{"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/2","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":2,"pages_in_order":249,"rows_per_page":100,"rows":[101,200],"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","next":"/method/multi-head-attention/papers/3","papers":[{"paper":null,"slug":"machine-vs-machine-using-ai-to-tackle","title":"Machine vs Machine: Using AI to Tackle Generative AI Threats in Assessment","date":"2025-05-31","arxiv_id":"2506.02046","n_code_links":0,"syntology":null},{"paper":null,"slug":"power-of-two-pot-weights-in-large-language","title":"Power-of-Two (PoT) Weights in Large Language Models (LLMs)","date":"2025-05-31","arxiv_id":"2506.00315","n_code_links":0,"syntology":null},{"paper":"/paper/translate-with-care-addressing-gender-bias","slug":"translate-with-care-addressing-gender-bias","title":"Translate With Care: Addressing Gender Bias, Neutrality, and Reasoning in Large Language Model Translations","date":"2025-05-31","arxiv_id":"2506.00748","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-threat-vectors-and-risk","title":"Adversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation Systems","date":"2025-05-30","arxiv_id":"2506.00281","n_code_links":0,"syntology":null},{"paper":"/paper/agent-x-evaluating-deep-multimodal-reasoning","slug":"agent-x-evaluating-deep-multimodal-reasoning","title":"Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks","date":"2025-05-30","arxiv_id":"2505.24876","n_code_links":1,"syntology":null},{"paper":"/paper/clueanchor-clue-anchored-knowledge-reasoning","slug":"clueanchor-clue-anchored-knowledge-reasoning","title":"ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation","date":"2025-05-30","arxiv_id":"2505.24388","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-attention-speculative-decoding","title":"Cross-Attention Speculative Decoding","date":"2025-05-30","arxiv_id":"2505.24544","n_code_links":0,"syntology":null},{"paper":null,"slug":"d2af-a-dual-driven-annotation-and-filtering","title":"D2AF: A Dual-Driven Annotation and Filtering Framework for Visual Grounding","date":"2025-05-30","arxiv_id":"2505.24372","n_code_links":0,"syntology":null},{"paper":null,"slug":"interpretable-phenotyping-of-heart-failure","title":"Interpretable phenotyping of Heart Failure patients with Dutch discharge letters","date":"2025-05-30","arxiv_id":"2505.24619","n_code_links":0,"syntology":null},{"paper":"/paper/interpreting-large-text-to-image-diffusion","slug":"interpreting-large-text-to-image-diffusion","title":"Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning","date":"2025-05-30","arxiv_id":"2505.24360","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-intermediate-features-of-vision","title":"Leveraging Intermediate Features of Vision Transformer for Face Anti-Spoofing","date":"2025-05-30","arxiv_id":"2505.24402","n_code_links":0,"syntology":null},{"paper":null,"slug":"lpass-linear-probes-as-stepping-stones-for","title":"LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs","date":"2025-05-30","arxiv_id":"2505.24451","n_code_links":0,"syntology":null},{"paper":"/paper/mamba-knockout-for-unraveling-factual","slug":"mamba-knockout-for-unraveling-factual","title":"Mamba Knockout for Unraveling Factual Information Flow","date":"2025-05-30","arxiv_id":"2505.24244","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nirendy/mamba-knockout"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/mastering-massive-multi-task-reinforcement","slug":"mastering-massive-multi-task-reinforcement","title":"Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer","date":"2025-05-30","arxiv_id":"2505.24378","n_code_links":1,"syntology":null},{"paper":"/paper/model-guided-network-with-cluster-based","slug":"model-guided-network-with-cluster-based","title":"Model-Guided Network with Cluster-Based Operators for Spatio-Spectral Super-Resolution","date":"2025-05-30","arxiv_id":"2505.24605","n_code_links":1,"syntology":null},{"paper":"/paper/mofgpt-generative-design-of-metal-organic","slug":"mofgpt-generative-design-of-metal-organic","title":"MOFGPT: Generative Design of Metal-Organic Frameworks using Language Models","date":"2025-05-30","arxiv_id":"2506.00198","n_code_links":1,"syntology":null},{"paper":null,"slug":"pcie-pose-solution-for-egoexo4d-pose-and","title":"PCIE_Pose Solution for EgoExo4D Pose and Proficiency Estimation Challenge","date":"2025-05-30","arxiv_id":"2505.24411","n_code_links":0,"syntology":null},{"paper":null,"slug":"persianmedqa-language-centric-evaluation-of","title":"PersianMedQA: Language-Centric Evaluation of LLMs in the Persian Medical Domain","date":"2025-05-30","arxiv_id":"2506.00250","n_code_links":0,"syntology":null},{"paper":null,"slug":"realdrive-retrieval-augmented-driving-with","title":"RealDrive: Retrieval-Augmented Driving with Diffusion Models","date":"2025-05-30","arxiv_id":"2505.24808","n_code_links":0,"syntology":null},{"paper":null,"slug":"sppsformer-high-quality-superpoint-based","title":"SPPSFormer: High-quality Superpoint-based Transformer for Roof Plane Instance Segmentation from Point Clouds","date":"2025-05-30","arxiv_id":"2505.24475","n_code_links":0,"syntology":null},{"paper":null,"slug":"when-gpt-spills-the-tea-comprehensive","title":"When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs","date":"2025-05-30","arxiv_id":"2506.00197","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-semantic-and-label-perturbation","slug":"adversarial-semantic-and-label-perturbation","title":"Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute Recognition","date":"2025-05-29","arxiv_id":"2505.23313","n_code_links":2,"syntology":null},{"paper":null,"slug":"atlas-learning-to-optimally-memorize-the","title":"ATLAS: Learning to Optimally Memorize the Context at Test Time","date":"2025-05-29","arxiv_id":"2505.23735","n_code_links":0,"syntology":null},{"paper":null,"slug":"bounded-rationality-for-llms-satisficing","title":"Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time","date":"2025-05-29","arxiv_id":"2505.23729","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-the-gap-between-semantic-and-user","title":"Bridging the Gap Between Semantic and User Preference Spaces for Multi-modal Music Representation Learning","date":"2025-05-29","arxiv_id":"2505.23298","n_code_links":0,"syntology":null},{"paper":null,"slug":"cf-detr-coarse-to-fine-transformer-for-real","title":"CF-DETR: Coarse-to-Fine Transformer for Real-Time Object Detection","date":"2025-05-29","arxiv_id":"2505.23317","n_code_links":0,"syntology":null},{"paper":null,"slug":"critical-batch-size-revisited-a-simple","title":"Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model Training","date":"2025-05-29","arxiv_id":"2505.23971","n_code_links":0,"syntology":null},{"paper":"/paper/da-vpt-semantic-guided-visual-prompt-tuning","slug":"da-vpt-semantic-guided-visual-prompt-tuning","title":"DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers","date":"2025-05-29","arxiv_id":"2505.23694","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 4 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; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["noahsark/da-vpt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"data-efficient-meta-models-for-evaluation-of","title":"Data-efficient Meta-models for Evaluation of Context-based Questions and Answers in LLMs","date":"2025-05-29","arxiv_id":"2505.23299","n_code_links":0,"syntology":null},{"paper":null,"slug":"datd3-depthwise-attention-twin-delayed-deep","title":"DATD3: Depthwise Attention Twin Delayed Deep Deterministic Policy Gradient For Model Free Reinforcement Learning Under Output Feedback Control","date":"2025-05-29","arxiv_id":"2505.23857","n_code_links":0,"syntology":null},{"paper":null,"slug":"daunce-data-attribution-through-uncertainty","title":"Daunce: Data Attribution through Uncertainty Estimation","date":"2025-05-29","arxiv_id":"2505.23223","n_code_links":0,"syntology":null},{"paper":null,"slug":"decom-renorm-merge-model-merging-on-the-right","title":"Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking","date":"2025-05-29","arxiv_id":"2505.23117","n_code_links":0,"syntology":null},{"paper":"/paper/deep-modeling-and-optimization-of-medical","slug":"deep-modeling-and-optimization-of-medical","title":"Deep Modeling and Optimization of Medical Image Classification","date":"2025-05-29","arxiv_id":"2505.23040","n_code_links":1,"syntology":null},{"paper":null,"slug":"differential-gated-self-attention","title":"Differential Gated Self-Attention","date":"2025-05-29","arxiv_id":"2505.24054","n_code_links":0,"syntology":null},{"paper":null,"slug":"dino-r1-incentivizing-reasoning-capability-in","title":"DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models","date":"2025-05-29","arxiv_id":"2505.24025","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-llm-based-code-generation-with","title":"Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach","date":"2025-05-29","arxiv_id":"2505.23953","n_code_links":0,"syntology":null},{"paper":null,"slug":"equivariant-spherical-transformer-for","title":"Equivariant Spherical Transformer for Efficient Molecular Modeling","date":"2025-05-29","arxiv_id":"2505.23086","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-ai-capabilities-in-detecting","slug":"evaluating-ai-capabilities-in-detecting","title":"Evaluating AI capabilities in detecting conspiracy theories on YouTube","date":"2025-05-29","arxiv_id":"2505.23570","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-images-to-signals-are-large-vision","title":"From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?","date":"2025-05-29","arxiv_id":"2505.24030","n_code_links":0,"syntology":null},{"paper":"/paper/hyperpointformer-multimodal-fusion-in-3d","slug":"hyperpointformer-multimodal-fusion-in-3d","title":"HyperPointFormer: Multimodal Fusion in 3D Space with Dual-Branch Cross-Attention Transformers","date":"2025-05-29","arxiv_id":"2505.23206","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-regulate-a-new-event-level","title":"Learning to Regulate: A New Event-Level Dataset of Capital Control Measures","date":"2025-05-29","arxiv_id":"2505.23025","n_code_links":0,"syntology":null},{"paper":null,"slug":"matryoshka-model-learning-for-improved","title":"Matryoshka Model Learning for Improved Elastic Student Models","date":"2025-05-29","arxiv_id":"2505.23337","n_code_links":0,"syntology":null},{"paper":null,"slug":"mcp-safety-training-learning-to-refuse","title":"MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment","date":"2025-05-29","arxiv_id":"2505.23634","n_code_links":0,"syntology":null},{"paper":null,"slug":"patient-domain-supervised-contrastive","title":"Patient Domain Supervised Contrastive Learning for Lung Sound Classification Using Mobile Phone","date":"2025-05-29","arxiv_id":"2505.23132","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-association-biases-in-llm-moderation","title":"Probing Association Biases in LLM Moderation Over-Sensitivity","date":"2025-05-29","arxiv_id":"2505.23914","n_code_links":0,"syntology":null},{"paper":null,"slug":"query-routing-for-retrieval-augmented","title":"Query Routing for Retrieval-Augmented Language Models","date":"2025-05-29","arxiv_id":"2505.23052","n_code_links":0,"syntology":null},{"paper":null,"slug":"reducing-latency-in-llm-based-natural","title":"Reducing Latency in LLM-Based Natural Language Commands Processing for Robot Navigation","date":"2025-05-29","arxiv_id":"2506.00075","n_code_links":0,"syntology":null},{"paper":"/paper/table-r1-inference-time-scaling-for-table","slug":"table-r1-inference-time-scaling-for-table","title":"Table-R1: Inference-Time Scaling for Table Reasoning","date":"2025-05-29","arxiv_id":"2505.23621","n_code_links":1,"syntology":null},{"paper":"/paper/the-warmup-dilemma-how-learning-rate","slug":"the-warmup-dilemma-how-learning-rate","title":"The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence","date":"2025-05-29","arxiv_id":"2505.23420","n_code_links":1,"syntology":null},{"paper":"/paper/vf-eval-evaluating-multimodal-llms-for","slug":"vf-eval-evaluating-multimodal-llms-for","title":"VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos","date":"2025-05-29","arxiv_id":"2505.23693","n_code_links":1,"syntology":null},{"paper":null,"slug":"agent-unirag-a-trainable-open-source-llm","title":"Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems","date":"2025-05-28","arxiv_id":"2505.22571","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-enhanced-prompt-decision","title":"Attention-Enhanced Prompt Decision Transformers for UAV-Assisted Communications with AoI","date":"2025-05-28","arxiv_id":"2505.22170","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-the-cloak-unveiling-chinese-cloaked","title":"Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon","date":"2025-05-28","arxiv_id":"2505.22184","n_code_links":0,"syntology":null},{"paper":"/paper/climate-finance-bench","slug":"climate-finance-bench","title":"Climate Finance Bench","date":"2025-05-28","arxiv_id":"2505.22752","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextual-memory-intelligence-a-foundational","title":"Contextual Memory Intelligence -- A Foundational Paradigm for Human-AI Collaboration and Reflective Generative AI Systems","date":"2025-05-28","arxiv_id":"2506.05370","n_code_links":0,"syntology":null},{"paper":"/paper/cross-modal-rag-sub-dimensional-retrieval","slug":"cross-modal-rag-sub-dimensional-retrieval","title":"Cross-modal RAG: Sub-dimensional Retrieval-Augmented Text-to-Image Generation","date":"2025-05-28","arxiv_id":"2505.21956","n_code_links":1,"syntology":null},{"paper":"/paper/hidream-i1-a-high-efficient-image-generative","slug":"hidream-i1-a-high-efficient-image-generative","title":"HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer","date":"2025-05-28","arxiv_id":"2505.22705","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hidream-ai/hidream-e1","hidream-ai/hidream-i1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improving-qa-efficiency-with-distilbert-fine","title":"Improving QA Efficiency with DistilBERT: Fine-Tuning and Inference on mobile Intel CPUs","date":"2025-05-28","arxiv_id":"2505.22937","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-mllm-knowledge-distillation-for-out-of","title":"Multi-MLLM Knowledge Distillation for Out-of-Context News Detection","date":"2025-05-28","arxiv_id":"2505.22517","n_code_links":0,"syntology":null},{"paper":null,"slug":"multiformer-a-multi-person-pose-estimation","title":"MultiFormer: A Multi-Person Pose Estimation System Based on CSI and Attention Mechanism","date":"2025-05-28","arxiv_id":"2505.22555","n_code_links":0,"syntology":null},{"paper":"/paper/ragppi-rag-benchmark-for-protein-protein","slug":"ragppi-rag-benchmark-for-protein-protein","title":"RAGPPI: RAG Benchmark for Protein-Protein Interactions in Drug Discovery","date":"2025-05-28","arxiv_id":"2505.23823","n_code_links":1,"syntology":null},{"paper":null,"slug":"say-what-you-mean-natural-language-access","title":"Say What You Mean: Natural Language Access Control with Large Language Models for Internet of Things","date":"2025-05-28","arxiv_id":"2505.23835","n_code_links":0,"syntology":null},{"paper":null,"slug":"skewroute-training-free-llm-routing-for","title":"SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context","date":"2025-05-28","arxiv_id":"2505.23841","n_code_links":0,"syntology":null},{"paper":null,"slug":"up-slam-adaptively-structured-gaussian-slam","title":"UP-SLAM: Adaptively Structured Gaussian SLAM with Uncertainty Prediction in Dynamic Environments","date":"2025-05-28","arxiv_id":"2505.22335","n_code_links":0,"syntology":null},{"paper":"/paper/update-your-transformer-to-the-latest-release","slug":"update-your-transformer-to-the-latest-release","title":"Update Your Transformer to the Latest Release: Re-Basin of Task Vectors","date":"2025-05-28","arxiv_id":"2505.22697","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 3 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["aimagelab/transfusion"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/vrag-rl-empower-vision-perception-based-rag","slug":"vrag-rl-empower-vision-perception-based-rag","title":"VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning","date":"2025-05-28","arxiv_id":"2505.22019","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":["alibaba-nlp/vrag"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/a-domain-adaptation-neural-network-for","slug":"a-domain-adaptation-neural-network-for","title":"A domain adaptation neural network for digital twin-supported fault diagnosis","date":"2025-05-27","arxiv_id":"2505.21046","n_code_links":1,"syntology":null},{"paper":"/paper/agrifm-a-multi-source-temporal-remote-sensing","slug":"agrifm-a-multi-source-temporal-remote-sensing","title":"AgriFM: A Multi-source Temporal Remote Sensing Foundation Model for Crop Mapping","date":"2025-05-27","arxiv_id":"2505.21357","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-1d-vision-transformers-and","title":"Beyond 1D: Vision Transformers and Multichannel Signal Images for PPG-to-ECG Reconstruction","date":"2025-05-27","arxiv_id":"2505.21767","n_code_links":0,"syntology":null},{"paper":null,"slug":"continuous-time-attention-pde-guided","title":"Continuous-Time Attention: PDE-Guided Mechanisms for Long-Sequence Transformers","date":"2025-05-27","arxiv_id":"2505.20666","n_code_links":0,"syntology":null},{"paper":null,"slug":"diagnosing-and-resolving-cloud-platform","title":"Diagnosing and Resolving Cloud Platform Instability with Multi-modal RAG LLMs","date":"2025-05-27","arxiv_id":"2505.21419","n_code_links":0,"syntology":null},{"paper":"/paper/explainability-of-large-language-models-using","slug":"explainability-of-large-language-models-using","title":"Explainability of Large Language Models using SMILE: Statistical Model-agnostic Interpretability with Local Explanations","date":"2025-05-27","arxiv_id":"2505.21657","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-prosthetic-memory-to-prosthetic-denial","title":"From prosthetic memory to prosthetic denial: Auditing whether large language models are prone to mass atrocity denialism","date":"2025-05-27","arxiv_id":"2505.21753","n_code_links":0,"syntology":null},{"paper":null,"slug":"had-hybrid-architecture-distillation","title":"HAD: Hybrid Architecture Distillation Outperforms Teacher in Genomic Sequence Modeling","date":"2025-05-27","arxiv_id":"2505.20836","n_code_links":0,"syntology":null},{"paper":null,"slug":"htmnet-a-hybrid-network-with-transformer","title":"HTMNet: A Hybrid Network with Transformer-Mamba Bottleneck Multimodal Fusion for Transparent and Reflective Objects Depth Completion","date":"2025-05-27","arxiv_id":"2505.20904","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-context-scaling-divide-and-conquer-via","title":"Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration","date":"2025-05-27","arxiv_id":"2505.20625","n_code_links":0,"syntology":null},{"paper":"/paper/minute-long-videos-with-dual-parallelisms","slug":"minute-long-videos-with-dual-parallelisms","title":"Minute-Long Videos with Dual Parallelisms","date":"2025-05-27","arxiv_id":"2505.21070","n_code_links":1,"syntology":null},{"paper":null,"slug":"mopformer-motion-primitive-transformer-for","title":"MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition","date":"2025-05-27","arxiv_id":"2505.20744","n_code_links":0,"syntology":null},{"paper":null,"slug":"pause-tokens-strictly-increase-the","title":"Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers","date":"2025-05-27","arxiv_id":"2505.21024","n_code_links":0,"syntology":null},{"paper":null,"slug":"privacy-preserving-chest-x-ray-report","title":"Privacy-Preserving Chest X-ray Report Generation via Multimodal Federated Learning with ViT and GPT-2","date":"2025-05-27","arxiv_id":"2505.21715","n_code_links":0,"syntology":null},{"paper":null,"slug":"sosbench-benchmarking-safety-alignment-on","title":"SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge","date":"2025-05-27","arxiv_id":"2505.21605","n_code_links":0,"syntology":null},{"paper":null,"slug":"absolute-coordinates-make-motion-generation","title":"Absolute Coordinates Make Motion Generation Easy","date":"2025-05-26","arxiv_id":"2505.19377","n_code_links":0,"syntology":null},{"paper":null,"slug":"aggregated-structural-representation-with","title":"Aggregated Structural Representation with Large Language Models for Human-Centric Layout Generation","date":"2025-05-26","arxiv_id":"2505.19554","n_code_links":0,"syntology":null},{"paper":"/paper/amqa-an-adversarial-dataset-for-benchmarking","slug":"amqa-an-adversarial-dataset-for-benchmarking","title":"AMQA: An Adversarial Dataset for Benchmarking Bias of LLMs in Medicine and Healthcare","date":"2025-05-26","arxiv_id":"2505.19562","n_code_links":1,"syntology":null},{"paper":null,"slug":"anveshana-a-new-benchmark-dataset-for-cross","title":"Anveshana: A New Benchmark Dataset for Cross-Lingual Information Retrieval On English Queries and Sanskrit Documents","date":"2025-05-26","arxiv_id":"2505.19494","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-evaluation-of-children-s-speech","title":"Automated evaluation of children's speech fluency for low-resource languages","date":"2025-05-26","arxiv_id":"2505.19671","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-multimodal-knowledge-conflict","slug":"benchmarking-multimodal-knowledge-conflict","title":"Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models","date":"2025-05-26","arxiv_id":"2505.19509","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-specialization-benchmarking-llms-for","title":"Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages","date":"2025-05-26","arxiv_id":"2505.19851","n_code_links":0,"syntology":null},{"paper":"/paper/calibrating-pre-trained-language-classifiers","slug":"calibrating-pre-trained-language-classifiers","title":"Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement","date":"2025-05-26","arxiv_id":"2505.19675","n_code_links":1,"syntology":null},{"paper":null,"slug":"cardiopatternformer-pattern-guided-attention","title":"CardioPatternFormer: Pattern-Guided Attention for Interpretable ECG Classification with Transformer Architecture","date":"2025-05-26","arxiv_id":"2505.20481","n_code_links":0,"syntology":null},{"paper":null,"slug":"conversational-lexicography-querying","title":"Conversational Lexicography: Querying Lexicographic Data on Knowledge Graphs with SPARQL through Natural Language","date":"2025-05-26","arxiv_id":"2505.19971","n_code_links":0,"syntology":null},{"paper":null,"slug":"dependency-parsing-is-more-parameter","title":"Dependency Parsing is More Parameter-Efficient with Normalization","date":"2025-05-26","arxiv_id":"2505.20215","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-of-suicidal-risk-on-social-media-a","title":"Detection of Suicidal Risk on Social Media: A Hybrid Model","date":"2025-05-26","arxiv_id":"2505.23797","n_code_links":0,"syntology":null},{"paper":null,"slug":"dgrag-distributed-graph-based-retrieval","title":"DGRAG: Distributed Graph-based Retrieval-Augmented Generation in Edge-Cloud Systems","date":"2025-05-26","arxiv_id":"2505.19847","n_code_links":0,"syntology":null},{"paper":null,"slug":"doctorrag-medical-rag-fusing-knowledge-with","title":"DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients","date":"2025-05-26","arxiv_id":"2505.19538","n_code_links":0,"syntology":null},{"paper":null,"slug":"electrolyzers-hsi-close-range-multi-scene","title":"Electrolyzers-HSI: Close-Range Multi-Scene Hyperspectral Imaging Benchmark Dataset","date":"2025-05-26","arxiv_id":"2505.20507","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-classification-in-context-in-spanish","title":"Emotion Classification In-Context in Spanish","date":"2025-05-26","arxiv_id":"2505.20571","n_code_links":0,"syntology":null},{"paper":null,"slug":"eslm-risk-averse-selective-language-modeling","title":"ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining","date":"2025-05-26","arxiv_id":"2505.19893","n_code_links":0,"syntology":null},{"paper":"/paper/golf-nrt-integrating-global-context-and-local","slug":"golf-nrt-integrating-global-context-and-local","title":"GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis","date":"2025-05-26","arxiv_id":"2505.19813","n_code_links":1,"syntology":{"ran":15,"of":24,"n_ran_checked":9,"n_instrument":6,"unverified":9,"pointer_only":24,"phrase":"15 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; 6 where Syntology's instrument failed) · 9 unverified","official":{"repos":["klmav-cuc/golf-nrt"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/grokking-explaind-unifying-model-data-and","slug":"grokking-explaind-unifying-model-data-and","title":"Grokking ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior","date":"2025-05-26","arxiv_id":"2505.20076","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["mainlp/explaind"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"3c15536adb9273afec9490087664af13153a08474d6ddfc0231268e0f4e9d31c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}