{"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-modelling/papers/6","list_of":"/task/language-modelling","task":"Language Modelling","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":6,"pages_in_order":177,"rows_per_page":100,"rows":[501,600],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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-modelling","prev":"/task/language-modelling/papers/5","next":"/task/language-modelling/papers/7","papers":[{"url":"/paper/grounding-of-textual-phrases-in-images-by","slug":"grounding-of-textual-phrases-in-images-by","title":"Grounding of Textual Phrases in Images by Reconstruction","date":"2015-11-12","arxiv_id":"1511.03745","repositories_listed":3,"syntology":null},{"url":"/paper/the-goldilocks-principle-reading-childrens","slug":"the-goldilocks-principle-reading-childrens","title":"The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations","date":"2015-11-07","arxiv_id":"1511.02301","repositories_listed":3,"syntology":null},{"url":"/paper/unifying-visual-semantic-embeddings-with","slug":"unifying-visual-semantic-embeddings-with","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","date":"2014-11-10","arxiv_id":"1411.2539","repositories_listed":3,"syntology":null},{"url":"/paper/one-billion-word-benchmark-for-measuring","slug":"one-billion-word-benchmark-for-measuring","title":"One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling","date":"2013-12-11","arxiv_id":"1312.3005","repositories_listed":3,"syntology":null},{"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/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/llamea-bo-a-large-language-model-evolutionary","slug":"llamea-bo-a-large-language-model-evolutionary","title":"LLaMEA-BO: A Large Language Model Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms","date":"2025-05-27","arxiv_id":"2505.21034","repositories_listed":2,"syntology":null},{"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/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/wirelessagent-large-language-model-agents-for-1","slug":"wirelessagent-large-language-model-agents-for-1","title":"WirelessAgent: Large Language Model Agents for Intelligent Wireless Networks","date":"2025-05-02","arxiv_id":"2505.01074","repositories_listed":2,"syntology":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/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/generalized-few-shot-3d-point-cloud","slug":"generalized-few-shot-3d-point-cloud","title":"Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model","date":"2025-03-20","arxiv_id":"2503.16282","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/generalized-few-shot-3d-point-cloud#ran","syntology_url":"https://syntology.ai/paper/2503.16282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16282"}},"official":{"repos":["zhaochongan/gfs-vl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/smoldocling-an-ultra-compact-vision-language","slug":"smoldocling-an-ultra-compact-vision-language","title":"SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion","date":"2025-03-14","arxiv_id":"2503.11576","repositories_listed":2,"syntology":null},{"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/textgames-learning-to-self-play-text-based","slug":"textgames-learning-to-self-play-text-based","title":"TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model Reasoning","date":"2025-02-25","arxiv_id":"2502.18431","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/textgames-learning-to-self-play-text-based#ran","syntology_url":"https://syntology.ai/paper/2502.18431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18431"}},"official":{"repos":["fhudi/textgames"],"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":["listed","official"]}}},{"url":"/paper/the-fft-strikes-back-an-efficient-alternative","slug":"the-fft-strikes-back-an-efficient-alternative","title":"SPECTRE: An FFT-Based Efficient Drop-In Replacement to Self-Attention for Long Contexts","date":"2025-02-25","arxiv_id":"2502.18394","repositories_listed":2,"syntology":null},{"url":"/paper/reproducing-nevir-negation-in-neural","slug":"reproducing-nevir-negation-in-neural","title":"Reproducing NevIR: Negation in Neural Information Retrieval","date":"2025-02-19","arxiv_id":"2502.13506","repositories_listed":2,"syntology":null},{"url":"/paper/ras-retrieval-and-structuring-for-knowledge","slug":"ras-retrieval-and-structuring-for-knowledge","title":"RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation","date":"2025-02-16","arxiv_id":"2502.10996","repositories_listed":2,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"8 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ras-retrieval-and-structuring-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2502.10996","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.10996"}},"official":{"repos":["pat-jj/ras","pat-jj/Retrieval-And-Structure"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["community","official"]}}},{"url":"/paper/scaling-up-test-time-compute-with-latent","slug":"scaling-up-test-time-compute-with-latent","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","date":"2025-02-07","arxiv_id":"2502.05171","repositories_listed":2,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":4,"phrase":"10 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/scaling-up-test-time-compute-with-latent#ran","syntology_url":"https://syntology.ai/paper/2502.05171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05171"}},"official":{"repos":["seal-rg/recurrent-pretraining"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/great-models-think-alike-and-this-undermines","slug":"great-models-think-alike-and-this-undermines","title":"Great Models Think Alike and this Undermines AI Oversight","date":"2025-02-06","arxiv_id":"2502.04313","repositories_listed":2,"syntology":null},{"url":"/paper/overcoming-vision-language-model-challenges","slug":"overcoming-vision-language-model-challenges","title":"Overcoming Vision Language Model Challenges in Diagram Understanding: A Proof-of-Concept with XML-Driven Large Language Models Solutions","date":"2025-02-05","arxiv_id":"2502.04389","repositories_listed":2,"syntology":null},{"url":"/paper/low-rank-adapting-models-for-sparse","slug":"low-rank-adapting-models-for-sparse","title":"Low-Rank Adapting Models for Sparse Autoencoders","date":"2025-01-31","arxiv_id":"2501.19406","repositories_listed":2,"syntology":null},{"url":"/paper/s1-simple-test-time-scaling","slug":"s1-simple-test-time-scaling","title":"s1: Simple test-time scaling","date":"2025-01-31","arxiv_id":"2501.19393","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/s1-simple-test-time-scaling#ran","syntology_url":"https://syntology.ai/paper/2501.19393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.19393"}},"official":{"repos":["simplescaling/s1"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/atla-selene-mini-a-general-purpose-evaluation","slug":"atla-selene-mini-a-general-purpose-evaluation","title":"Atla Selene Mini: A General Purpose Evaluation Model","date":"2025-01-27","arxiv_id":"2501.17195","repositories_listed":2,"syntology":null},{"url":"/paper/fixing-imbalanced-attention-to-mitigate-in","slug":"fixing-imbalanced-attention-to-mitigate-in","title":"PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model","date":"2025-01-21","arxiv_id":"2501.12206","repositories_listed":2,"syntology":null},{"url":"/paper/vargpt-unified-understanding-and-generation","slug":"vargpt-unified-understanding-and-generation","title":"VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model","date":"2025-01-21","arxiv_id":"2501.12327","repositories_listed":2,"syntology":null},{"url":"/paper/lavcap-llm-based-audio-visual-captioning","slug":"lavcap-llm-based-audio-visual-captioning","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","date":"2025-01-16","arxiv_id":"2501.09291","repositories_listed":2,"syntology":null},{"url":"/paper/segmenting-text-and-learning-their-rewards","slug":"segmenting-text-and-learning-their-rewards","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model","date":"2025-01-06","arxiv_id":"2501.02790","repositories_listed":2,"syntology":null},{"url":"/paper/virgo-a-preliminary-exploration-on","slug":"virgo-a-preliminary-exploration-on","title":"Virgo: A Preliminary Exploration on Reproducing o1-like MLLM","date":"2025-01-03","arxiv_id":"2501.01904","repositories_listed":2,"syntology":null},{"url":"/paper/training-software-engineering-agents-and","slug":"training-software-engineering-agents-and","title":"Training Software Engineering Agents and Verifiers with SWE-Gym","date":"2024-12-30","arxiv_id":"2412.21139","repositories_listed":2,"syntology":null},{"url":"/paper/yulan-mini-an-open-data-efficient-language","slug":"yulan-mini-an-open-data-efficient-language","title":"YuLan-Mini: An Open Data-efficient Language Model","date":"2024-12-23","arxiv_id":"2412.17743","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/yulan-mini-an-open-data-efficient-language#ran","syntology_url":"https://syntology.ai/paper/2412.17743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.17743"}},"official":{"repos":["ruc-gsai/yulan-mini"],"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","unlocated"]}}},{"url":"/paper/ecg-byte-a-tokenizer-for-end-to-end","slug":"ecg-byte-a-tokenizer-for-end-to-end","title":"ECG-Byte: A Tokenizer for End-to-End Generative Electrocardiogram Language Modeling","date":"2024-12-18","arxiv_id":"2412.14373","repositories_listed":2,"syntology":null},{"url":"/paper/batchtopk-sparse-autoencoders","slug":"batchtopk-sparse-autoencoders","title":"BatchTopK Sparse Autoencoders","date":"2024-12-09","arxiv_id":"2412.06410","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/batchtopk-sparse-autoencoders#ran","syntology_url":"https://syntology.ai/paper/2412.06410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06410"}},"official":{"repos":["bartbussmann/batchtopk"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-language-models-as-synthetic-data","slug":"evaluating-language-models-as-synthetic-data","title":"Evaluating Language Models as Synthetic Data Generators","date":"2024-12-04","arxiv_id":"2412.03679","repositories_listed":2,"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/evaluating-language-models-as-synthetic-data#ran","syntology_url":"https://syntology.ai/paper/2412.03679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03679"}},"official":{"repos":["neulab/data-agora"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/flair-vlm-with-fine-grained-language-informed","slug":"flair-vlm-with-fine-grained-language-informed","title":"FLAIR: VLM with Fine-grained Language-informed Image Representations","date":"2024-12-04","arxiv_id":"2412.03561","repositories_listed":2,"syntology":{"n":20,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":20,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/flair-vlm-with-fine-grained-language-informed#ran","syntology_url":"https://syntology.ai/paper/2412.03561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03561"}},"official":{"repos":["explainableml/flair"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/remote-sensing-temporal-vision-language","slug":"remote-sensing-temporal-vision-language","title":"Remote Sensing Temporal Vision-Language Models: A Comprehensive Survey","date":"2024-12-03","arxiv_id":"2412.02573","repositories_listed":2,"syntology":null},{"url":"/paper/cls-attention-is-all-you-need-for-training","slug":"cls-attention-is-all-you-need-for-training","title":"Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs","date":"2024-12-02","arxiv_id":"2412.01818","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cls-attention-is-all-you-need-for-training#ran","syntology_url":"https://syntology.ai/paper/2412.01818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01818"}},"official":{"repos":["theia-4869/fastervlm","theia-4869/vispruner"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pushing-the-limits-of-large-language-model","slug":"pushing-the-limits-of-large-language-model","title":"Pushing the Limits of Large Language Model Quantization via the Linearity Theorem","date":"2024-11-26","arxiv_id":"2411.17525","repositories_listed":2,"syntology":{"n":36,"n_ran":21,"n_constructed":0,"n_ran_checked":21,"n_instrument":0,"n_unverified":15,"n_honours":0,"n_violates":1,"n_no_contract":20,"n_pointer_only":1,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/pushing-the-limits-of-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2411.17525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17525"}},"official":null}},{"url":"/paper/re-bench-evaluating-frontier-ai-r-d","slug":"re-bench-evaluating-frontier-ai-r-d","title":"RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts","date":"2024-11-22","arxiv_id":"2411.15114","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/re-bench-evaluating-frontier-ai-r-d#ran","syntology_url":"https://syntology.ai/paper/2411.15114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15114"}},"official":{"repos":["METR/ai-rd-tasks","wecoai/aideml"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unlocking-state-tracking-in-linear-rnns","slug":"unlocking-state-tracking-in-linear-rnns","title":"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues","date":"2024-11-19","arxiv_id":"2411.12537","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unlocking-state-tracking-in-linear-rnns#ran","syntology_url":"https://syntology.ai/paper/2411.12537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12537"}},"official":{"repos":["automl/unlocking_state_tracking"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learn-from-downstream-and-be-yourself-in","slug":"learn-from-downstream-and-be-yourself-in","title":"Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning","date":"2024-11-17","arxiv_id":"2411.10928","repositories_listed":2,"syntology":null},{"url":"/paper/llm-neo-parameter-efficient-knowledge","slug":"llm-neo-parameter-efficient-knowledge","title":"LLM-Neo: Parameter Efficient Knowledge Distillation for Large Language Models","date":"2024-11-11","arxiv_id":"2411.06839","repositories_listed":2,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-neo-parameter-efficient-knowledge#ran","syntology_url":"https://syntology.ai/paper/2411.06839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06839"}},"official":null}},{"url":"/paper/training-neural-networks-as-recognizers-of","slug":"training-neural-networks-as-recognizers-of","title":"Training Neural Networks as Recognizers of Formal Languages","date":"2024-11-11","arxiv_id":"2411.07107","repositories_listed":2,"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/training-neural-networks-as-recognizers-of#ran","syntology_url":"https://syntology.ai/paper/2411.07107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07107"}},"official":{"repos":["rycolab/flare","rycolab/neural-network-recognizers"],"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/plan-on-graph-self-correcting-adaptive","slug":"plan-on-graph-self-correcting-adaptive","title":"Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs","date":"2024-10-31","arxiv_id":"2410.23875","repositories_listed":2,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"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) · 5 unverified","sample_list":"/paper/plan-on-graph-self-correcting-adaptive#ran","syntology_url":"https://syntology.ai/paper/2410.23875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23875"}},"official":{"repos":["liyichen-cly/pog"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/graphteam-facilitating-large-language-model","slug":"graphteam-facilitating-large-language-model","title":"GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration","date":"2024-10-23","arxiv_id":"2410.18032","repositories_listed":2,"syntology":null},{"url":"/paper/papillon-privacy-preservation-from-internet","slug":"papillon-privacy-preservation-from-internet","title":"PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles","date":"2024-10-22","arxiv_id":"2410.17127","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/papillon-privacy-preservation-from-internet#ran","syntology_url":"https://syntology.ai/paper/2410.17127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17127"}},"official":{"repos":["columbia-nlp-lab/papillon","siyan-sylvia-li/papillon"],"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/pldr-llm-large-language-model-from-power-law","slug":"pldr-llm-large-language-model-from-power-law","title":"PLDR-LLM: Large Language Model from Power Law Decoder Representations","date":"2024-10-22","arxiv_id":"2410.16703","repositories_listed":2,"syntology":null},{"url":"/paper/improve-vision-language-model-chain-of","slug":"improve-vision-language-model-chain-of","title":"Improve Vision Language Model Chain-of-thought Reasoning","date":"2024-10-21","arxiv_id":"2410.16198","repositories_listed":2,"syntology":{"n":22,"n_ran":18,"n_constructed":0,"n_ran_checked":13,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":3,"n_no_contract":10,"n_pointer_only":22,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 3 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/improve-vision-language-model-chain-of#ran","syntology_url":"https://syntology.ai/paper/2410.16198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.16198"}},"official":{"repos":["riflezhang/llava-reasoner-dpo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/toward-guidance-free-ar-visual-generation-via","slug":"toward-guidance-free-ar-visual-generation-via","title":"Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment","date":"2024-10-12","arxiv_id":"2410.09347","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/toward-guidance-free-ar-visual-generation-via#ran","syntology_url":"https://syntology.ai/paper/2410.09347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09347"}},"official":{"repos":["thu-ml/cca","FoundationVision/VAR"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/baichuan-omni-technical-report","slug":"baichuan-omni-technical-report","title":"Baichuan-Omni Technical Report","date":"2024-10-11","arxiv_id":"2410.08565","repositories_listed":2,"syntology":null},{"url":"/paper/enhancing-multi-step-reasoning-abilities-of","slug":"enhancing-multi-step-reasoning-abilities-of","title":"Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization","date":"2024-10-11","arxiv_id":"2410.09302","repositories_listed":2,"syntology":null},{"url":"/paper/oneref-unified-one-tower-expression-grounding","slug":"oneref-unified-one-tower-expression-grounding","title":"OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling","date":"2024-10-10","arxiv_id":"2410.08021","repositories_listed":2,"syntology":{"n":16,"n_ran":11,"n_constructed":7,"n_ran_checked":7,"n_instrument":4,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"11 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/oneref-unified-one-tower-expression-grounding#ran","syntology_url":"https://syntology.ai/paper/2410.08021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08021"}},"official":{"repos":["linhuixiao/oneref"],"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":["listed","official"]}}},{"url":"/paper/simplicity-prevails-rethinking-negative","slug":"simplicity-prevails-rethinking-negative","title":"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning","date":"2024-10-09","arxiv_id":"2410.07163","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/simplicity-prevails-rethinking-negative#ran","syntology_url":"https://syntology.ai/paper/2410.07163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07163"}},"official":{"repos":["OPTML-Group/Unlearn-Simple"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/differential-transformer","slug":"differential-transformer","title":"Differential Transformer","date":"2024-10-07","arxiv_id":"2410.05258","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/differential-transformer#ran","syntology_url":"https://syntology.ai/paper/2410.05258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05258"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/improver-agent-based-automated-proof","slug":"improver-agent-based-automated-proof","title":"ImProver: Agent-Based Automated Proof Optimization","date":"2024-10-07","arxiv_id":"2410.04753","repositories_listed":2,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/improver-agent-based-automated-proof#ran","syntology_url":"https://syntology.ai/paper/2410.04753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04753"}},"official":{"repos":["riyazahuja/ImProver"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/colacare-enhancing-electronic-health-record","slug":"colacare-enhancing-electronic-health-record","title":"ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration","date":"2024-10-03","arxiv_id":"2410.02551","repositories_listed":2,"syntology":null},{"url":"/paper/fan-fourier-analysis-networks","slug":"fan-fourier-analysis-networks","title":"FAN: Fourier Analysis Networks","date":"2024-10-03","arxiv_id":"2410.02675","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"6 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fan-fourier-analysis-networks#ran","syntology_url":"https://syntology.ai/paper/2410.02675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02675"}},"official":{"repos":["yihongdong/fan"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["community","listed","official"]}}},{"url":"/paper/large-language-model-empowered-embedding","slug":"large-language-model-empowered-embedding","title":"LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation","date":"2024-09-30","arxiv_id":"2409.19925","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/large-language-model-empowered-embedding#ran","syntology_url":"https://syntology.ai/paper/2409.19925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19925"}},"official":{"repos":["applied-machine-learning-lab/llmemb","liuqidong07/LLMEmb"],"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/cascade-prompt-learning-for-vision-language","slug":"cascade-prompt-learning-for-vision-language","title":"Cascade Prompt Learning for Vision-Language Model Adaptation","date":"2024-09-26","arxiv_id":"2409.17805","repositories_listed":2,"syntology":null},{"url":"/paper/data-prep-kit-getting-your-data-ready-for-llm","slug":"data-prep-kit-getting-your-data-ready-for-llm","title":"Data-Prep-Kit: getting your data ready for LLM application development","date":"2024-09-26","arxiv_id":"2409.18164","repositories_listed":2,"syntology":null},{"url":"/paper/enigma-enhanced-interactive-generative-model","slug":"enigma-enhanced-interactive-generative-model","title":"EnIGMA: Enhanced Interactive Generative Model Agent for CTF Challenges","date":"2024-09-24","arxiv_id":"2409.16165","repositories_listed":2,"syntology":null},{"url":"/paper/2409-13740","slug":"2409-13740","title":"Language agents achieve superhuman synthesis of scientific knowledge","date":"2024-09-10","arxiv_id":"2409.13740","repositories_listed":2,"syntology":null},{"url":"/paper/alignment-aware-model-extraction-attacks-on","slug":"alignment-aware-model-extraction-attacks-on","title":"\"Yes, My LoRD.\" Guiding Language Model Extraction with Locality Reinforced Distillation","date":"2024-09-04","arxiv_id":"2409.02718","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/alignment-aware-model-extraction-attacks-on#ran","syntology_url":"https://syntology.ai/paper/2409.02718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02718"}},"official":{"repos":["liangzid/alignmentextraction","liangzid/lord-mea"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/olmoe-open-mixture-of-experts-language-models","slug":"olmoe-open-mixture-of-experts-language-models","title":"OLMoE: Open Mixture-of-Experts Language Models","date":"2024-09-03","arxiv_id":"2409.02060","repositories_listed":2,"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/olmoe-open-mixture-of-experts-language-models#ran","syntology_url":"https://syntology.ai/paper/2409.02060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02060"}},"official":{"repos":["allenai/OLMoE"],"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/recoverable-compression-a-multimodal-vision","slug":"recoverable-compression-a-multimodal-vision","title":"Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information","date":"2024-09-02","arxiv_id":"2409.01179","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/recoverable-compression-a-multimodal-vision#ran","syntology_url":"https://syntology.ai/paper/2409.01179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.01179"}},"official":{"repos":["banjiuyufen/recoverablecompression","banjiuyufen/Recoverable-Compression"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/the-mamba-in-the-llama-distilling-and","slug":"the-mamba-in-the-llama-distilling-and","title":"The Mamba in the Llama: Distilling and Accelerating Hybrid Models","date":"2024-08-27","arxiv_id":"2408.15237","repositories_listed":2,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":5,"phrase":"9 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; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/the-mamba-in-the-llama-distilling-and#ran","syntology_url":"https://syntology.ai/paper/2408.15237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15237"}},"official":{"repos":["itsdaniele/speculative_mamba","jxiw/mambainllama"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/pedestrian-attribute-recognition-a-new","slug":"pedestrian-attribute-recognition-a-new","title":"Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework","date":"2024-08-19","arxiv_id":"2408.09720","repositories_listed":2,"syntology":null},{"url":"/paper/deepseek-prover-v1-5-harnessing-proof","slug":"deepseek-prover-v1-5-harnessing-proof","title":"DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search","date":"2024-08-15","arxiv_id":"2408.08152","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/deepseek-prover-v1-5-harnessing-proof#ran","syntology_url":"https://syntology.ai/paper/2408.08152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08152"}},"official":{"repos":["deepseek-ai/deepseek-prover-v1.5"],"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":["listed","official"]}}},{"url":"/paper/cross-platform-video-person-reid-a-new","slug":"cross-platform-video-person-reid-a-new","title":"Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach","date":"2024-08-14","arxiv_id":"2408.07500","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"0 ran · 6 unverified","sample_list":"/paper/cross-platform-video-person-reid-a-new#ran","syntology_url":"https://syntology.ai/paper/2408.07500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07500"}},"official":{"repos":["fhr-l/g2a-vreid","fhr-l/vsla-clip"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":[]}}},{"url":"/paper/the-ai-scientist-towards-fully-automated-open","slug":"the-ai-scientist-towards-fully-automated-open","title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","date":"2024-08-12","arxiv_id":"2408.06292","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":9,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-ai-scientist-towards-fully-automated-open#ran","syntology_url":"https://syntology.ai/paper/2408.06292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06292"}},"official":{"repos":["sakanaai/ai-scientist"],"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":["listed","official"]}}},{"url":"/paper/utilizing-large-language-models-to-optimize","slug":"utilizing-large-language-models-to-optimize","title":"PhishLang: A Real-Time, Fully Client-Side Phishing Detection Framework Using MobileBERT","date":"2024-08-11","arxiv_id":"2408.05667","repositories_listed":2,"syntology":null},{"url":"/paper/llm-stability-a-detailed-analysis-with-some","slug":"llm-stability-a-detailed-analysis-with-some","title":"Non-Determinism of \"Deterministic\" LLM Settings","date":"2024-08-06","arxiv_id":"2408.04667","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/llm-stability-a-detailed-analysis-with-some#ran","syntology_url":"https://syntology.ai/paper/2408.04667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04667"}},"official":{"repos":["breckbaldwin/llm-stability","Comcast/llm-stability"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-zero-shot-multimodal-machine","slug":"towards-zero-shot-multimodal-machine","title":"Towards Zero-Shot Multimodal Machine Translation","date":"2024-07-18","arxiv_id":"2407.13579","repositories_listed":2,"syntology":null},{"url":"/paper/qwen2-audio-technical-report","slug":"qwen2-audio-technical-report","title":"Qwen2-Audio Technical Report","date":"2024-07-15","arxiv_id":"2407.10759","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/qwen2-audio-technical-report#ran","syntology_url":"https://syntology.ai/paper/2407.10759","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10759"}},"official":{"repos":["qwenlm/qwen2-audio"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/illm-tsc-integration-reinforcement-learning","slug":"illm-tsc-integration-reinforcement-learning","title":"iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvement","date":"2024-07-08","arxiv_id":"2407.06025","repositories_listed":2,"syntology":null},{"url":"/paper/minference-1-0-accelerating-pre-filling-for","slug":"minference-1-0-accelerating-pre-filling-for","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","date":"2024-07-02","arxiv_id":"2407.02490","repositories_listed":2,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/minference-1-0-accelerating-pre-filling-for#ran","syntology_url":"https://syntology.ai/paper/2407.02490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02490"}},"official":{"repos":["microsoft/MInference"],"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":["listed","official"]}}},{"url":"/paper/multilingual-trolley-problems-for-language","slug":"multilingual-trolley-problems-for-language","title":"Language Model Alignment in Multilingual Trolley Problems","date":"2024-07-02","arxiv_id":"2407.02273","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multilingual-trolley-problems-for-language#ran","syntology_url":"https://syntology.ai/paper/2407.02273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02273"}},"official":{"repos":["causalNLP/moralmachine","causalnlp/multitp"],"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/learning-formal-mathematics-from-intrinsic","slug":"learning-formal-mathematics-from-intrinsic","title":"Learning Formal Mathematics From Intrinsic Motivation","date":"2024-06-30","arxiv_id":"2407.00695","repositories_listed":2,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/learning-formal-mathematics-from-intrinsic#ran","syntology_url":"https://syntology.ai/paper/2407.00695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00695"}},"official":{"repos":["gpoesia/minimo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mm-instruct-generated-visual-instructions-for","slug":"mm-instruct-generated-visual-instructions-for","title":"MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment","date":"2024-06-28","arxiv_id":"2406.19736","repositories_listed":2,"syntology":null},{"url":"/paper/long-context-transfer-from-language-to-vision","slug":"long-context-transfer-from-language-to-vision","title":"Long Context Transfer from Language to Vision","date":"2024-06-24","arxiv_id":"2406.16852","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-context-transfer-from-language-to-vision#ran","syntology_url":"https://syntology.ai/paper/2406.16852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16852"}},"official":{"repos":["evolvinglmms-lab/longva"],"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":["listed","official","unlocated"]}}},{"url":"/paper/a-llm-based-ranking-method-for-the-evaluation","slug":"a-llm-based-ranking-method-for-the-evaluation","title":"A LLM-Based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation","date":"2024-06-21","arxiv_id":"2406.15227","repositories_listed":2,"syntology":null},{"url":"/paper/autonomous-agents-for-collaborative-task","slug":"autonomous-agents-for-collaborative-task","title":"Autonomous Agents for Collaborative Task under Information Asymmetry","date":"2024-06-21","arxiv_id":"2406.14928","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/autonomous-agents-for-collaborative-task#ran","syntology_url":"https://syntology.ai/paper/2406.14928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14928"}},"official":{"repos":["thinkwee/iAgents"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/bioscan-5m-a-multimodal-dataset-for-insect","slug":"bioscan-5m-a-multimodal-dataset-for-insect","title":"BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity","date":"2024-06-18","arxiv_id":"2406.12723","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bioscan-5m-a-multimodal-dataset-for-insect#ran","syntology_url":"https://syntology.ai/paper/2406.12723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12723"}},"official":{"repos":["bioscan-ml/dataset"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["named_in_paper","official"]}}},{"url":"/paper/interpretable-preferences-via-multi-objective","slug":"interpretable-preferences-via-multi-objective","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","date":"2024-06-18","arxiv_id":"2406.12845","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/interpretable-preferences-via-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2406.12845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12845"}},"official":{"repos":["RLHFlow/RLHF-Reward-Modeling"],"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/talk-with-human-like-agents-empathetic","slug":"talk-with-human-like-agents-empathetic","title":"Talk With Human-like Agents: Empathetic Dialogue Through Perceptible Acoustic Reception and Reaction","date":"2024-06-18","arxiv_id":"2406.12707","repositories_listed":2,"syntology":null},{"url":"/paper/a-simple-and-effective-l-2-norm-based","slug":"a-simple-and-effective-l-2-norm-based","title":"A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression","date":"2024-06-17","arxiv_id":"2406.11430","repositories_listed":2,"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/a-simple-and-effective-l-2-norm-based#ran","syntology_url":"https://syntology.ai/paper/2406.11430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11430"}},"official":{"repos":["alessiodevoto/l2compress"],"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/fairer-preferences-elicit-improved-human","slug":"fairer-preferences-elicit-improved-human","title":"Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments","date":"2024-06-17","arxiv_id":"2406.11370","repositories_listed":2,"syntology":{"n":29,"n_ran":20,"n_constructed":4,"n_ran_checked":10,"n_instrument":10,"n_unverified":9,"n_honours":3,"n_violates":2,"n_no_contract":5,"n_pointer_only":2,"phrase":"20 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 2 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/fairer-preferences-elicit-improved-human#ran","syntology_url":"https://syntology.ai/paper/2406.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11370"}},"official":{"repos":["cambridgeltl/zepo"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/gama-a-large-audio-language-model-with","slug":"gama-a-large-audio-language-model-with","title":"GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities","date":"2024-06-17","arxiv_id":"2406.11768","repositories_listed":2,"syntology":null},{"url":"/paper/large-scale-transfer-learning-for-tabular","slug":"large-scale-transfer-learning-for-tabular","title":"Large Scale Transfer Learning for Tabular Data via Language Modeling","date":"2024-06-17","arxiv_id":"2406.12031","repositories_listed":2,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/large-scale-transfer-learning-for-tabular#ran","syntology_url":"https://syntology.ai/paper/2406.12031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12031"}},"official":{"repos":["mlfoundations/rtfm","mlfoundations/tabliblib"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/optimizing-instructions-and-demonstrations","slug":"optimizing-instructions-and-demonstrations","title":"Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs","date":"2024-06-17","arxiv_id":"2406.11695","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/optimizing-instructions-and-demonstrations#ran","syntology_url":"https://syntology.ai/paper/2406.11695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11695"}},"official":{"repos":["stanfordnlp/dspy"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/regularizing-hidden-states-enables-learning","slug":"regularizing-hidden-states-enables-learning","title":"Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs","date":"2024-06-14","arxiv_id":"2406.10216","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/regularizing-hidden-states-enables-learning#ran","syntology_url":"https://syntology.ai/paper/2406.10216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10216"}},"official":{"repos":["yangrui2015/generalizable-reward-model"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/unibridge-a-unified-approach-to-cross-lingual-1","slug":"unibridge-a-unified-approach-to-cross-lingual-1","title":"UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages","date":"2024-06-14","arxiv_id":"2406.09717","repositories_listed":2,"syntology":null},{"url":"/paper/llm-reading-tea-leaves-automatically","slug":"llm-reading-tea-leaves-automatically","title":"LLM Reading Tea Leaves: Automatically Evaluating Topic Models with Large Language Models","date":"2024-06-13","arxiv_id":"2406.09008","repositories_listed":2,"syntology":null},{"url":"/paper/samba-simple-hybrid-state-space-models-for","slug":"samba-simple-hybrid-state-space-models-for","title":"Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling","date":"2024-06-11","arxiv_id":"2406.07522","repositories_listed":2,"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/samba-simple-hybrid-state-space-models-for#ran","syntology_url":"https://syntology.ai/paper/2406.07522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07522"}},"official":{"repos":["microsoft/Samba","sustcsonglin/flash-linear-attention"],"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/simple-and-effective-masked-diffusion","slug":"simple-and-effective-masked-diffusion","title":"Simple and Effective Masked Diffusion Language Models","date":"2024-06-11","arxiv_id":"2406.07524","repositories_listed":2,"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/simple-and-effective-masked-diffusion#ran","syntology_url":"https://syntology.ai/paper/2406.07524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07524"}},"official":{"repos":["kuleshov-group/mdlm"],"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/crag-comprehensive-rag-benchmark","slug":"crag-comprehensive-rag-benchmark","title":"CRAG -- Comprehensive RAG Benchmark","date":"2024-06-07","arxiv_id":"2406.04744","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"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) · 0 unverified","sample_list":"/paper/crag-comprehensive-rag-benchmark#ran","syntology_url":"https://syntology.ai/paper/2406.04744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04744"}},"official":{"repos":["facebookresearch/crag"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lawgpt-a-chinese-legal-knowledge-enhanced","slug":"lawgpt-a-chinese-legal-knowledge-enhanced","title":"LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model","date":"2024-06-07","arxiv_id":"2406.04614","repositories_listed":2,"syntology":null},{"url":"/paper/your-absorbing-discrete-diffusion-secretly","slug":"your-absorbing-discrete-diffusion-secretly","title":"Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data","date":"2024-06-06","arxiv_id":"2406.03736","repositories_listed":2,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":13,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/your-absorbing-discrete-diffusion-secretly#ran","syntology_url":"https://syntology.ai/paper/2406.03736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03736"}},"official":{"repos":["ml-gsai/radd"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-based-rewriting-of-inappropriate","slug":"llm-based-rewriting-of-inappropriate","title":"LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback","date":"2024-06-05","arxiv_id":"2406.03363","repositories_listed":2,"syntology":null}],"record_sha256":"2fb872e0b75b2f71c4af942654427d0e144c148d510ab6dad8230bdb685adc8a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}