{"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/31","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":31,"pages_in_order":316,"rows_per_page":100,"rows":[3001,3100],"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/30","next":"/method/attention/papers/32","papers":[{"paper":null,"slug":"language-models-for-automated-classification","title":"Language Models for Automated Classification of Brain MRI Reports and Growth Chart Generation","date":"2025-03-15","arxiv_id":"2503.12143","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-motion-information-for-better-self","title":"Leveraging Motion Information for Better Self-Supervised Video Correspondence Learning","date":"2025-03-15","arxiv_id":"2503.12026","n_code_links":0,"syntology":null},{"paper":"/paper/llm-hpc-benchmarking-deepseek-s-performance","slug":"llm-hpc-benchmarking-deepseek-s-performance","title":"LLM & HPC:Benchmarking DeepSeek's Performance in High-Performance Computing Tasks","date":"2025-03-15","arxiv_id":"2504.03665","n_code_links":1,"syntology":null},{"paper":null,"slug":"maritime-mission-planning-for-unmanned","title":"Maritime Mission Planning for Unmanned Surface Vessel using Large Language Model","date":"2025-03-15","arxiv_id":"2503.12065","n_code_links":0,"syntology":null},{"paper":"/paper/o-tpt-orthogonality-constraints-for-1","slug":"o-tpt-orthogonality-constraints-for-1","title":"O-TPT: Orthogonality Constraints for Calibrating Test-time Prompt Tuning in Vision-Language Models","date":"2025-03-15","arxiv_id":"2503.12096","n_code_links":1,"syntology":null},{"paper":null,"slug":"tailor-an-integrated-text-driven-cg-ready","title":"Tailor: An Integrated Text-Driven CG-Ready Human and Garment Generation System","date":"2025-03-15","arxiv_id":"2503.12052","n_code_links":0,"syntology":null},{"paper":null,"slug":"verimind-agentic-llm-for-automated-verilog","title":"VeriMind: Agentic LLM for Automated Verilog Generation with a Novel Evaluation Metric","date":"2025-03-15","arxiv_id":"2503.16514","n_code_links":0,"syntology":null},{"paper":null,"slug":"vton-360-high-fidelity-virtual-try-on-from","title":"VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction","date":"2025-03-15","arxiv_id":"2503.12165","n_code_links":0,"syntology":null},{"paper":"/paper/weighted-graph-structure-learning-with","slug":"weighted-graph-structure-learning-with","title":"Weighted Graph Structure Learning with Attention Denoising for Node Classification","date":"2025-03-15","arxiv_id":"2503.12157","n_code_links":1,"syntology":null},{"paper":"/paper/winning-the-midst-challenge-new-membership","slug":"winning-the-midst-challenge-new-membership","title":"Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis","date":"2025-03-15","arxiv_id":"2503.12008","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-neural-network-architecture-based-on","title":"A Neural Network Architecture Based on Attention Gate Mechanism for 3D Magnetotelluric Forward Modeling","date":"2025-03-14","arxiv_id":"2503.11408","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-review-of-deepseek-models-key-innovative","title":"A Review of DeepSeek Models' Key Innovative Techniques","date":"2025-03-14","arxiv_id":"2503.11486","n_code_links":0,"syntology":null},{"paper":"/paper/a-survey-of-cross-domain-graph-learning","slug":"a-survey-of-cross-domain-graph-learning","title":"A Survey of Cross-domain Graph Learning: Progress and Future Directions","date":"2025-03-14","arxiv_id":"2503.11086","n_code_links":1,"syntology":null},{"paper":null,"slug":"addressing-information-loss-and-interaction","title":"Addressing Information Loss and Interaction Collapse: A Dual Enhanced Attention Framework for Feature Interaction","date":"2025-03-14","arxiv_id":"2503.11233","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-deep-learning-methods-for-protein","title":"Advanced Deep Learning Methods for Protein Structure Prediction and Design","date":"2025-03-14","arxiv_id":"2503.13522","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-3d-gaussian-splatting-editing-with","title":"Advancing 3D Gaussian Splatting Editing with Complementary and Consensus Information","date":"2025-03-14","arxiv_id":"2503.11601","n_code_links":0,"syntology":null},{"paper":null,"slug":"alzheimer-s-disease-classification-using","title":"Alzheimer's Disease Classification Using Retinal OCT: TransnetOCT and Swin Transformer Models","date":"2025-03-14","arxiv_id":"2503.11511","n_code_links":0,"syntology":null},{"paper":"/paper/apla-a-simple-adaptation-method-for-vision","slug":"apla-a-simple-adaptation-method-for-vision","title":"APLA: A Simple Adaptation Method for Vision Transformers","date":"2025-03-14","arxiv_id":"2503.11335","n_code_links":1,"syntology":null},{"paper":null,"slug":"asynchronous-sharpness-aware-minimization-for","title":"Asynchronous Sharpness-Aware Minimization For Fast and Accurate Deep Learning","date":"2025-03-14","arxiv_id":"2503.11147","n_code_links":0,"syntology":null},{"paper":null,"slug":"augmenting-image-annotation-a-human-lmm","title":"Augmenting Image Annotation: A Human-LMM Collaborative Framework for Efficient Object Selection and Label Generation","date":"2025-03-14","arxiv_id":"2503.11096","n_code_links":0,"syntology":null},{"paper":null,"slug":"banneragency-advertising-banner-design-with","title":"BannerAgency: Advertising Banner Design with Multimodal LLM Agents","date":"2025-03-14","arxiv_id":"2503.11060","n_code_links":0,"syntology":null},{"paper":"/paper/bevdiffloc-end-to-end-lidar-global","slug":"bevdiffloc-end-to-end-lidar-global","title":"BEVDiffLoc: End-to-End LiDAR Global Localization in BEV View based on Diffusion Model","date":"2025-03-14","arxiv_id":"2503.11372","n_code_links":1,"syntology":null},{"paper":"/paper/bottom-up-iterative-anomalous-diffusion","slug":"bottom-up-iterative-anomalous-diffusion","title":"Bottom-up Iterative Anomalous Diffusion Detector (BI-ADD)","date":"2025-03-14","arxiv_id":"2503.11529","n_code_links":1,"syntology":null},{"paper":"/paper/brain-effective-connectivity-estimation-via","slug":"brain-effective-connectivity-estimation-via","title":"Brain Effective Connectivity Estimation via Fourier Spatiotemporal Attention","date":"2025-03-14","arxiv_id":"2503.11283","n_code_links":1,"syntology":null},{"paper":null,"slug":"cardiomyopathy-diagnosis-model-from","title":"Cardiomyopathy Diagnosis Model from Endomyocardial Biopsy Specimens: Appropriate Feature Space and Class Boundary in Small Sample Size Data","date":"2025-03-14","arxiv_id":"2503.11331","n_code_links":0,"syntology":null},{"paper":"/paper/combining-causal-models-for-more-accurate","slug":"combining-causal-models-for-more-accurate","title":"Combining Causal Models for More Accurate Abstractions of Neural Networks","date":"2025-03-14","arxiv_id":"2503.11429","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["marapislar/combining-causal-models-for-accurate-nn-abstractions"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"context-aware-rule-mining-using-a-dynamic","title":"Context-Aware Rule Mining Using a Dynamic Transformer-Based Framework","date":"2025-03-14","arxiv_id":"2503.11125","n_code_links":0,"syntology":null},{"paper":null,"slug":"dcat-dual-cross-attention-fusion-for-disease","title":"DCAT: Dual Cross-Attention Fusion for Disease Classification in Radiological Images with Uncertainty Estimation","date":"2025-03-14","arxiv_id":"2503.11851","n_code_links":0,"syntology":null},{"paper":null,"slug":"direction-aware-diagonal-autoregressive-image","title":"Direction-Aware Diagonal Autoregressive Image Generation","date":"2025-03-14","arxiv_id":"2503.11129","n_code_links":0,"syntology":null},{"paper":null,"slug":"don-t-take-things-out-of-context-attention","title":"Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models","date":"2025-03-14","arxiv_id":"2503.11154","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynrsl-vlm-enhancing-autonomous-driving","title":"DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Models","date":"2025-03-14","arxiv_id":"2503.11265","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-multi-view-pedestrian-detection","title":"Enhanced Multi-View Pedestrian Detection Using Probabilistic Occupancy Volume","date":"2025-03-14","arxiv_id":"2503.10982","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-competitive-and-collusive-behaviors","title":"Exploring Competitive and Collusive Behaviors in Algorithmic Pricing with Deep Reinforcement Learning","date":"2025-03-14","arxiv_id":"2503.11270","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-potential-of-large-multimodal","title":"Exploring the Potential of Large Multimodal Models as Effective Alternatives for Pronunciation Assessment","date":"2025-03-14","arxiv_id":"2503.11229","n_code_links":0,"syntology":null},{"paper":null,"slug":"fmnet-frequency-assisted-mamba-like-linear","title":"FMNet: Frequency-Assisted Mamba-Like Linear Attention Network for Camouflaged Object Detection","date":"2025-03-14","arxiv_id":"2503.11030","n_code_links":0,"syntology":null},{"paper":"/paper/from-pixels-to-histopathology-a-graph-based","slug":"from-pixels-to-histopathology-a-graph-based","title":"From Pixels to Histopathology: A Graph-Based Framework for Interpretable Whole Slide Image Analysis","date":"2025-03-14","arxiv_id":"2503.11846","n_code_links":1,"syntology":null},{"paper":"/paper/gaussianip-identity-preserving-realistic-3d","slug":"gaussianip-identity-preserving-realistic-3d","title":"GaussianIP: Identity-Preserving Realistic 3D Human Generation via Human-Centric Diffusion Prior","date":"2025-03-14","arxiv_id":"2503.11143","n_code_links":1,"syntology":null},{"paper":"/paper/image-goal-navigation-using-refined-feature","slug":"image-goal-navigation-using-refined-feature","title":"Image-Goal Navigation Using Refined Feature Guidance and Scene Graph Enhancement","date":"2025-03-14","arxiv_id":"2503.10986","n_code_links":1,"syntology":null},{"paper":null,"slug":"key-value-compress-a-systematic-exploration","title":"Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques","date":"2025-03-14","arxiv_id":"2503.11816","n_code_links":0,"syntology":null},{"paper":null,"slug":"limits-of-kv-cache-compression-for-tensor","title":"Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding","date":"2025-03-14","arxiv_id":"2503.11108","n_code_links":0,"syntology":null},{"paper":null,"slug":"llava-mlb-mitigating-and-leveraging-attention","title":"LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs","date":"2025-03-14","arxiv_id":"2503.11205","n_code_links":0,"syntology":null},{"paper":null,"slug":"making-every-step-effective-jailbreaking","title":"Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization","date":"2025-03-14","arxiv_id":"2503.11750","n_code_links":0,"syntology":null},{"paper":null,"slug":"meet-a-million-scale-dataset-for-fine-grained","title":"MEET: A Million-Scale Dataset for Fine-Grained Geospatial Scene Classification with Zoom-Free Remote Sensing Imagery","date":"2025-03-14","arxiv_id":"2503.11219","n_code_links":0,"syntology":null},{"paper":"/paper/modeling-and-optimization-for-flexible","slug":"modeling-and-optimization-for-flexible","title":"Modeling and Optimization for Flexible Cylindrical Arrays-Enabled Wireless Communications","date":"2025-03-14","arxiv_id":"2503.11123","n_code_links":1,"syntology":null},{"paper":null,"slug":"mtv-inpaint-multi-task-long-video-inpainting","title":"MTV-Inpaint: Multi-Task Long Video Inpainting","date":"2025-03-14","arxiv_id":"2503.11412","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-view-industrial-anomaly-detection-with","title":"Multi-View Industrial Anomaly Detection with Epipolar Constrained Cross-View Fusion","date":"2025-03-14","arxiv_id":"2503.11088","n_code_links":0,"syntology":null},{"paper":"/paper/open3dvqa-a-benchmark-for-comprehensive","slug":"open3dvqa-a-benchmark-for-comprehensive","title":"Open3DVQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space","date":"2025-03-14","arxiv_id":"2503.11094","n_code_links":1,"syntology":null},{"paper":null,"slug":"paric-probabilistic-attention-regularization","title":"PARIC: Probabilistic Attention Regularization for Language Guided Image Classification from Pre-trained Vison Language Models","date":"2025-03-14","arxiv_id":"2503.11360","n_code_links":0,"syntology":null},{"paper":"/paper/prof-robot-differentiable-robot-rendering","slug":"prof-robot-differentiable-robot-rendering","title":"Prof. Robot: Differentiable Robot Rendering Without Static and Self-Collisions","date":"2025-03-14","arxiv_id":"2503.11269","n_code_links":1,"syntology":null},{"paper":null,"slug":"prompt-sentiment-the-catalyst-for-llm-change","title":"Prompt Sentiment: The Catalyst for LLM Change","date":"2025-03-14","arxiv_id":"2503.13510","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-interpretability-in-clip-models","title":"Quantifying Interpretability in CLIP Models with Concept Consistency","date":"2025-03-14","arxiv_id":"2503.11103","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-kg-il-a-multi-agent-hybrid-framework-for","title":"RAG-KG-IL: A Multi-Agent Hybrid Framework for Reducing Hallucinations and Enhancing LLM Reasoning through RAG and Incremental Knowledge Graph Learning Integration","date":"2025-03-14","arxiv_id":"2503.13514","n_code_links":0,"syntology":null},{"paper":"/paper/relevance-isn-t-all-you-need-scaling-rag","slug":"relevance-isn-t-all-you-need-scaling-rag","title":"Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Reranking","date":"2025-03-14","arxiv_id":"2504.07104","n_code_links":2,"syntology":null},{"paper":null,"slug":"response-benchmarking-the-ability-of-language","title":"RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation","date":"2025-03-14","arxiv_id":"2503.11348","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-and-contextual-modeling-for","title":"Semantic and Contextual Modeling for Malicious Comment Detection with BERT-BiLSTM","date":"2025-03-14","arxiv_id":"2503.11084","n_code_links":0,"syntology":null},{"paper":null,"slug":"solution-for-8th-competition-on-affective","title":"Solution for 8th Competition on Affective & Behavior Analysis in-the-wild","date":"2025-03-14","arxiv_id":"2503.11115","n_code_links":0,"syntology":null},{"paper":null,"slug":"spaceseg-a-high-precision-intelligent","title":"SpaceSeg: A High-Precision Intelligent Perception Segmentation Method for Multi-Spacecraft On-Orbit Targets","date":"2025-03-14","arxiv_id":"2503.11133","n_code_links":0,"syntology":null},{"paper":"/paper/taming-knowledge-conflicts-in-language-models","slug":"taming-knowledge-conflicts-in-language-models","title":"Taming Knowledge Conflicts in Language Models","date":"2025-03-14","arxiv_id":"2503.10996","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["GaotangLi/JUICE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"text-compression-for-efficient-language","title":"Text Compression for Efficient Language Generation","date":"2025-03-14","arxiv_id":"2503.11426","n_code_links":0,"syntology":null},{"paper":null,"slug":"transit-transient-transformer-for-non-line-of","title":"TransiT: Transient Transformer for Non-line-of-sight Videography","date":"2025-03-14","arxiv_id":"2503.11328","n_code_links":0,"syntology":null},{"paper":"/paper/treemeshgpt-artistic-mesh-generation-with","slug":"treemeshgpt-artistic-mesh-generation-with","title":"TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing","date":"2025-03-14","arxiv_id":"2503.11629","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 6 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sail-sg/treemeshgpt"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"va-ar-learning-velocity-aware-action","title":"VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention","date":"2025-03-14","arxiv_id":"2503.11004","n_code_links":0,"syntology":null},{"paper":"/paper/when-do-transformers-outperform-feedforward","slug":"when-do-transformers-outperform-feedforward","title":"When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective","date":"2025-03-14","arxiv_id":"2503.11272","n_code_links":1,"syntology":null},{"paper":null,"slug":"x-ecomla-upcycling-pre-trained-attention-into","title":"X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression","date":"2025-03-14","arxiv_id":"2503.11132","n_code_links":0,"syntology":null},{"paper":"/paper/a-frustratingly-simple-yet-highly-effective","slug":"a-frustratingly-simple-yet-highly-effective","title":"A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1","date":"2025-03-13","arxiv_id":"2503.10635","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vila-lab/m-attack"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-hybrid-architecture-with-efficient-fine","title":"A Hybrid Architecture with Efficient Fine Tuning for Abstractive Patent Document Summarization","date":"2025-03-13","arxiv_id":"2503.10354","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-modal-federated-learning-framework","title":"A Multi-Modal Federated Learning Framework for Remote Sensing Image Classification","date":"2025-03-13","arxiv_id":"2503.10262","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-tool-learning-and-selection-system","title":"Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLM","date":"2025-03-13","arxiv_id":"2503.10071","n_code_links":0,"syntology":null},{"paper":null,"slug":"arled-leveraging-led-based-arman-model-for","title":"ARLED: Leveraging LED-based ARMAN Model for Abstractive Summarization of Persian Long Documents","date":"2025-03-13","arxiv_id":"2503.10233","n_code_links":0,"syntology":null},{"paper":null,"slug":"attentionrag-attention-guided-context-pruning","title":"AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation","date":"2025-03-13","arxiv_id":"2503.10720","n_code_links":0,"syntology":null},{"paper":null,"slug":"audiox-diffusion-transformer-for-anything-to","title":"AudioX: Diffusion Transformer for Anything-to-Audio Generation","date":"2025-03-13","arxiv_id":"2503.10522","n_code_links":0,"syntology":null},{"paper":"/paper/autoregressive-image-generation-with","slug":"autoregressive-image-generation-with","title":"Autoregressive Image Generation with Randomized Parallel Decoding","date":"2025-03-13","arxiv_id":"2503.10568","n_code_links":1,"syntology":{"ran":13,"of":18,"n_ran_checked":7,"n_instrument":6,"unverified":5,"pointer_only":6,"phrase":"13 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; 6 where Syntology's instrument failed) · 5 unverified","official":{"repos":["hp-l33/ARPG"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"category-prompt-mamba-network-for-nuclei","title":"Category Prompt Mamba Network for Nuclei Segmentation and Classification","date":"2025-03-13","arxiv_id":"2503.10422","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-encounters-morphing-attack-detection","title":"ChatGPT Encounters Morphing Attack Detection: Zero-Shot MAD with Multi-Modal Large Language Models and General Vision Models","date":"2025-03-13","arxiv_id":"2503.10937","n_code_links":0,"syntology":null},{"paper":null,"slug":"cocmt-communication-efficient-cross-modal","title":"CoCMT: Communication-Efficient Cross-Modal Transformer for Collaborative Perception","date":"2025-03-13","arxiv_id":"2503.13504","n_code_links":0,"syntology":null},{"paper":null,"slug":"codiphy-a-general-framework-for-applying","title":"CoDiPhy: A General Framework for Applying Denoising Diffusion Models to the Physical Layer of Wireless Communication Systems","date":"2025-03-13","arxiv_id":"2503.10297","n_code_links":0,"syntology":null},{"paper":"/paper/cognitive-mental-llm-leveraging-reasoning-in","slug":"cognitive-mental-llm-leveraging-reasoning-in","title":"Cognitive-Mental-LLM: Evaluating Reasoning in Large Language Models for Mental Health Prediction via Online Text","date":"2025-03-13","arxiv_id":"2503.10095","n_code_links":1,"syntology":null},{"paper":null,"slug":"compositional-subspace-representation-fine","title":"Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models","date":"2025-03-13","arxiv_id":"2503.10617","n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-rectangular-attention-module","title":"Convolutional Rectangular Attention Module","date":"2025-03-13","arxiv_id":"2503.10875","n_code_links":0,"syntology":null},{"paper":null,"slug":"cosh-dit-co-speech-gesture-video-synthesis","title":"Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers","date":"2025-03-13","arxiv_id":"2503.09942","n_code_links":0,"syntology":null},{"paper":null,"slug":"countpath-automating-fragment-counting-in","title":"CountPath: Automating Fragment Counting in Digital Pathology","date":"2025-03-13","arxiv_id":"2503.10520","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-i-look-like-a-cat-n-01-to-you-a-taxonomy","title":"Do I look like a `cat.n.01` to you? A Taxonomy Image Generation Benchmark","date":"2025-03-13","arxiv_id":"2503.10357","n_code_links":0,"syntology":null},{"paper":"/paper/dta-dual-temporal-channel-wise-attention-for","slug":"dta-dual-temporal-channel-wise-attention-for","title":"DTA: Dual Temporal-channel-wise Attention for Spiking Neural Networks","date":"2025-03-13","arxiv_id":"2503.10052","n_code_links":1,"syntology":null},{"paper":null,"slug":"edge-fog-computing-enabled-eeg-data","title":"Edge-Fog Computing-Enabled EEG Data Compression via Asymmetrical Variational Discrete Cosine Transform Network","date":"2025-03-13","arxiv_id":"2503.09961","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-recognition-with-clip-and-sequential","title":"Emotion Recognition with CLIP and Sequential Learning","date":"2025-03-13","arxiv_id":"2503.09929","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-mutual-empowerment-between-wireless","title":"DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey","date":"2025-03-13","arxiv_id":"2503.09956","n_code_links":0,"syntology":null},{"paper":null,"slug":"extreme-learning-machines-for-attention-based","title":"Extreme Learning Machines for Attention-based Multiple Instance Learning in Whole-Slide Image Classification","date":"2025-03-13","arxiv_id":"2503.10510","n_code_links":0,"syntology":null},{"paper":"/paper/fg-rag-enhancing-query-focused-summarization","slug":"fg-rag-enhancing-query-focused-summarization","title":"FG-RAG: Enhancing Query-Focused Summarization with Context-Aware Fine-Grained Graph RAG","date":"2025-03-13","arxiv_id":"2504.07103","n_code_links":1,"syntology":null},{"paper":null,"slug":"fixed-point-rnns-from-diagonal-to-dense-in-a","title":"Fixed-Point RNNs: From Diagonal to Dense in a Few Iterations","date":"2025-03-13","arxiv_id":"2503.10799","n_code_links":0,"syntology":null},{"paper":"/paper/groundingsuite-measuring-complex-multi","slug":"groundingsuite-measuring-complex-multi","title":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding","date":"2025-03-13","arxiv_id":"2503.10596","n_code_links":1,"syntology":null},{"paper":"/paper/gumiho-a-hybrid-architecture-to-prioritize","slug":"gumiho-a-hybrid-architecture-to-prioritize","title":"Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding","date":"2025-03-13","arxiv_id":"2503.10135","n_code_links":0,"syntology":{"ran":12,"of":15,"n_ran_checked":8,"n_instrument":4,"unverified":3,"pointer_only":8,"phrase":"12 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; 4 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"h2-marl-multi-agent-reinforcement-learning","title":"H2-MARL: Multi-Agent Reinforcement Learning for Pareto Optimality in Hospital Capacity Strain and Human Mobility during Epidemic","date":"2025-03-13","arxiv_id":"2503.10907","n_code_links":0,"syntology":null},{"paper":null,"slug":"heightformer-learning-height-prediction-in","title":"HeightFormer: Learning Height Prediction in Voxel Features for Roadside Vision Centric 3D Object Detection via Transformer","date":"2025-03-13","arxiv_id":"2503.10777","n_code_links":0,"syntology":null},{"paper":"/paper/how-do-multimodal-large-language-models","slug":"how-do-multimodal-large-language-models","title":"How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape Game","date":"2025-03-13","arxiv_id":"2503.10042","n_code_links":1,"syntology":null},{"paper":null,"slug":"interactive-multimodal-fusion-with-temporal","title":"Interactive Multimodal Fusion with Temporal Modeling","date":"2025-03-13","arxiv_id":"2503.10523","n_code_links":0,"syntology":null},{"paper":null,"slug":"it-is-too-many-options-pitfalls-of-multiple","title":"It is Too Many Options: Pitfalls of Multiple-Choice Questions in Generative AI and Medical Education","date":"2025-03-13","arxiv_id":"2503.13508","n_code_links":0,"syntology":null},{"paper":null,"slug":"kolmogorov-arnold-attention-is-learnable","title":"Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?","date":"2025-03-13","arxiv_id":"2503.10632","n_code_links":0,"syntology":null},{"paper":null,"slug":"kv-distill-nearly-lossless-learnable-context","title":"KV-Distill: Nearly Lossless Learnable Context Compression for LLMs","date":"2025-03-13","arxiv_id":"2503.10337","n_code_links":0,"syntology":null},{"paper":"/paper/kvq-boosting-video-quality-assessment-via","slug":"kvq-boosting-video-quality-assessment-via","title":"KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception","date":"2025-03-13","arxiv_id":"2503.10259","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":5,"n_instrument":4,"unverified":4,"pointer_only":13,"phrase":"9 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["qyp2000/kvq"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/lhm-large-animatable-human-reconstruction","slug":"lhm-large-animatable-human-reconstruction","title":"LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds","date":"2025-03-13","arxiv_id":"2503.10625","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":["aigc3d/LHM"],"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"]}}}],"record_sha256":"db9c5455483a9953defbb196147fcd45adb3006198e71c2361bd7316cc552f1b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}