{"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/70","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":70,"pages_in_order":249,"rows_per_page":100,"rows":[6901,7000],"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/69","next":"/method/multi-head-attention/papers/71","papers":[{"paper":"/paper/disentangling-and-integrating-relational-and","slug":"disentangling-and-integrating-relational-and","title":"Disentangling and Integrating Relational and Sensory Information in Transformer Architectures","date":"2024-05-26","arxiv_id":"2405.16727","n_code_links":2,"syntology":{"ran":14,"of":21,"n_ran_checked":10,"n_instrument":4,"unverified":7,"pointer_only":0,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","official":{"repos":["awni00/dual-attention"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/grag-graph-retrieval-augmented-generation","slug":"grag-graph-retrieval-augmented-generation","title":"GRAG: Graph Retrieval-Augmented Generation","date":"2024-05-26","arxiv_id":"2405.16506","n_code_links":1,"syntology":null},{"paper":null,"slug":"m-rag-reinforcing-large-language-model","title":"M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions","date":"2024-05-26","arxiv_id":"2405.16420","n_code_links":0,"syntology":null},{"paper":"/paper/mambats-improved-selective-state-space-models","slug":"mambats-improved-selective-state-space-models","title":"MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting","date":"2024-05-26","arxiv_id":"2405.16440","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":4,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["XiudingCai/MambaTS-pytorch"],"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"]}}},{"paper":"/paper/meta-task-planning-for-language-agents","slug":"meta-task-planning-for-language-agents","title":"Planning with Multi-Constraints via Collaborative Language Agents","date":"2024-05-26","arxiv_id":"2405.16510","n_code_links":1,"syntology":null},{"paper":null,"slug":"scalable-numerical-embeddings-for","title":"Scalable Numerical Embeddings for Multivariate Time Series: Enhancing Healthcare Data Representation Learning","date":"2024-05-26","arxiv_id":"2405.16557","n_code_links":0,"syntology":null},{"paper":"/paper/spinquant-llm-quantization-with-learned","slug":"spinquant-llm-quantization-with-learned","title":"SpinQuant: LLM quantization with learned rotations","date":"2024-05-26","arxiv_id":"2405.16406","n_code_links":3,"syntology":{"ran":10,"of":10,"n_ran_checked":7,"n_instrument":3,"unverified":0,"pointer_only":10,"phrase":"10 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; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"accelerating-inference-of-retrieval-augmented","title":"Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection","date":"2024-05-25","arxiv_id":"2405.16178","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-transformers-with-spectrum-1","slug":"accelerating-transformers-with-spectrum-1","title":"Accelerating Transformers with Spectrum-Preserving Token Merging","date":"2024-05-25","arxiv_id":"2405.16148","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":2,"n_instrument":4,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hchautran/PiToMe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/automanual-generating-instruction-manuals-by","slug":"automanual-generating-instruction-manuals-by","title":"AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning","date":"2024-05-25","arxiv_id":"2405.16247","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["minghchen/automanual"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"comparative-analysis-of-open-source-language","title":"Comparative Analysis of Open-Source Language Models in Summarizing Medical Text Data","date":"2024-05-25","arxiv_id":"2405.16295","n_code_links":0,"syntology":null},{"paper":"/paper/confidence-under-the-hood-an-investigation","slug":"confidence-under-the-hood-an-investigation","title":"Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models","date":"2024-05-25","arxiv_id":"2405.16282","n_code_links":1,"syntology":{"ran":1,"of":6,"n_ran_checked":1,"n_instrument":0,"unverified":5,"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) · 5 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["akkeshav/confidence_probability_alignment"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dynamic-inhomogeneous-quantum-resource","title":"Dynamic Inhomogeneous Quantum Resource Scheduling with Reinforcement Learning","date":"2024-05-25","arxiv_id":"2405.16380","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-temporal-action-segmentation-via","slug":"efficient-temporal-action-segmentation-via","title":"Efficient Temporal Action Segmentation via Boundary-aware Query Voting","date":"2024-05-25","arxiv_id":"2405.15995","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-deep-learning-methods-applied-to","slug":"evaluating-deep-learning-methods-applied-to","title":"Evaluating deep learning methods applied to Landsat time series subsequences to detect and classify boreal forest disturbances events: The challenge of partial and progressive disturbances","date":"2024-05-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"geneagent-self-verification-language-agent","title":"GeneAgent: Self-verification Language Agent for Gene Set Knowledge Discovery using Domain Databases","date":"2024-05-25","arxiv_id":"2405.16205","n_code_links":0,"syntology":null},{"paper":null,"slug":"hethub-a-heterogeneous-distributed-hybrid","title":"HETHUB: A Distributed Training System with Heterogeneous Cluster for Large-Scale Models","date":"2024-05-25","arxiv_id":"2405.16256","n_code_links":0,"syntology":null},{"paper":null,"slug":"incremental-comprehension-of-garden-path","title":"Incremental Comprehension of Garden-Path Sentences by Large Language Models: Semantic Interpretation, Syntactic Re-Analysis, and Attention","date":"2024-05-25","arxiv_id":"2405.16042","n_code_links":0,"syntology":null},{"paper":"/paper/lateralization-mlp-a-simple-brain-inspired","slug":"lateralization-mlp-a-simple-brain-inspired","title":"Lateralization MLP: A Simple Brain-inspired Architecture for Diffusion","date":"2024-05-25","arxiv_id":"2405.16098","n_code_links":1,"syntology":null},{"paper":null,"slug":"mindstar-enhancing-math-reasoning-in-pre","title":"MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time","date":"2024-05-25","arxiv_id":"2405.16265","n_code_links":0,"syntology":null},{"paper":"/paper/moeut-mixture-of-experts-universal","slug":"moeut-mixture-of-experts-universal","title":"MoEUT: Mixture-of-Experts Universal Transformers","date":"2024-05-25","arxiv_id":"2405.16039","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":5,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["robertcsordas/moeut"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"picturing-ambiguity-a-visual-twist-on-the","title":"Picturing Ambiguity: A Visual Twist on the Winograd Schema Challenge","date":"2024-05-25","arxiv_id":"2405.16277","n_code_links":0,"syntology":null},{"paper":"/paper/stride-a-tool-assisted-llm-agent-framework","slug":"stride-a-tool-assisted-llm-agent-framework","title":"STRIDE: A Tool-Assisted LLM Agent Framework for Strategic and Interactive Decision-Making","date":"2024-05-25","arxiv_id":"2405.16376","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["cyrilli/stride"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-black-box-membership-inference-attack","title":"Towards Black-Box Membership Inference Attack for Diffusion Models","date":"2024-05-25","arxiv_id":"2405.20771","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-unlocking-insights-from-logbooks","title":"Towards Unlocking Insights from Logbooks Using AI","date":"2024-05-25","arxiv_id":"2406.12881","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-meets-gated-residual-networks-to","title":"Transformer Meets Gated Residual Networks To Enhance Photoplethysmogram Artifact Detection Informed by Mutual Information Neural Estimation","date":"2024-05-25","arxiv_id":"2405.16177","n_code_links":0,"syntology":null},{"paper":"/paper/uu-mamba-uncertainty-aware-u-mamba-for","slug":"uu-mamba-uncertainty-aware-u-mamba-for","title":"UU-Mamba: Uncertainty-aware U-Mamba for Cardiac Image Segmentation","date":"2024-05-25","arxiv_id":"2405.17496","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-evaluation-of-estimative-uncertainty-in","title":"An Evaluation of Estimative Uncertainty in Large Language Models","date":"2024-05-24","arxiv_id":"2405.15185","n_code_links":0,"syntology":null},{"paper":"/paper/before-generation-align-it-a-novel-and","slug":"before-generation-align-it-a-novel-and","title":"Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation","date":"2024-05-24","arxiv_id":"2405.15307","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":7,"n_instrument":1,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["quge2023/TA-SQL"],"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"]}}},{"paper":null,"slug":"benchmarking-hierarchical-image-pyramid","title":"Benchmarking Hierarchical Image Pyramid Transformer for the classification of colon biopsies and polyps in histopathology images","date":"2024-05-24","arxiv_id":"2405.15127","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-pre-trained-large-language","title":"Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks","date":"2024-05-24","arxiv_id":"2405.15453","n_code_links":0,"syntology":null},{"paper":"/paper/continuously-learning-adapting-and-improving","slug":"continuously-learning-adapting-and-improving","title":"Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving","date":"2024-05-24","arxiv_id":"2405.15324","n_code_links":1,"syntology":null},{"paper":"/paper/convllava-hierarchical-backbones-as-visual","slug":"convllava-hierarchical-backbones-as-visual","title":"ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models","date":"2024-05-24","arxiv_id":"2405.15738","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":5,"n_instrument":3,"unverified":2,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alibaba/conv-llava"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/culturepark-boosting-cross-cultural","slug":"culturepark-boosting-cross-cultural","title":"CulturePark: Boosting Cross-cultural Understanding in Large Language Models","date":"2024-05-24","arxiv_id":"2405.15145","n_code_links":1,"syntology":{"ran":0,"of":7,"n_ran_checked":0,"n_instrument":0,"unverified":7,"pointer_only":7,"phrase":"0 ran · 7 unverified","official":{"repos":["scarelette/culturepark"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":[]}}},{"paper":null,"slug":"distinguish-any-fake-videos-unleashing-the","title":"Distinguish Any Fake Videos: Unleashing the Power of Large-scale Data and Motion Features","date":"2024-05-24","arxiv_id":"2405.15343","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-augmentative-and-alternative","title":"Enhancing Augmentative and Alternative Communication with Card Prediction and Colourful Semantics","date":"2024-05-24","arxiv_id":"2405.15896","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-adversarial-robustness-of-1","slug":"evaluating-the-adversarial-robustness-of-1","title":"Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learning","date":"2024-05-24","arxiv_id":"2405.15984","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["simonucl/adv-retreival-icl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/filtered-corpus-training-fict-shows-that","slug":"filtered-corpus-training-fict-shows-that","title":"Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidence","date":"2024-05-24","arxiv_id":"2405.15750","n_code_links":1,"syntology":null},{"paper":"/paper/generalizable-and-scalable-multistage","slug":"generalizable-and-scalable-multistage","title":"Generalizable and Scalable Multistage Biomedical Concept Normalization Leveraging Large Language Models","date":"2024-05-24","arxiv_id":"2405.15122","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-is-not-an-annotator-the-necessity-of","title":"GPT is Not an Annotator: The Necessity of Human Annotation in Fairness Benchmark Construction","date":"2024-05-24","arxiv_id":"2405.15760","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-reflect-human-citation","slug":"large-language-models-reflect-human-citation","title":"Large Language Models Reflect Human Citation Patterns with a Heightened Citation Bias","date":"2024-05-24","arxiv_id":"2405.15739","n_code_links":1,"syntology":null},{"paper":"/paper/learning-the-language-of-protein-structure","slug":"learning-the-language-of-protein-structure","title":"Learning the Language of Protein Structure","date":"2024-05-24","arxiv_id":"2405.15840","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["instadeepai/protein-structure-tokenizer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/machine-unlearning-in-large-language-models","slug":"machine-unlearning-in-large-language-models","title":"Machine Unlearning in Large Language Models","date":"2024-05-24","arxiv_id":"2405.15152","n_code_links":1,"syntology":null},{"paper":"/paper/mambavc-learned-visual-compression-with","slug":"mambavc-learned-visual-compression-with","title":"MambaVC: Learned Visual Compression with Selective State Spaces","date":"2024-05-24","arxiv_id":"2405.15413","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qinsy123/2024-mambavc"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"matchings-predictions-and-counterfactual-harm","title":"Matchings, Predictions and Counterfactual Harm in Refugee Resettlement Processes","date":"2024-05-24","arxiv_id":"2407.13052","n_code_links":0,"syntology":null},{"paper":"/paper/memo-meaningful-modular-controllers-via-noise","slug":"memo-meaningful-modular-controllers-via-noise","title":"MeMo: Meaningful, Modular Controllers via Noise Injection","date":"2024-05-24","arxiv_id":"2407.01567","n_code_links":0,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/mlps-learn-in-context","slug":"mlps-learn-in-context","title":"MLPs Learn In-Context on Regression and Classification Tasks","date":"2024-05-24","arxiv_id":"2405.15618","n_code_links":2,"syntology":{"ran":15,"of":16,"n_ran_checked":13,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"15 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["wtong98/mlp-icl"],"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":["listed","official"]}}},{"paper":"/paper/pointramba-a-hybrid-transformer-mamba","slug":"pointramba-a-hybrid-transformer-mamba","title":"PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis","date":"2024-05-24","arxiv_id":"2405.15463","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":7,"n_instrument":1,"unverified":0,"pointer_only":7,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xiaoyao3302/pointramba"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"recasting-generic-pretrained-vision","title":"Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policies","date":"2024-05-24","arxiv_id":"2405.15916","n_code_links":0,"syntology":null},{"paper":"/paper/spectraformer-a-unified-random-feature","slug":"spectraformer-a-unified-random-feature","title":"Spectraformer: A Unified Random Feature Framework for Transformer","date":"2024-05-24","arxiv_id":"2405.15310","n_code_links":2,"syntology":null},{"paper":null,"slug":"steerable-transformers","title":"Steerable Transformers","date":"2024-05-24","arxiv_id":"2405.15932","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-guided-3d-human-motion-generation-with","title":"Text-guided 3D Human Motion Generation with Keyframe-based Parallel Skip Transformer","date":"2024-05-24","arxiv_id":"2405.15439","n_code_links":0,"syntology":null},{"paper":null,"slug":"textit-comet-a-underline-com-munication","title":"Comet: A Communication-efficient and Performant Approximation for Private Transformer Inference","date":"2024-05-24","arxiv_id":"2405.17485","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-and-opportunities-of-generative-ai","title":"The Impact and Opportunities of Generative AI in Fact-Checking","date":"2024-05-24","arxiv_id":"2405.15985","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-better-understanding-of-in-context","title":"Towards Better Understanding of In-Context Learning Ability from In-Context Uncertainty Quantification","date":"2024-05-24","arxiv_id":"2405.15115","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-understanding-how-transformer-perform","title":"The Buffer Mechanism for Multi-Step Information Reasoning in Language Models","date":"2024-05-24","arxiv_id":"2405.15302","n_code_links":0,"syntology":null},{"paper":null,"slug":"unitnorm-rethinking-normalization-for","title":"UnitNorm: Rethinking Normalization for Transformers in Time Series","date":"2024-05-24","arxiv_id":"2405.15903","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-spam-email-classification-using-pre","title":"Zero-Shot Spam Email Classification Using Pre-trained Large Language Models","date":"2024-05-24","arxiv_id":"2405.15936","n_code_links":0,"syntology":null},{"paper":null,"slug":"3d-learnable-supertoken-transformer-for-lidar","title":"3D Learnable Supertoken Transformer for LiDAR Point Cloud Scene Segmentation","date":"2024-05-23","arxiv_id":"2405.15826","n_code_links":0,"syntology":null},{"paper":"/paper/a-declarative-system-for-optimizing-ai","slug":"a-declarative-system-for-optimizing-ai","title":"A Declarative System for Optimizing AI Workloads","date":"2024-05-23","arxiv_id":"2405.14696","n_code_links":1,"syntology":null},{"paper":"/paper/a-structure-aware-framework-for-learning","slug":"a-structure-aware-framework-for-learning","title":"A Structure-Aware Framework for Learning Device Placements on Computation Graphs","date":"2024-05-23","arxiv_id":"2405.14185","n_code_links":1,"syntology":null},{"paper":"/paper/agile-a-novel-framework-of-llm-agents","slug":"agile-a-novel-framework-of-llm-agents","title":"AGILE: A Novel Reinforcement Learning Framework of LLM Agents","date":"2024-05-23","arxiv_id":"2405.14751","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bytarnish/agile"],"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"]}}},{"paper":null,"slug":"attending-to-topological-spaces-the-cellular","title":"Attending to Topological Spaces: The Cellular Transformer","date":"2024-05-23","arxiv_id":"2405.14094","n_code_links":0,"syntology":null},{"paper":"/paper/autocoder-enhancing-code-large-language-model","slug":"autocoder-enhancing-code-large-language-model","title":"AutoCoder: Enhancing Code Large Language Model with \\textsc{AIEV-Instruct}","date":"2024-05-23","arxiv_id":"2405.14906","n_code_links":1,"syntology":null},{"paper":"/paper/ceebert-cross-domain-inference-in-early-exit","slug":"ceebert-cross-domain-inference-in-early-exit","title":"CEEBERT: Cross-Domain Inference in Early Exit BERT","date":"2024-05-23","arxiv_id":"2405.15039","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"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","official":{"repos":["Div290/CeeBERT"],"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"]}}},{"paper":"/paper/combining-denoising-autoencoders-with","slug":"combining-denoising-autoencoders-with","title":"Combining Denoising Autoencoders with Contrastive Learning to fine-tune Transformer Models","date":"2024-05-23","arxiv_id":"2405.14437","n_code_links":1,"syntology":null},{"paper":"/paper/deepseek-prover-advancing-theorem-proving-in","slug":"deepseek-prover-advancing-theorem-proving-in","title":"DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data","date":"2024-05-23","arxiv_id":"2405.14333","n_code_links":0,"syntology":null},{"paper":"/paper/designing-a-sustainable-marine-debris-clean","slug":"designing-a-sustainable-marine-debris-clean","title":"Designing A Sustainable Marine Debris Clean-up Framework without Human Labels","date":"2024-05-23","arxiv_id":"2405.14815","n_code_links":1,"syntology":null},{"paper":"/paper/dinomaly-the-less-is-more-philosophy-in-multi","slug":"dinomaly-the-less-is-more-philosophy-in-multi","title":"Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection","date":"2024-05-23","arxiv_id":"2405.14325","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":4,"n_instrument":5,"unverified":1,"pointer_only":5,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["guojiajeremy/dinomaly"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/direct3d-scalable-image-to-3d-generation-via","slug":"direct3d-scalable-image-to-3d-generation-via","title":"Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer","date":"2024-05-23","arxiv_id":"2405.14832","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":4,"n_instrument":1,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":null}},{"paper":"/paper/editworld-simulating-world-dynamics-for","slug":"editworld-simulating-world-dynamics-for","title":"EditWorld: Simulating World Dynamics for Instruction-Following Image Editing","date":"2024-05-23","arxiv_id":"2405.14785","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yangling0818/editworld"],"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/efficient-medical-question-answering-with","slug":"efficient-medical-question-answering-with","title":"Efficient Medical Question Answering with Knowledge-Augmented Question Generation","date":"2024-05-23","arxiv_id":"2405.14654","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-point-transformer-with-dynamic","title":"Efficient Point Transformer with Dynamic Token Aggregating for LiDAR Point Cloud Processing","date":"2024-05-23","arxiv_id":"2405.15827","n_code_links":0,"syntology":null},{"paper":"/paper/eliciting-informative-text-evaluations-with","slug":"eliciting-informative-text-evaluations-with","title":"Eliciting Informative Text Evaluations with Large Language Models","date":"2024-05-23","arxiv_id":"2405.15077","n_code_links":1,"syntology":{"ran":10,"of":14,"n_ran_checked":8,"n_instrument":2,"unverified":4,"pointer_only":14,"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) · 4 unverified","official":{"repos":["yx-lu/eliciting-informative-text-evaluations-with-large-language-models"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluating-large-language-models-for-public","title":"Evaluating Large Language Models for Public Health Classification and Extraction Tasks","date":"2024-05-23","arxiv_id":"2405.14766","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-use-of-a-large-language-model","title":"Exploring the use of a Large Language Model for data extraction in systematic reviews: a rapid feasibility study","date":"2024-05-23","arxiv_id":"2405.14445","n_code_links":0,"syntology":null},{"paper":"/paper/from-explicit-cot-to-implicit-cot-learning-to","slug":"from-explicit-cot-to-implicit-cot-learning-to","title":"From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step","date":"2024-05-23","arxiv_id":"2405.14838","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["da03/internalize_cot_step_by_step"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/hipporag-neurobiologically-inspired-long-term","slug":"hipporag-neurobiologically-inspired-long-term","title":"HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models","date":"2024-05-23","arxiv_id":"2405.14831","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["osu-nlp-group/hipporag"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/impact-of-non-standard-unicode-characters-on","slug":"impact-of-non-standard-unicode-characters-on","title":"Impact of Non-Standard Unicode Characters on Security and Comprehension in Large Language Models","date":"2024-05-23","arxiv_id":"2405.14490","n_code_links":1,"syntology":null},{"paper":"/paper/improving-gloss-free-sign-language","slug":"improving-gloss-free-sign-language","title":"Improving Gloss-free Sign Language Translation by Reducing Representation Density","date":"2024-05-23","arxiv_id":"2405.14312","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["jinhuiye/signcl"],"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":"improving-language-models-trained-with","title":"Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis","date":"2024-05-23","arxiv_id":"2405.14277","n_code_links":0,"syntology":null},{"paper":"/paper/jiuzhang3-0-efficiently-improving","slug":"jiuzhang3-0-efficiently-improving","title":"JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models","date":"2024-05-23","arxiv_id":"2405.14365","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["rucaibox/jiuzhang3.0"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"large-language-models-can-self-correct-with","title":"Large Language Models Can Self-Correct with Key Condition Verification","date":"2024-05-23","arxiv_id":"2405.14092","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-semantic-segmentation-masks-with","title":"Leveraging Semantic Segmentation Masks with Embeddings for Fine-Grained Form Classification","date":"2024-05-23","arxiv_id":"2405.14162","n_code_links":0,"syntology":null},{"paper":"/paper/linking-in-context-learning-in-transformers","slug":"linking-in-context-learning-in-transformers","title":"Linking In-context Learning in Transformers to Human Episodic Memory","date":"2024-05-23","arxiv_id":"2405.14992","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":0,"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","official":{"repos":["corxyz/icl-cmr"],"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"]}}},{"paper":"/paper/lorentz-equivariant-geometric-algebra","slug":"lorentz-equivariant-geometric-algebra","title":"Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics","date":"2024-05-23","arxiv_id":"2405.14806","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["heidelberg-hepml/lorentz-gatr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"magnetic-resonance-image-processing","title":"Magnetic Resonance Image Processing Transformer for General Accelerated Image Reconstruction","date":"2024-05-23","arxiv_id":"2405.15098","n_code_links":0,"syntology":null},{"paper":"/paper/not-all-language-model-features-are-linear","slug":"not-all-language-model-features-are-linear","title":"Not All Language Model Features Are Linear","date":"2024-05-23","arxiv_id":"2405.14860","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["joshengels/multidimensionalfeatures"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"optimizing-example-selection-for-retrieval","title":"Optimizing example selection for retrieval-augmented machine translation with translation memories","date":"2024-05-23","arxiv_id":"2405.15070","n_code_links":0,"syntology":null},{"paper":null,"slug":"perception-of-knowledge-boundary-for-large","title":"Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering","date":"2024-05-23","arxiv_id":"2405.14383","n_code_links":0,"syntology":null},{"paper":null,"slug":"polyak-meets-parameter-free-clipped-gradient","title":"Parameter-free Clipped Gradient Descent Meets Polyak","date":"2024-05-23","arxiv_id":"2405.15010","n_code_links":0,"syntology":null},{"paper":"/paper/privcirnet-efficient-private-inference-via","slug":"privcirnet-efficient-private-inference-via","title":"PrivCirNet: Efficient Private Inference via Block Circulant Transformation","date":"2024-05-23","arxiv_id":"2405.14569","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tianshi-xu/privcirnet"],"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"]}}},{"paper":"/paper/putr-a-pure-transformer-for-decoupled-and","slug":"putr-a-pure-transformer-for-decoupled-and","title":"PuTR: A Pure Transformer for Decoupled and Online Multi-Object Tracking","date":"2024-05-23","arxiv_id":"2405.14119","n_code_links":1,"syntology":null},{"paper":null,"slug":"rafe-ranking-feedback-improves-query","title":"RaFe: Ranking Feedback Improves Query Rewriting for RAG","date":"2024-05-23","arxiv_id":"2405.14431","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalable-visual-state-space-model-with","title":"Scalable Visual State Space Model with Fractal Scanning","date":"2024-05-23","arxiv_id":"2405.14480","n_code_links":0,"syntology":null},{"paper":null,"slug":"shapeformer-shapelet-transformer-for","title":"ShapeFormer: Shapelet Transformer for Multivariate Time Series Classification","date":"2024-05-23","arxiv_id":"2405.14608","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-tuning-adapting-vision-transformers","slug":"sparse-tuning-adapting-vision-transformers","title":"Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference","date":"2024-05-23","arxiv_id":"2405.14700","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":9,"n_instrument":2,"unverified":0,"pointer_only":11,"phrase":"11 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["liuting20/sparse-tuning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transformers-for-image-goal-navigation","title":"Transformers for Image-Goal Navigation","date":"2024-05-23","arxiv_id":"2405.14128","n_code_links":0,"syntology":null},{"paper":"/paper/vihatet5-enhancing-hate-speech-detection-in","slug":"vihatet5-enhancing-hate-speech-detection-in","title":"ViHateT5: Enhancing Hate Speech Detection in Vietnamese With A Unified Text-to-Text Transformer Model","date":"2024-05-23","arxiv_id":"2405.14141","n_code_links":1,"syntology":null},{"paper":"/paper/wise-rethinking-the-knowledge-memory-for","slug":"wise-rethinking-the-knowledge-memory-for","title":"WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models","date":"2024-05-23","arxiv_id":"2405.14768","n_code_links":1,"syntology":{"ran":13,"of":16,"n_ran_checked":4,"n_instrument":9,"unverified":3,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified","official":{"repos":["zjunlp/easyedit"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"c522869a3cfbb14806a44458e046416cb436195116dfce1468758c179b2b383b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}