{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/multi-head-attention/papers/114","list_of":"/method/multi-head-attention","method":"Multi-Head Attention","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":114,"pages_in_order":249,"rows_per_page":100,"rows":[11301,11400],"of":24855,"counts":{"archive_papers_tagged":24855,"with_a_code_link":11214,"where_syntology_ran_a_sample":3454,"not_listed_spam_title":0,"listed":24855,"listed_where_code_ran":3454,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2916,"every_run_a_failure_of_syntologys_instrument":538,"listed_with_a_run_with_no_instrument_failure":2916,"listed_every_run_a_failure_of_syntologys_instrument":538,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/multi-head-attention","prev":"/method/multi-head-attention/papers/113","next":"/method/multi-head-attention/papers/115","papers":[{"paper":"/paper/pixart-a-fast-training-of-diffusion","slug":"pixart-a-fast-training-of-diffusion","title":"PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","date":"2023-09-30","arxiv_id":"2310.00426","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["PixArt-alpha/PixArt-alpha"],"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":["listed","unlocated"]}}},{"paper":null,"slug":"pubic-symphysis-fetal-head-segmentation-using","title":"Pubic Symphysis-Fetal Head Segmentation Using Pure Transformer with Bi-level Routing Attention","date":"2023-09-30","arxiv_id":"2310.00289","n_code_links":0,"syntology":null},{"paper":"/paper/question-answering-model-for-schizophrenia","slug":"question-answering-model-for-schizophrenia","title":"Question-Answering Model for Schizophrenia Symptoms and Their Impact on Daily Life using Mental Health Forums Data","date":"2023-09-30","arxiv_id":"2310.00448","n_code_links":0,"syntology":null},{"paper":"/paper/quiz-an-arbitrary-volumetric-point-matching","slug":"quiz-an-arbitrary-volumetric-point-matching","title":"QUIZ: An Arbitrary Volumetric Point Matching Method for Medical Image Registration","date":"2023-09-30","arxiv_id":"2310.00296","n_code_links":2,"syntology":null},{"paper":"/paper/relbert-embedding-relations-with-language","slug":"relbert-embedding-relations-with-language","title":"RelBERT: Embedding Relations with Language Models","date":"2023-09-30","arxiv_id":"2310.00299","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlocking-bias-detection-leveraging","title":"Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysis","date":"2023-09-30","arxiv_id":"2310.00347","n_code_links":0,"syntology":null},{"paper":null,"slug":"upar-a-kantian-inspired-prompting-framework","title":"UPAR: A Kantian-Inspired Prompting Framework for Enhancing Large Language Model Capabilities","date":"2023-09-30","arxiv_id":"2310.01441","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-large-language-model-approach-to","title":"A Large Language Model Approach to Educational Survey Feedback Analysis","date":"2023-09-29","arxiv_id":"2309.17447","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-evaluation-of-gpt-models-for-phenotype","title":"An evaluation of GPT models for phenotype concept recognition","date":"2023-09-29","arxiv_id":"2309.17169","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-the-abilities-of-large-language","slug":"benchmarking-the-abilities-of-large-language","title":"Benchmarking the Abilities of Large Language Models for RDF Knowledge Graph Creation and Comprehension: How Well Do LLMs Speak Turtle?","date":"2023-09-29","arxiv_id":"2309.17122","n_code_links":3,"syntology":null},{"paper":"/paper/craft-customizing-llms-by-creating-and","slug":"craft-customizing-llms-by-creating-and","title":"CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets","date":"2023-09-29","arxiv_id":"2309.17428","n_code_links":2,"syntology":{"ran":0,"of":5,"n_ran_checked":0,"n_instrument":0,"unverified":5,"pointer_only":5,"phrase":"0 ran · 5 unverified","official":{"repos":["lifan-yuan/craft"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"paper":"/paper/dyval-graph-informed-dynamic-evaluation-of","slug":"dyval-graph-informed-dynamic-evaluation-of","title":"DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks","date":"2023-09-29","arxiv_id":"2309.17167","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-large-language-models-in-coding","slug":"enhancing-large-language-models-in-coding","title":"Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency","date":"2023-09-29","arxiv_id":"2309.17272","n_code_links":1,"syntology":{"ran":8,"of":14,"n_ran_checked":7,"n_instrument":1,"unverified":6,"pointer_only":0,"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) · 6 unverified","official":{"repos":["skpig/MPSC"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gsdc-transformer-an-efficient-and-effective","title":"GSDC Transformer: An Efficient and Effective Cue Fusion for Monocular Multi-Frame Depth Estimation","date":"2023-09-29","arxiv_id":"2309.17059","n_code_links":0,"syntology":null},{"paper":null,"slug":"ifast-weakly-supervised-interpretable-face","title":"IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images","date":"2023-09-29","arxiv_id":"2309.17399","n_code_links":0,"syntology":null},{"paper":null,"slug":"intuitive-or-dependent-investigating-llms","title":"Intuitive or Dependent? Investigating LLMs' Behavior Style to Conflicting Prompts","date":"2023-09-29","arxiv_id":"2309.17415","n_code_links":0,"syntology":null},{"paper":"/paper/llm-deliberation-evaluating-llms-with","slug":"llm-deliberation-evaluating-llms-with","title":"Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation","date":"2023-09-29","arxiv_id":"2309.17234","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"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) · 0 unverified","official":{"repos":["s-abdelnabi/llm-deliberation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/memory-gym-partially-observable-challenges-to","slug":"memory-gym-partially-observable-challenges-to","title":"Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents","date":"2023-09-29","arxiv_id":"2309.17207","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["marcometer/endless-memory-gym"],"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"]}}},{"paper":null,"slug":"multilingual-natural-language-processingmodel","title":"Multilingual Natural Language Processing Model for Radiology Reports -- The Summary is all you need!","date":"2023-09-29","arxiv_id":"2310.00100","n_code_links":0,"syntology":null},{"paper":null,"slug":"revolutionizing-mobile-interaction-enabling-a","title":"Revolutionizing Mobile Interaction: Enabling a 3 Billion Parameter GPT LLM on Mobile","date":"2023-09-29","arxiv_id":"2310.01434","n_code_links":0,"syntology":null},{"paper":"/paper/robots-that-can-see-leveraging-human-pose-for","slug":"robots-that-can-see-leveraging-human-pose-for","title":"Robots That Can See: Leveraging Human Pose for Trajectory Prediction","date":"2023-09-29","arxiv_id":"2309.17209","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["google-research/human-scene-transformer"],"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"]}}},{"paper":"/paper/scale-synergized-collaboration-of-asymmetric","slug":"scale-synergized-collaboration-of-asymmetric","title":"SCALE: Synergized Collaboration of Asymmetric Language Translation Engines","date":"2023-09-29","arxiv_id":"2309.17061","n_code_links":1,"syntology":null},{"paper":null,"slug":"scaling-experiments-in-self-supervised-cross","title":"Scaling Experiments in Self-Supervised Cross-Table Representation Learning","date":"2023-09-29","arxiv_id":"2309.17339","n_code_links":0,"syntology":null},{"paper":"/paper/socreval-large-language-models-with-the","slug":"socreval-large-language-models-with-the","title":"SocREval: Large Language Models with the Socratic Method for Reference-Free Reasoning Evaluation","date":"2023-09-29","arxiv_id":"2310.00074","n_code_links":1,"syntology":null},{"paper":null,"slug":"split-and-merge-aligning-position-biases-in","title":"Split and Merge: Aligning Position Biases in LLM-based Evaluators","date":"2023-09-29","arxiv_id":"2310.01432","n_code_links":0,"syntology":null},{"paper":"/paper/suspicion-agent-playing-imperfect-information","slug":"suspicion-agent-playing-imperfect-information","title":"Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4","date":"2023-09-29","arxiv_id":"2309.17277","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cr-gjx/suspicion-agent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","slug":"tora-a-tool-integrated-reasoning-agent-for","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","date":"2023-09-29","arxiv_id":"2309.17452","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":9,"n_instrument":2,"unverified":1,"pointer_only":9,"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) · 1 unverified","official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"training-and-inference-of-large-language","title":"Training and inference of large language models using 8-bit floating point","date":"2023-09-29","arxiv_id":"2309.17224","n_code_links":0,"syntology":null},{"paper":null,"slug":"trandrl-a-transformer-driven-deep","title":"TranDRL: A Transformer-Driven Deep Reinforcement Learning Enabled Prescriptive Maintenance Framework","date":"2023-09-29","arxiv_id":"2309.16935","n_code_links":0,"syntology":null},{"paper":"/paper/when-epipolar-constraint-meets-non-local-1","slug":"when-epipolar-constraint-meets-non-local-1","title":"When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo","date":"2023-09-29","arxiv_id":"2309.17218","n_code_links":1,"syntology":{"ran":8,"of":13,"n_ran_checked":4,"n_instrument":4,"unverified":5,"pointer_only":0,"phrase":"8 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; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["tqtqliu/et-mvsnet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ae-gpt-using-large-language-models-to-extract","title":"AE-GPT: Using Large Language Models to Extract Adverse Events from Surveillance Reports-A Use Case with Influenza Vaccine Adverse Events","date":"2023-09-28","arxiv_id":"2309.16150","n_code_links":0,"syntology":null},{"paper":"/paper/augmenting-transformers-with-recursively","slug":"augmenting-transformers-with-recursively","title":"Augmenting Transformers with Recursively Composed Multi-grained Representations","date":"2023-09-28","arxiv_id":"2309.16319","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ant-research/structuredlm_rtdt"],"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":["official"]}}},{"paper":"/paper/channel-vision-transformers-an-image-is-worth","slug":"channel-vision-transformers-an-image-is-worth","title":"Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words","date":"2023-09-28","arxiv_id":"2309.16108","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["insitro/channelvit"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/controllable-text-generation-with-residual","slug":"controllable-text-generation-with-residual","title":"Controllable Text Generation with Residual Memory Transformer","date":"2023-09-28","arxiv_id":"2309.16231","n_code_links":2,"syntology":null},{"paper":null,"slug":"d-3-fields-dynamic-3d-descriptor-fields-for","title":"D$^3$Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement","date":"2023-09-28","arxiv_id":"2309.16118","n_code_links":0,"syntology":null},{"paper":"/paper/deep-geometrized-cartoon-line-inbetweening-1","slug":"deep-geometrized-cartoon-line-inbetweening-1","title":"Deep Geometrized Cartoon Line Inbetweening","date":"2023-09-28","arxiv_id":"2309.16643","n_code_links":1,"syntology":null},{"paper":null,"slug":"ewastenet-a-two-stream-data-efficient-image","title":"EWasteNet: A Two-Stream Data Efficient Image Transformer Approach for E-Waste Classification","date":"2023-09-28","arxiv_id":"2311.12823","n_code_links":0,"syntology":null},{"paper":"/paper/flip-cross-domain-face-anti-spoofing-with-1","slug":"flip-cross-domain-face-anti-spoofing-with-1","title":"FLIP: Cross-domain Face Anti-spoofing with Language Guidance","date":"2023-09-28","arxiv_id":"2309.16649","n_code_links":3,"syntology":null},{"paper":"/paper/gaflow-incorporating-gaussian-attention-into-1","slug":"gaflow-incorporating-gaussian-attention-into-1","title":"GAFlow: Incorporating Gaussian Attention into Optical Flow","date":"2023-09-28","arxiv_id":"2309.16217","n_code_links":2,"syntology":{"ran":7,"of":9,"n_ran_checked":4,"n_instrument":3,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["la30/gaflow"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/gpt-fathom-benchmarking-large-language-models","slug":"gpt-fathom-benchmarking-large-language-models","title":"GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond","date":"2023-09-28","arxiv_id":"2309.16583","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["gpt-fathom/gpt-fathom"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/hallucination-reduction-in-long-input-text","slug":"hallucination-reduction-in-long-input-text","title":"Hallucination Reduction in Long Input Text Summarization","date":"2023-09-28","arxiv_id":"2309.16781","n_code_links":1,"syntology":null},{"paper":"/paper/htc-dc-net-monocular-height-estimation-from","slug":"htc-dc-net-monocular-height-estimation-from","title":"HTC-DC Net: Monocular Height Estimation from Single Remote Sensing Images","date":"2023-09-28","arxiv_id":"2309.16486","n_code_links":1,"syntology":null},{"paper":"/paper/improving-equivariance-in-state-of-the-art-1","slug":"improving-equivariance-in-state-of-the-art-1","title":"Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors","date":"2023-09-28","arxiv_id":"2309.16646","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-model-soft-ideologization-via","title":"Large Language Model Soft Ideologization via AI-Self-Consciousness","date":"2023-09-28","arxiv_id":"2309.16167","n_code_links":0,"syntology":null},{"paper":"/paper/lawbench-benchmarking-legal-knowledge-of","slug":"lawbench-benchmarking-legal-knowledge-of","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","date":"2023-09-28","arxiv_id":"2309.16289","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":{"repos":["open-compass/lawbench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-scale-recurrent-lstm-and-transformer","title":"Gated Cross-Attention Network for Depth Completion","date":"2023-09-28","arxiv_id":"2309.16301","n_code_links":0,"syntology":null},{"paper":null,"slug":"neuro-symbolic-reasoning-for-planning","title":"Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving","date":"2023-09-28","arxiv_id":"2309.16436","n_code_links":0,"syntology":null},{"paper":null,"slug":"radar-instance-transformer-reliable-moving","title":"Radar Instance Transformer: Reliable Moving Instance Segmentation in Sparse Radar Point Clouds","date":"2023-09-28","arxiv_id":"2309.16435","n_code_links":0,"syntology":null},{"paper":null,"slug":"stock-volatility-prediction-based-on","title":"Stock Volatility Prediction Based on Transformer Model Using Mixed-Frequency Data","date":"2023-09-28","arxiv_id":"2309.16196","n_code_links":0,"syntology":null},{"paper":null,"slug":"stress-testing-chain-of-thought-prompting-for","title":"Stress Testing Chain-of-Thought Prompting for Large Language Models","date":"2023-09-28","arxiv_id":"2309.16621","n_code_links":0,"syntology":null},{"paper":null,"slug":"t1-t2-relaxation-temporal-modelling-from","title":"T1/T2 relaxation temporal modelling from accelerated acquisitions using a Latent Transformer","date":"2023-09-28","arxiv_id":"2309.16853","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-aware-decision-transformer-for","title":"Uncertainty-Aware Decision Transformer for Stochastic Driving Environments","date":"2023-09-28","arxiv_id":"2309.16397","n_code_links":0,"syntology":null},{"paper":"/paper/unmasking-the-chameleons-a-benchmark-for-out","slug":"unmasking-the-chameleons-a-benchmark-for-out","title":"Unmasking the Chameleons: A Benchmark for Out-of-Distribution Detection in Medical Tabular Data","date":"2023-09-28","arxiv_id":"2309.16220","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"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) · 1 unverified","official":{"repos":["mazizmalayeri/tabmedood"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"upb-acti-detecting-conspiracies-using-fine","title":"UPB @ ACTI: Detecting Conspiracies using fine tuned Sentence Transformers","date":"2023-09-28","arxiv_id":"2309.16275","n_code_links":0,"syntology":null},{"paper":null,"slug":"uvl-a-unified-framework-for-video-tampering","title":"UVL2: A Unified Framework for Video Tampering Localization","date":"2023-09-28","arxiv_id":"2309.16126","n_code_links":0,"syntology":null},{"paper":"/paper/vision-transformers-need-registers","slug":"vision-transformers-need-registers","title":"Vision Transformers Need Registers","date":"2023-09-28","arxiv_id":"2309.16588","n_code_links":6,"syntology":{"ran":15,"of":20,"n_ran_checked":13,"n_instrument":2,"unverified":5,"pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["facebookresearch/dinov2"],"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":["listed","official"]}}},{"paper":"/paper/aperture-diffraction-for-compact-snapshot-1","slug":"aperture-diffraction-for-compact-snapshot-1","title":"Aperture Diffraction for Compact Snapshot Spectral Imaging","date":"2023-09-27","arxiv_id":"2309.16372","n_code_links":1,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["krito-ex/csst"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/chatcounselor-a-large-language-models-for","slug":"chatcounselor-a-large-language-models-for","title":"ChatCounselor: A Large Language Models for Mental Health Support","date":"2023-09-27","arxiv_id":"2309.15461","n_code_links":1,"syntology":null},{"paper":null,"slug":"hpl-vit-a-unified-perception-framework-for","title":"HPL-ViT: A Unified Perception Framework for Heterogeneous Parallel LiDARs in V2V","date":"2023-09-27","arxiv_id":"2309.15572","n_code_links":0,"syntology":null},{"paper":"/paper/improving-facade-parsing-with-vision","slug":"improving-facade-parsing-with-vision","title":"Improving Facade Parsing with Vision Transformers and Line Integration","date":"2023-09-27","arxiv_id":"2309.15523","n_code_links":1,"syntology":null},{"paper":null,"slug":"mededit-model-editing-for-medical-question","title":"MKRAG: Medical Knowledge Retrieval Augmented Generation for Medical Question Answering","date":"2023-09-27","arxiv_id":"2309.16035","n_code_links":0,"syntology":null},{"paper":"/paper/mindgpt-interpreting-what-you-see-with-non","slug":"mindgpt-interpreting-what-you-see-with-non","title":"MindGPT: Interpreting What You See with Non-invasive Brain Recordings","date":"2023-09-27","arxiv_id":"2309.15729","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":7,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["jxuanc/mindgpt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"neuromorphic-imaging-and-classification-with","title":"Neuromorphic Imaging and Classification with Graph Learning","date":"2023-09-27","arxiv_id":"2309.15627","n_code_links":0,"syntology":null},{"paper":"/paper/nlpbench-evaluating-large-language-models-on","slug":"nlpbench-evaluating-large-language-models-on","title":"NLPBench: Evaluating Large Language Models on Solving NLP Problems","date":"2023-09-27","arxiv_id":"2309.15630","n_code_links":1,"syntology":null},{"paper":"/paper/a-simple-text-to-video-model-via-transformer","slug":"a-simple-text-to-video-model-via-transformer","title":"A Simple Text to Video Model via Transformer","date":"2023-09-26","arxiv_id":"2309.14683","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-nlp-benchmark-dataset-for-assessing","title":"An NLP Benchmark Dataset for Assessing Corporate Climate Policy Engagement","date":"2023-09-26","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"balancing-computational-efficiency-and","title":"Balancing Computational Efficiency and Forecast Error in Machine Learning-based Time-Series Forecasting: Insights from Live Experiments on Meteorological Nowcasting","date":"2023-09-26","arxiv_id":"2309.15207","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-large-language-models-on-cmexam-1","slug":"benchmarking-large-language-models-on-cmexam-1","title":"Benchmarking Large Language Models on CMExam - A comprehensive Chinese Medical Exam Dataset","date":"2023-09-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/capp-130-a-corpus-of-chinese-application","slug":"capp-130-a-corpus-of-chinese-application","title":"CAPP-130: A Corpus of Chinese Application Privacy Policy Summarization and Interpretation","date":"2023-09-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-artificial","title":"Legal Question-Answering in the Indian Context: Efficacy, Challenges, and Potential of Modern AI Models","date":"2023-09-26","arxiv_id":"2309.14735","n_code_links":0,"syntology":null},{"paper":"/paper/event-stream-based-visual-object-tracking-a","slug":"event-stream-based-visual-object-tracking-a","title":"Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline","date":"2023-09-26","arxiv_id":"2309.14611","n_code_links":4,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["event-ahu/coesot","event-ahu/eventvot_benchmark","wangxiao5791509/Single_Object_Tracking_Paper_List","wangxiao5791509/VisEvent_SOT_Benchmark"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-small-language-models-with-prompt","title":"Exploring Small Language Models with Prompt-Learning Paradigm for Efficient Domain-Specific Text Classification","date":"2023-09-26","arxiv_id":"2309.14779","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-catch-an-ai-liar-lie-detection-in","slug":"how-to-catch-an-ai-liar-lie-detection-in","title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions","date":"2023-09-26","arxiv_id":"2309.15840","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["lorypack/llm-liedetector"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"leveraging-herpangina-data-to-enhance","title":"Leveraging Herpangina Data to Enhance Hospital-level Prediction of Hand-Foot-and-Mouth Disease Admissions Using UPTST","date":"2023-09-26","arxiv_id":"2309.14674","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-rank-adaptation-of-large-language-model","title":"Low-rank Adaptation of Large Language Model Rescoring for Parameter-Efficient Speech Recognition","date":"2023-09-26","arxiv_id":"2309.15223","n_code_links":0,"syntology":null},{"paper":null,"slug":"program-repair-with-minimal-edits-using","title":"Program Repair with Minimal Edits Using CodeT5","date":"2023-09-26","arxiv_id":"2309.14760","n_code_links":0,"syntology":null},{"paper":"/paper/question-answering-approach-to-evaluate-legal","slug":"question-answering-approach-to-evaluate-legal","title":"Question-Answering Approach to Evaluating Legal Summaries","date":"2023-09-26","arxiv_id":"2309.15016","n_code_links":1,"syntology":null},{"paper":"/paper/ragas-automated-evaluation-of-retrieval","slug":"ragas-automated-evaluation-of-retrieval","title":"RAGAS: Automated Evaluation of Retrieval Augmented Generation","date":"2023-09-26","arxiv_id":"2309.15217","n_code_links":3,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":null}},{"paper":"/paper/rankvicuna-zero-shot-listwise-document","slug":"rankvicuna-zero-shot-listwise-document","title":"RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models","date":"2023-09-26","arxiv_id":"2309.15088","n_code_links":3,"syntology":null},{"paper":"/paper/robust-sequential-deepfake-detection","slug":"robust-sequential-deepfake-detection","title":"Robust Sequential DeepFake Detection","date":"2023-09-26","arxiv_id":"2309.14991","n_code_links":1,"syntology":null},{"paper":"/paper/supersonic-learning-to-generate-source-code","slug":"supersonic-learning-to-generate-source-code","title":"Supersonic: Learning to Generate Source Code Optimizations in C/C++","date":"2023-09-26","arxiv_id":"2309.14846","n_code_links":1,"syntology":null},{"paper":null,"slug":"tile-classification-based-viewport-prediction","title":"Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer","date":"2023-09-26","arxiv_id":"2309.14704","n_code_links":0,"syntology":null},{"paper":null,"slug":"visit-bench-a-dynamic-benchmark-for","title":"VisIT-Bench: A Dynamic Benchmark for Evaluating Instruction-Following Vision-and-Language Models","date":"2023-09-26","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-survey-of-transformer-applications-for","slug":"a-survey-of-transformer-applications-for","title":"A survey of Transformer applications for histopathological image analysis: New developments and future directions","date":"2023-09-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"aligning-large-multimodal-models-with","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","date":"2023-09-25","arxiv_id":"2309.14525","n_code_links":0,"syntology":null},{"paper":null,"slug":"comprehensive-overview-of-named-entity","title":"Comprehensive Overview of Named Entity Recognition: Models, Domain-Specific Applications and Challenges","date":"2023-09-25","arxiv_id":"2309.14084","n_code_links":0,"syntology":null},{"paper":"/paper/data-upcycling-knowledge-distillation-for","slug":"data-upcycling-knowledge-distillation-for","title":"Data Upcycling Knowledge Distillation for Image Super-Resolution","date":"2023-09-25","arxiv_id":"2309.14162","n_code_links":1,"syntology":null},{"paper":"/paper/deepspeed-ulysses-system-optimizations-for","slug":"deepspeed-ulysses-system-optimizations-for","title":"DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models","date":"2023-09-25","arxiv_id":"2309.14509","n_code_links":6,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/egocentric-rgb-depth-action-recognition-in","slug":"egocentric-rgb-depth-action-recognition-in","title":"Egocentric RGB+Depth Action Recognition in Industry-Like Settings","date":"2023-09-25","arxiv_id":"2309.13962","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-cognitive-maps-and-planning-in","title":"Evaluating Cognitive Maps and Planning in Large Language Models with CogEval","date":"2023-09-25","arxiv_id":"2309.15129","n_code_links":0,"syntology":null},{"paper":null,"slug":"guess-sketch-language-model-guided","title":"Guess & Sketch: Language Model Guided Transpilation","date":"2023-09-25","arxiv_id":"2309.14396","n_code_links":0,"syntology":null},{"paper":"/paper/loggpt-log-anomaly-detection-via-gpt","slug":"loggpt-log-anomaly-detection-via-gpt","title":"LogGPT: Log Anomaly Detection via GPT","date":"2023-09-25","arxiv_id":"2309.14482","n_code_links":1,"syntology":null},{"paper":null,"slug":"only-5-attention-is-all-you-need-efficient","title":"Only 5\\% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation","date":"2023-09-25","arxiv_id":"2309.14174","n_code_links":0,"syntology":null},{"paper":"/paper/particle-part-discovery-and-contrastive","slug":"particle-part-discovery-and-contrastive","title":"PARTICLE: Part Discovery and Contrastive Learning for Fine-grained Recognition","date":"2023-09-25","arxiv_id":"2309.13822","n_code_links":1,"syntology":null},{"paper":null,"slug":"physics-of-language-models-part-3-2-knowledge","title":"Physics of Language Models: Part 3.2, Knowledge Manipulation","date":"2023-09-25","arxiv_id":"2309.14402","n_code_links":0,"syntology":null},{"paper":"/paper/unitedhuman-harnessing-multi-source-data-for","slug":"unitedhuman-harnessing-multi-source-data-for","title":"UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation","date":"2023-09-25","arxiv_id":"2309.14335","n_code_links":1,"syntology":null},{"paper":null,"slug":"watch-your-language-large-language-models-and","title":"Watch Your Language: Investigating Content Moderation with Large Language Models","date":"2023-09-25","arxiv_id":"2309.14517","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sam-based-solution-for-hierarchical","title":"A SAM-based Solution for Hierarchical Panoptic Segmentation of Crops and Weeds Competition","date":"2023-09-24","arxiv_id":"2309.13578","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-large-batch-training-via","title":"Accelerating Large Batch Training via Gradient Signal to Noise Ratio (GSNR)","date":"2023-09-24","arxiv_id":"2309.13681","n_code_links":0,"syntology":null},{"paper":null,"slug":"changes-aware-transformer-learning","title":"Changes-Aware Transformer: Learning Generalized Changes Representation","date":"2023-09-24","arxiv_id":"2309.13619","n_code_links":0,"syntology":null}],"record_sha256":"714a0cb2ee608b80c2825470cb2a6d0e885aaf8cbc0f51bc113635f2b8a82a11","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}