{"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/attention/papers/90","list_of":"/method/attention","method":"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":90,"pages_in_order":316,"rows_per_page":100,"rows":[8901,9000],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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/attention","prev":"/method/attention/papers/89","next":"/method/attention/papers/91","papers":[{"paper":"/paper/diffusion-auto-regressive-transformer-for","slug":"diffusion-auto-regressive-transformer-for","title":"Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series Forecasting","date":"2024-10-08","arxiv_id":"2410.05711","n_code_links":3,"syntology":{"ran":27,"of":31,"n_ran_checked":24,"n_instrument":3,"unverified":4,"pointer_only":31,"phrase":"27 ran (of which 8 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 2 violated, 21 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["melmaphother/timedart"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"dimol-dimensional-awareness-as-a-new","title":"DimOL: Dimensional Awareness as A New 'Dimension' in Operator Learning","date":"2024-10-08","arxiv_id":"2410.05894","n_code_links":0,"syntology":null},{"paper":null,"slug":"diversity-and-inclusion-index-with-networks","title":"Diversity and Inclusion Index with Networks and Similarity: Analysis and its Application","date":"2024-10-08","arxiv_id":"2410.05668","n_code_links":0,"syntology":null},{"paper":"/paper/does-roberta-perform-better-than-bert-in","slug":"does-roberta-perform-better-than-bert-in","title":"Does RoBERTa Perform Better than BERT in Continual Learning: An Attention Sink Perspective","date":"2024-10-08","arxiv_id":"2410.05648","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-playback-performance-in-video","title":"Enhancing Playback Performance in Video Recommender Systems with an On-Device Gating and Ranking Framework","date":"2024-10-08","arxiv_id":"2410.05863","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-sparql-generation-by-triplet-order","slug":"enhancing-sparql-generation-by-triplet-order","title":"Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training","date":"2024-10-08","arxiv_id":"2410.05731","n_code_links":1,"syntology":null},{"paper":null,"slug":"extracting-finite-state-machines-from","title":"Extracting Finite State Machines from Transformers","date":"2024-10-08","arxiv_id":"2410.06045","n_code_links":0,"syntology":null},{"paper":"/paper/facmic-federated-adaptative-clip-model-for","slug":"facmic-federated-adaptative-clip-model-for","title":"FACMIC: Federated Adaptative CLIP Model for Medical Image Classification","date":"2024-10-08","arxiv_id":"2410.14707","n_code_links":1,"syntology":null},{"paper":null,"slug":"grounding-is-all-you-need-dual-temporal","title":"Grounding is All You Need? Dual Temporal Grounding for Video Dialog","date":"2024-10-08","arxiv_id":"2410.05767","n_code_links":0,"syntology":null},{"paper":null,"slug":"guided-self-attention-find-the-generalized","title":"Guided Self-attention: Find the Generalized Necessarily Distinct Vectors for Grain Size Grading","date":"2024-10-08","arxiv_id":"2410.05762","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-matrix-completion-for-the","title":"Hierarchical Matrix Completion for the Prediction of Properties of Binary Mixtures","date":"2024-10-08","arxiv_id":"2410.06060","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-embedding-accuracy-for-document","title":"Improving Embedding Accuracy for Document Retrieval Using Entity Relationship Maps and Model-Aware Contrastive Sampling","date":"2024-10-08","arxiv_id":"2410.18105","n_code_links":0,"syntology":null},{"paper":"/paper/incsar-a-dual-fusion-incremental-learning","slug":"incsar-a-dual-fusion-incremental-learning","title":"IncSAR: A Dual Fusion Incremental Learning Framework for SAR Target Recognition","date":"2024-10-08","arxiv_id":"2410.05820","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-image-derived-pde-phenotypes-from","title":"Learning Image Derived PDE-Phenotypes from fMRI Data","date":"2024-10-08","arxiv_id":"2410.18110","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-free-energy-in-pretraining-model","title":"Leveraging free energy in pretraining model selection for improved fine-tuning","date":"2024-10-08","arxiv_id":"2410.05612","n_code_links":0,"syntology":null},{"paper":"/paper/lightrag-simple-and-fast-retrieval-augmented","slug":"lightrag-simple-and-fast-retrieval-augmented","title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","date":"2024-10-08","arxiv_id":"2410.05779","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hkuds/lightrag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"listen-to-the-patient-enhancing-medical","title":"Listening to Patients: A Framework of Detecting and Mitigating Patient Misreport for Medical Dialogue Generation","date":"2024-10-08","arxiv_id":"2410.06094","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-context-llms-meet-rag-overcoming","title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG","date":"2024-10-08","arxiv_id":"2410.05983","n_code_links":0,"syntology":null},{"paper":"/paper/mtfl-multi-timescale-feature-learning-for","slug":"mtfl-multi-timescale-feature-learning-for","title":"MTFL: Multi-Timescale Feature Learning for Weakly-Supervised Anomaly Detection in Surveillance Videos","date":"2024-10-08","arxiv_id":"2410.05900","n_code_links":1,"syntology":null},{"paper":"/paper/pyramidal-flow-matching-for-efficient-video","slug":"pyramidal-flow-matching-for-efficient-video","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","date":"2024-10-08","arxiv_id":"2410.05954","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 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["jy0205/Pyramid-Flow"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/quadratic-is-not-what-you-need-for-multimodal","slug":"quadratic-is-not-what-you-need-for-multimodal","title":"Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See","date":"2024-10-08","arxiv_id":"2410.06169","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":2,"n_instrument":6,"unverified":2,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ZhangAIPI/YOPO_MLLM_Pruning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"retrieving-rethinking-and-revising-the-chain","title":"Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation","date":"2024-10-08","arxiv_id":"2410.05801","n_code_links":0,"syntology":null},{"paper":null,"slug":"round-and-round-we-go-what-makes-rotary","title":"Round and Round We Go! What makes Rotary Positional Encodings useful?","date":"2024-10-08","arxiv_id":"2410.06205","n_code_links":0,"syntology":null},{"paper":"/paper/sc-bench-a-large-scale-dataset-for-smart","slug":"sc-bench-a-large-scale-dataset-for-smart","title":"SC-Bench: A Large-Scale Dataset for Smart Contract Auditing","date":"2024-10-08","arxiv_id":"2410.06176","n_code_links":1,"syntology":null},{"paper":"/paper/stnet-deep-audio-visual-fusion-network-for","slug":"stnet-deep-audio-visual-fusion-network-for","title":"STNet: Deep Audio-Visual Fusion Network for Robust Speaker Tracking","date":"2024-10-08","arxiv_id":"2410.05964","n_code_links":1,"syntology":null},{"paper":null,"slug":"stress-detection-on-code-mixed-texts-in","title":"Stress Detection on Code-Mixed Texts in Dravidian Languages using Machine Learning","date":"2024-10-08","arxiv_id":"2410.06428","n_code_links":0,"syntology":null},{"paper":null,"slug":"swiftqueue-optimizing-low-latency","title":"SwiftQueue: Optimizing Low-Latency Applications with Swift Packet Queuing","date":"2024-10-08","arxiv_id":"2410.06112","n_code_links":0,"syntology":null},{"paper":"/paper/tackling-the-abstraction-and-reasoning-corpus-1","slug":"tackling-the-abstraction-and-reasoning-corpus-1","title":"Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects","date":"2024-10-08","arxiv_id":"2410.06405","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["khalil-research/ViTARC"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"timba-time-series-imputation-with-bi","title":"TIMBA: Time series Imputation with Bi-directional Mamba Blocks and Diffusion models","date":"2024-10-08","arxiv_id":"2410.05916","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-robust-spacecraft-trajectory","title":"Towards Robust Spacecraft Trajectory Optimization via Transformers","date":"2024-10-08","arxiv_id":"2410.05585","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-free-open-ended-object-detection-and","title":"Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts","date":"2024-10-08","arxiv_id":"2410.05963","n_code_links":0,"syntology":null},{"paper":"/paper/tree-based-leakage-inspection-and-control-in","slug":"tree-based-leakage-inspection-and-control-in","title":"Tree-Based Leakage Inspection and Control in Concept Bottleneck Models","date":"2024-10-08","arxiv_id":"2410.06352","n_code_links":1,"syntology":null},{"paper":null,"slug":"unveiling-transformer-perception-by-exploring","title":"Unveiling Transformer Perception by Exploring Input Manifolds","date":"2024-10-08","arxiv_id":"2410.06019","n_code_links":0,"syntology":null},{"paper":null,"slug":"vector-grimoire-codebook-based-shape","title":"Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision","date":"2024-10-08","arxiv_id":"2410.05991","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-transformer-based-random-walk-for","title":"Vision Transformer based Random Walk for Group Re-Identification","date":"2024-10-08","arxiv_id":"2410.05808","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-image-segmentation-framework-via-in","slug":"a-simple-image-segmentation-framework-via-in","title":"A Simple Image Segmentation Framework via In-Context Examples","date":"2024-10-07","arxiv_id":"2410.04842","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["aim-uofa/sine"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"anyattack-towards-large-scale-self-supervised","title":"AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models","date":"2024-10-07","arxiv_id":"2410.05346","n_code_links":0,"syntology":null},{"paper":"/paper/causal-context-adjustment-loss-for-learned","slug":"causal-context-adjustment-loss-for-learned","title":"Causal Context Adjustment Loss for Learned Image Compression","date":"2024-10-07","arxiv_id":"2410.04847","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["LabShuHangGU/CCA"],"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":["official"]}}},{"paper":null,"slug":"chain-and-causal-attention-for-efficient","title":"Chain and Causal Attention for Efficient Entity Tracking","date":"2024-10-07","arxiv_id":"2410.05565","n_code_links":0,"syntology":null},{"paper":null,"slug":"computational-design-of-target-specific","title":"Computational design of target-specific linear peptide binders with TransformerBeta","date":"2024-10-07","arxiv_id":"2410.16302","n_code_links":0,"syntology":null},{"paper":null,"slug":"contrastive-learning-to-improve-retrieval-for","title":"Contrastive Learning to Improve Retrieval for Real-world Fact Checking","date":"2024-10-07","arxiv_id":"2410.04657","n_code_links":0,"syntology":null},{"paper":"/paper/dape-v2-process-attention-score-as-feature","slug":"dape-v2-process-attention-score-as-feature","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","date":"2024-10-07","arxiv_id":"2410.04798","n_code_links":2,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"pointer_only":5,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["chuanyang-zheng/dape"],"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/deciphering-the-interplay-of-parametric-and","slug":"deciphering-the-interplay-of-parametric-and","title":"Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models","date":"2024-10-07","arxiv_id":"2410.05162","n_code_links":1,"syntology":{"ran":14,"of":17,"n_ran_checked":13,"n_instrument":1,"unverified":3,"pointer_only":17,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["m3hrdadfi/rag-memory-interplay"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/differential-transformer","slug":"differential-transformer","title":"Differential Transformer","date":"2024-10-07","arxiv_id":"2410.05258","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["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"]}}},{"paper":"/paper/diffusereg-denoising-diffusion-model-for","slug":"diffusereg-denoising-diffusion-model-for","title":"DiffuseReg: Denoising Diffusion Model for Obtaining Deformation Fields in Unsupervised Deformable Image Registration","date":"2024-10-07","arxiv_id":"2410.05234","n_code_links":1,"syntology":null},{"paper":null,"slug":"editing-music-with-melody-and-text-using","title":"Editing Music with Melody and Text: Using ControlNet for Diffusion Transformer","date":"2024-10-07","arxiv_id":"2410.05151","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-transformer-with-reinforced","title":"Efficient transformer with reinforced position embedding for language models","date":"2024-10-07","arxiv_id":"2410.04731","n_code_links":0,"syntology":null},{"paper":null,"slug":"falcon-mamba-the-first-competitive-attention","title":"Falcon Mamba: The First Competitive Attention-free 7B Language Model","date":"2024-10-07","arxiv_id":"2410.05355","n_code_links":0,"syntology":null},{"paper":"/paper/feature-selection-gates-with-gradient-routing","slug":"feature-selection-gates-with-gradient-routing","title":"Feature Selection Gates with Gradient Routing for Endoscopic Image Computing","date":"2024-10-07","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"fellas-enhancing-federated-sequential","title":"FELLAS: Enhancing Federated Sequential Recommendation with LLM as External Services","date":"2024-10-07","arxiv_id":"2410.04927","n_code_links":0,"syntology":null},{"paper":"/paper/fresh-frequency-shifting-for-accelerated","slug":"fresh-frequency-shifting-for-accelerated","title":"FreSh: Frequency Shifting for Accelerated Neural Representation Learning","date":"2024-10-07","arxiv_id":"2410.05050","n_code_links":1,"syntology":null},{"paper":"/paper/from-sparse-dependence-to-sparse-attention","slug":"from-sparse-dependence-to-sparse-attention","title":"From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency","date":"2024-10-07","arxiv_id":"2410.05459","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["zhqwqwq/Learning-Parity-with-CoT"],"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":["official"]}}},{"paper":null,"slug":"from-transparency-to-accountability-and-back","title":"From Transparency to Accountability and Back: A Discussion of Access and Evidence in AI Auditing","date":"2024-10-07","arxiv_id":"2410.04772","n_code_links":0,"syntology":null},{"paper":null,"slug":"garlic-llm-guided-dynamic-progress-control","title":"GARLIC: LLM-Guided Dynamic Progress Control with Hierarchical Weighted Graph for Long Document QA","date":"2024-10-07","arxiv_id":"2410.04790","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-cad-code-with-vision-language","title":"Generating CAD Code with Vision-Language Models for 3D Designs","date":"2024-10-07","arxiv_id":"2410.05340","n_code_links":0,"syntology":null},{"paper":null,"slug":"igroupss-mamba-interval-group-spatial","title":"IGroupSS-Mamba: Interval Group Spatial-Spectral Mamba for Hyperspectral Image Classification","date":"2024-10-07","arxiv_id":"2410.05100","n_code_links":0,"syntology":null},{"paper":"/paper/improving-image-clustering-with-artifacts","slug":"improving-image-clustering-with-artifacts","title":"Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering","date":"2024-10-07","arxiv_id":"2410.04801","n_code_links":0,"syntology":null},{"paper":"/paper/improving-object-detection-via-local-global","slug":"improving-object-detection-via-local-global","title":"Improving Object Detection via Local-global Contrastive Learning","date":"2024-10-07","arxiv_id":"2410.05058","n_code_links":0,"syntology":null},{"paper":null,"slug":"initialization-of-large-language-models-via","title":"Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes","date":"2024-10-07","arxiv_id":"2410.05052","n_code_links":0,"syntology":null},{"paper":null,"slug":"intriguing-properties-of-large-language-and","title":"Intriguing Properties of Large Language and Vision Models","date":"2024-10-07","arxiv_id":"2410.04751","n_code_links":0,"syntology":null},{"paper":null,"slug":"l-c4-language-based-video-colorization-for","title":"L-C4: Language-Based Video Colorization for Creative and Consistent Color","date":"2024-10-07","arxiv_id":"2410.04972","n_code_links":0,"syntology":null},{"paper":null,"slug":"levattention-time-space-and-streaming","title":"LevAttention: Time, Space, and Streaming Efficient Algorithm for Heavy Attentions","date":"2024-10-07","arxiv_id":"2410.05462","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-grammar-induction-for-language","slug":"leveraging-grammar-induction-for-language","title":"Leveraging Grammar Induction for Language Understanding and Generation","date":"2024-10-07","arxiv_id":"2410.04878","n_code_links":1,"syntology":null},{"paper":null,"slug":"low-rank-continual-pyramid-vision-transformer","title":"Low-Rank Continual Pyramid Vision Transformer: Incrementally Segment Whole-Body Organs in CT with Light-Weighted Adaptation","date":"2024-10-07","arxiv_id":"2410.04689","n_code_links":0,"syntology":null},{"paper":null,"slug":"lpzero-language-model-zero-cost-proxy-search","title":"LPZero: Language Model Zero-cost Proxy Search from Zero","date":"2024-10-07","arxiv_id":"2410.04808","n_code_links":0,"syntology":null},{"paper":"/paper/mars-multi-view-attention-regularizations-for","slug":"mars-multi-view-attention-regularizations-for","title":"MARs: Multi-view Attention Regularizations for Patch-based Feature Recognition of Space Terrain","date":"2024-10-07","arxiv_id":"2410.05182","n_code_links":1,"syntology":null},{"paper":null,"slug":"masked-autoencoder-with-swin-transformer","title":"Masked Autoencoder with Swin Transformer Network for Mitigating Electrode Shift in HD-EMG-based Gesture Recognition","date":"2024-10-07","arxiv_id":"2410.17261","n_code_links":0,"syntology":null},{"paper":null,"slug":"mastering-chinese-chess-ai-xiangqi-without","title":"Mastering Chinese Chess AI (Xiangqi) Without Search","date":"2024-10-07","arxiv_id":"2410.04865","n_code_links":0,"syntology":null},{"paper":"/paper/mitigating-modality-prior-induced","slug":"mitigating-modality-prior-induced","title":"Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality","date":"2024-10-07","arxiv_id":"2410.04780","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["the-martyr/causalmm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/mrf-net-an-infrared-remote-sensing-image-thin","slug":"mrf-net-an-infrared-remote-sensing-image-thin","title":"MRF-Net: An Infrared Remote Sensing Image Thin Cloud Removal Method With the Intra-Inter Coherent Constraint","date":"2024-10-07","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/narrative-of-thought-improving-temporal","slug":"narrative-of-thought-improving-temporal","title":"Narrative-of-Thought: Improving Temporal Reasoning of Large Language Models via Recounted Narratives","date":"2024-10-07","arxiv_id":"2410.05558","n_code_links":1,"syntology":null},{"paper":"/paper/neurobolt-resting-state-eeg-to-fmri-synthesis","slug":"neurobolt-resting-state-eeg-to-fmri-synthesis","title":"NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping","date":"2024-10-07","arxiv_id":"2410.05341","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["soupeeli/NeuroBOLT"],"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":"on-instruction-finetuning-neural-machine","title":"On Instruction-Finetuning Neural Machine Translation Models","date":"2024-10-07","arxiv_id":"2410.05553","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-optimization-and-generalization-of-two","title":"On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent","date":"2024-10-07","arxiv_id":"2410.04870","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimal-information-acquisition-strategies","title":"Optimal Information Acquisition Strategies: The Case of Online Lending","date":"2024-10-07","arxiv_id":"2410.05539","n_code_links":0,"syntology":null},{"paper":null,"slug":"patch-is-enough-naturalistic-adversarial","title":"Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models","date":"2024-10-07","arxiv_id":"2410.04884","n_code_links":0,"syntology":null},{"paper":"/paper/predformer-transformers-are-effective-spatial","slug":"predformer-transformers-are-effective-spatial","title":"Video Prediction Transformers without Recurrence or Convolution","date":"2024-10-07","arxiv_id":"2410.04733","n_code_links":1,"syntology":null},{"paper":null,"slug":"real-time-ship-recognition-and-georeferencing","title":"Real-time Ship Recognition and Georeferencing for the Improvement of Maritime Situational Awareness","date":"2024-10-07","arxiv_id":"2410.04946","n_code_links":0,"syntology":null},{"paper":null,"slug":"restnet-defense-against-adversarial-policies","title":"ResTNet: Defense against Adversarial Policies via Transformer in Computer Go","date":"2024-10-07","arxiv_id":"2410.05347","n_code_links":0,"syntology":null},{"paper":"/paper/spatio-temporal-3d-point-clouds-from-wifi-csi","slug":"spatio-temporal-3d-point-clouds-from-wifi-csi","title":"Spatio-Temporal 3D Point Clouds from WiFi-CSI Data via Transformer Networks","date":"2024-10-07","arxiv_id":"2410.16303","n_code_links":1,"syntology":null},{"paper":null,"slug":"temporal-relational-reasoning-of-large","title":"Temporal Relational Reasoning of Large Language Models for Detecting Stock Portfolio Crashes","date":"2024-10-07","arxiv_id":"2410.17266","n_code_links":0,"syntology":null},{"paper":null,"slug":"tex-nerf-neural-radiance-fields-from-pseudo","title":"TeX-NeRF: Neural Radiance Fields from Pseudo-TeX Vision","date":"2024-10-07","arxiv_id":"2410.04873","n_code_links":0,"syntology":null},{"paper":"/paper/tidaldecode-fast-and-accurate-llm-decoding","slug":"tidaldecode-fast-and-accurate-llm-decoding","title":"TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention","date":"2024-10-07","arxiv_id":"2410.05076","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":7,"n_instrument":5,"unverified":1,"pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["DerrickYLJ/TidalDecode"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tight-stability-convergence-and-robustness","title":"Tight Stability, Convergence, and Robustness Bounds for Predictive Coding Networks","date":"2024-10-07","arxiv_id":"2410.04708","n_code_links":0,"syntology":null},{"paper":"/paper/timer-xl-long-context-transformers-for","slug":"timer-xl-long-context-transformers-for","title":"Timer-XL: Long-Context Transformers for Unified Time Series Forecasting","date":"2024-10-07","arxiv_id":"2410.04803","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-measuring-goal-directedness-in-ai","title":"Towards Measuring Goal-Directedness in AI Systems","date":"2024-10-07","arxiv_id":"2410.04683","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-learn-variable-order-markov","title":"Transformers learn variable-order Markov chains in-context","date":"2024-10-07","arxiv_id":"2410.05493","n_code_links":0,"syntology":null},{"paper":"/paper/tuning-free-bilevel-optimization-new","slug":"tuning-free-bilevel-optimization-new","title":"Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis","date":"2024-10-07","arxiv_id":"2410.05140","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["optmn-lab/tfbo"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"zero-shot-vision-and-language-navigation-with","title":"Zero-Shot Vision-and-Language Navigation with Collision Mitigation in Continuous Environment","date":"2024-10-07","arxiv_id":"2410.17267","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-attention-based-algorithm-for-gravity","title":"An Attention-Based Algorithm for Gravity Adaptation Zone Calibration","date":"2024-10-06","arxiv_id":"2410.04457","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-shift-steering-ai-away-from-unsafe","title":"Attention Shift: Steering AI Away from Unsafe Content","date":"2024-10-06","arxiv_id":"2410.04447","n_code_links":0,"syntology":null},{"paper":null,"slug":"channel-aware-throughput-maximization-for","title":"Channel-Aware Throughput Maximization for Cooperative Data Fusion in CAV","date":"2024-10-06","arxiv_id":"2410.04320","n_code_links":0,"syntology":null},{"paper":null,"slug":"copylens-dynamically-flagging-copyrighted-sub","title":"Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture","date":"2024-10-06","arxiv_id":"2410.04454","n_code_links":0,"syntology":null},{"paper":null,"slug":"damro-dive-into-the-attention-mechanism-of","title":"DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination","date":"2024-10-06","arxiv_id":"2410.04514","n_code_links":0,"syntology":null},{"paper":null,"slug":"diagnosing-robotics-systems-issues-with-large","title":"Diagnosing Robotics Systems Issues with Large Language Models","date":"2024-10-06","arxiv_id":"2410.09084","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-3d-human-pose-estimation-amidst","slug":"enhancing-3d-human-pose-estimation-amidst","title":"Enhancing 3D Human Pose Estimation Amidst Severe Occlusion with Dual Transformer Fusion","date":"2024-10-06","arxiv_id":"2410.04574","n_code_links":1,"syntology":null},{"paper":"/paper/famma-a-benchmark-for-financial-domain","slug":"famma-a-benchmark-for-financial-domain","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","date":"2024-10-06","arxiv_id":"2410.04526","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":["famma-bench/bench-script"],"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/generative-flows-on-synthetic-pathway-for","slug":"generative-flows-on-synthetic-pathway-for","title":"Generative Flows on Synthetic Pathway for Drug Design","date":"2024-10-06","arxiv_id":"2410.04542","n_code_links":3,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["SeonghwanSeo/RxnFlow"],"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":"inference-scaling-for-long-context-retrieval","title":"Inference Scaling for Long-Context Retrieval Augmented Generation","date":"2024-10-06","arxiv_id":"2410.04343","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-guided-dynamic-modality-attention","slug":"knowledge-guided-dynamic-modality-attention","title":"Knowledge-Guided Dynamic Modality Attention Fusion Framework for Multimodal Sentiment Analysis","date":"2024-10-06","arxiv_id":"2410.04491","n_code_links":1,"syntology":null}],"record_sha256":"eeab04f0cdfdab49601ba89cffb778a1b52a9409e4d8987b22518827995fa9d0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}