date":"2025-04-14","arxiv_id":"2504.10479","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":1,"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/internvl3-exploring-advanced-training-and#ran","syntology_url":"https://syntology.ai/paper/2504.10479","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.10479"}},"official":{"repos":["opengvlab/internvl"],"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"]}}},{"url":"/paper/segearth-r1-geospatial-pixel-reasoning-via","slug":"segearth-r1-geospatial-pixel-reasoning-via","title":"SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model","date":"2025-04-13","arxiv_id":"2504.09644","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":1,"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/segearth-r1-geospatial-pixel-reasoning-via#ran","syntology_url":"https://syntology.ai/paper/2504.09644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.09644"}},"official":{"repos":["earth-insights/segearth-r1"],"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/pact-pruning-and-clustering-based-token","slug":"pact-pruning-and-clustering-based-token","title":"PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models","date":"2025-04-11","arxiv_id":"2504.08966","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":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) · 1 unverified","sample_list":"/paper/pact-pruning-and-clustering-based-token#ran","syntology_url":"https://syntology.ai/paper/2504.08966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.08966"}},"official":{"repos":["orailix/pact"],"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/glus-global-local-reasoning-unified-into-a","slug":"glus-global-local-reasoning-unified-into-a","title":"GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation","date":"2025-04-10","arxiv_id":"2504.07962","repositories_listed":1,"syntology":{"n":12,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"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) · 9 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/glus-global-local-reasoning-unified-into-a#ran","syntology_url":"https://syntology.ai/paper/2504.07962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07962"}},"official":null}},{"url":"/paper/taste-text-aligned-speech-tokenization-and","slug":"taste-text-aligned-speech-tokenization-and","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","date":"2025-04-09","arxiv_id":"2504.07053","repositories_listed":2,"syntology":{"n":20,"n_ran":14,"n_constructed":0,"n_ran_checked":12,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":20,"phrase":"14 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; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/taste-text-aligned-speech-tokenization-and#ran","syntology_url":"https://syntology.ai/paper/2504.07053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07053"}},"official":{"repos":["mtkresearch/taste-spokenlm"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/skywork-r1v-pioneering-multimodal-reasoning","slug":"skywork-r1v-pioneering-multimodal-reasoning","title":"Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought","date":"2025-04-08","arxiv_id":"2504.05599","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":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/skywork-r1v-pioneering-multimodal-reasoning#ran","syntology_url":"https://syntology.ai/paper/2504.05599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.05599"}},"official":null}},{"url":"/paper/co-bench-benchmarking-language-model-agents","slug":"co-bench-benchmarking-language-model-agents","title":"CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization","date":"2025-04-06","arxiv_id":"2504.04310","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/co-bench-benchmarking-language-model-agents#ran","syntology_url":"https://syntology.ai/paper/2504.04310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.04310"}},"official":{"repos":["sunnweiwei/co-bench"],"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/scaling-video-language-models-to-10k-frames","slug":"scaling-video-language-models-to-10k-frames","title":"Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation","date":"2025-04-03","arxiv_id":"2504.02438","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/scaling-video-language-models-to-10k-frames#ran","syntology_url":"https://syntology.ai/paper/2504.02438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.02438"}},"official":{"repos":["steven-ccq/vilamp"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/representation-bending-for-large-language","slug":"representation-bending-for-large-language","title":"Representation Bending for Large Language Model Safety","date":"2025-04-02","arxiv_id":"2504.01550","repositories_listed":2,"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/representation-bending-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2504.01550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.01550"}},"official":{"repos":["aim-intelligence/repbend"],"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/bolt-boost-large-vision-language-model","slug":"bolt-boost-large-vision-language-model","title":"BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding","date":"2025-03-27","arxiv_id":"2503.21483","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/bolt-boost-large-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2503.21483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21483"}},"official":{"repos":["sming256/bolt"],"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/rethinking-vision-language-model-in-face","slug":"rethinking-vision-language-model-in-face","title":"Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector","date":"2025-03-26","arxiv_id":"2503.20188","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/rethinking-vision-language-model-in-face#ran","syntology_url":"https://syntology.ai/paper/2503.20188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20188"}},"official":{"repos":["chelsea234/m2f2_det"],"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"]}}},{"url":"/paper/cafe-unifying-representation-and-generation","slug":"cafe-unifying-representation-and-generation","title":"CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning","date":"2025-03-25","arxiv_id":"2503.19900","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cafe-unifying-representation-and-generation#ran","syntology_url":"https://syntology.ai/paper/2503.19900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19900"}},"official":{"repos":["haoyu-bu/CAFe"],"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/med3dvlm-an-efficient-vision-language-model","slug":"med3dvlm-an-efficient-vision-language-model","title":"Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis","date":"2025-03-25","arxiv_id":"2503.20047","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/med3dvlm-an-efficient-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2503.20047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20047"}},"official":{"repos":["mirthai/med3dvlm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/what-makes-a-reward-model-a-good-teacher-an","slug":"what-makes-a-reward-model-a-good-teacher-an","title":"What Makes a Reward Model a Good Teacher? An Optimization Perspective","date":"2025-03-19","arxiv_id":"2503.15477","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/what-makes-a-reward-model-a-good-teacher-an#ran","syntology_url":"https://syntology.ai/paper/2503.15477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.15477"}},"official":{"repos":["princeton-pli/what-makes-good-rm"],"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/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/valid-text-to-sql-generation-with-unification","slug":"valid-text-to-sql-generation-with-unification","title":"Valid Text-to-SQL Generation with Unification-based DeepStochLog","date":"2025-03-17","arxiv_id":"2503.13342","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":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","sample_list":"/paper/valid-text-to-sql-generation-with-unification#ran","syntology_url":"https://syntology.ai/paper/2503.13342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13342"}},"official":{"repos":["ML-KULeuven/deepstochlog-lm"],"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/matvlm-hybrid-mamba-transformer-for-efficient","slug":"matvlm-hybrid-mamba-transformer-for-efficient","title":"MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling","date":"2025-03-17","arxiv_id":"2503.13440","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"9 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/matvlm-hybrid-mamba-transformer-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2503.13440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13440"}},"official":{"repos":["hustvl/MaTVLM"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/svd-llm-v2-optimizing-singular-value","slug":"svd-llm-v2-optimizing-singular-value","title":"SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression","date":"2025-03-16","arxiv_id":"2503.12340","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/svd-llm-v2-optimizing-singular-value#ran","syntology_url":"https://syntology.ai/paper/2503.12340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.12340"}},"official":{"repos":["aiot-mlsys-lab/svd-llm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/does-your-vision-language-model-get-lost-in","slug":"does-your-vision-language-model-get-lost-in","title":"Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?","date":"2025-03-16","arxiv_id":"2503.12496","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/does-your-vision-language-model-get-lost-in#ran","syntology_url":"https://syntology.ai/paper/2503.12496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.12496"}},"official":{"repos":["dvlab-research/LSDBench"],"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"]}}},{"url":"/paper/got-unleashing-reasoning-capability-of","slug":"got-unleashing-reasoning-capability-of","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing","date":"2025-03-13","arxiv_id":"2503.10639","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/got-unleashing-reasoning-capability-of#ran","syntology_url":"https://syntology.ai/paper/2503.10639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10639"}},"official":{"repos":["rongyaofang/got"],"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/multimodal-language-modeling-for-high","slug":"multimodal-language-modeling-for-high","title":"Language-Enhanced Representation Learning for Single-Cell Transcriptomics","date":"2025-03-12","arxiv_id":"2503.09427","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":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","sample_list":"/paper/multimodal-language-modeling-for-high#ran","syntology_url":"https://syntology.ai/paper/2503.09427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09427"}},"official":{"repos":["syr-cn/scmmgpt"],"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":["unlocated"]}}},{"url":"/paper/block-diffusion-interpolating-between","slug":"block-diffusion-interpolating-between","title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models","date":"2025-03-12","arxiv_id":"2503.09573","repositories_listed":2,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":8,"phrase":"14 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/block-diffusion-interpolating-between#ran","syntology_url":"https://syntology.ai/paper/2503.09573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09573"}},"official":{"repos":["kuleshov-group/bd3lms"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/simlingo-vision-only-closed-loop-autonomous","slug":"simlingo-vision-only-closed-loop-autonomous","title":"SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment","date":"2025-03-12","arxiv_id":"2503.09594","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":8,"n_ran_checked":8,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 8 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) · 3 unverified","sample_list":"/paper/simlingo-vision-only-closed-loop-autonomous#ran","syntology_url":"https://syntology.ai/paper/2503.09594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09594"}},"official":null}},{"url":"/paper/longprolip-a-probabilistic-vision-language","slug":"longprolip-a-probabilistic-vision-language","title":"LongProLIP: A Probabilistic Vision-Language Model with Long Context Text","date":"2025-03-11","arxiv_id":"2503.08048","repositories_listed":1,"syntology":{"n":16,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":16,"phrase":"7 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; 6 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/longprolip-a-probabilistic-vision-language#ran","syntology_url":"https://syntology.ai/paper/2503.08048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08048"}},"official":{"repos":["naver-ai/prolip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":9,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/mellow-a-small-audio-language-model-for","slug":"mellow-a-small-audio-language-model-for","title":"Mellow: a small audio language model for reasoning","date":"2025-03-11","arxiv_id":"2503.08540","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mellow-a-small-audio-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2503.08540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08540"}},"official":{"repos":["soham97/mellow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/perplexity-trap-plm-based-retrievers-overrate","slug":"perplexity-trap-plm-based-retrievers-overrate","title":"Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents","date":"2025-03-11","arxiv_id":"2503.08684","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/perplexity-trap-plm-based-retrievers-overrate#ran","syntology_url":"https://syntology.ai/paper/2503.08684","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08684"}},"official":{"repos":["whydwelledonai/perplexity-trap"],"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"]}}}],"record_sha256":"d74f7894fe82d1895353f234e31cc95a4cd2377380abb41c17f3e798b0c200fa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}