{"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/8","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":8,"pages_in_order":316,"rows_per_page":100,"rows":[701,800],"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/7","next":"/method/attention/papers/9","papers":[{"paper":"/paper/adams-momentum-itself-can-be-a-normalizer-for","slug":"adams-momentum-itself-can-be-a-normalizer-for","title":"AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training","date":"2025-05-22","arxiv_id":"2505.16363","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":["pku-huzhang/AdamS"],"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":["found_in_text"]}}},{"paper":null,"slug":"align-grag-reasoning-guided-dual-alignment","title":"Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation","date":"2025-05-22","arxiv_id":"2505.16237","n_code_links":0,"syntology":null},{"paper":"/paper/alto-adaptive-length-tokenizer-for","slug":"alto-adaptive-length-tokenizer-for","title":"ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation","date":"2025-05-22","arxiv_id":"2505.16495","n_code_links":1,"syntology":null},{"paper":null,"slug":"anchorformer-differentiable-anchor-attention","title":"AnchorFormer: Differentiable Anchor Attention for Efficient Vision Transformer","date":"2025-05-22","arxiv_id":"2505.16463","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-generalization-performance-of","title":"Assessing the generalization performance of SAM for ureteroscopy scene understanding","date":"2025-05-22","arxiv_id":"2505.17210","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-with-trained-embeddings-provably","title":"Attention with Trained Embeddings Provably Selects Important Tokens","date":"2025-05-22","arxiv_id":"2505.17282","n_code_links":0,"syntology":null},{"paper":"/paper/attributing-response-to-context-a-jensen","slug":"attributing-response-to-context-a-jensen","title":"Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation","date":"2025-05-22","arxiv_id":"2505.16415","n_code_links":0,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"augmenting-llm-reasoning-with-dynamic-notes","title":"Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA","date":"2025-05-22","arxiv_id":"2505.16293","n_code_links":0,"syntology":null},{"paper":"/paper/backdoor-cleaning-without-external-guidance","slug":"backdoor-cleaning-without-external-guidance","title":"Backdoor Cleaning without External Guidance in MLLM Fine-tuning","date":"2025-05-22","arxiv_id":"2505.16916","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xuankunrong/bye"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/beamforming-codebook-aware-channel-knowledge","slug":"beamforming-codebook-aware-channel-knowledge","title":"Beamforming-Codebook-Aware Channel Knowledge Map Construction for Multi-Antenna Systems","date":"2025-05-22","arxiv_id":"2505.16132","n_code_links":1,"syntology":null},{"paper":null,"slug":"better-rates-for-private-linear-regression-in","title":"Better Rates for Private Linear Regression in the Proportional Regime via Aggressive Clipping","date":"2025-05-22","arxiv_id":"2505.16329","n_code_links":0,"syntology":null},{"paper":null,"slug":"bottlenecked-transformers-periodic-kv-cache","title":"Bottlenecked Transformers: Periodic KV Cache Abstraction for Generalised Reasoning","date":"2025-05-22","arxiv_id":"2505.16950","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-complexity-barriers-high-resolution","title":"Breaking Complexity Barriers: High-Resolution Image Restoration with Rank Enhanced Linear Attention","date":"2025-05-22","arxiv_id":"2505.16157","n_code_links":0,"syntology":null},{"paper":null,"slug":"caiformer-a-causal-informed-transformer-for","title":"CAIFormer: A Causal Informed Transformer for Multivariate Time Series Forecasting","date":"2025-05-22","arxiv_id":"2505.16308","n_code_links":0,"syntology":null},{"paper":null,"slug":"chain-of-thought-poisoning-attacks-against-r1","title":"Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems","date":"2025-05-22","arxiv_id":"2505.16367","n_code_links":0,"syntology":null},{"paper":null,"slug":"code-graph-model-cgm-a-graph-integrated-large","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","date":"2025-05-22","arxiv_id":"2505.16901","n_code_links":0,"syntology":null},{"paper":null,"slug":"creatively-upscaling-images-with-global","title":"Creatively Upscaling Images with Global-Regional Priors","date":"2025-05-22","arxiv_id":"2505.16976","n_code_links":0,"syntology":null},{"paper":null,"slug":"dailyqa-a-benchmark-to-evaluate-web-retrieval","title":"DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World Changes","date":"2025-05-22","arxiv_id":"2505.17162","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-driven-breakthroughs-and-future","title":"Data-Driven Breakthroughs and Future Directions in AI Infrastructure: A Comprehensive Review","date":"2025-05-22","arxiv_id":"2505.16771","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-based-recommender-system","title":"Emotion-based Recommender System","date":"2025-05-22","arxiv_id":"2505.16121","n_code_links":0,"syntology":null},{"paper":null,"slug":"erased-or-dormant-rethinking-concept-erasure","title":"Erased or Dormant? Rethinking Concept Erasure Through Reversibility","date":"2025-05-22","arxiv_id":"2505.16174","n_code_links":0,"syntology":null},{"paper":null,"slug":"explain-less-understand-more-jargon-detection","title":"Explain Less, Understand More: Jargon Detection via Personalized Parameter-Efficient Fine-tuning","date":"2025-05-22","arxiv_id":"2505.16227","n_code_links":0,"syntology":null},{"paper":null,"slug":"four-eyes-are-better-than-two-harnessing-the","title":"Four Eyes Are Better Than Two: Harnessing the Collaborative Potential of Large Models via Differentiated Thinking and Complementary Ensembles","date":"2025-05-22","arxiv_id":"2505.16784","n_code_links":0,"syntology":null},{"paper":null,"slug":"fusion-of-foundation-and-vision-transformer","title":"Fusion of Foundation and Vision Transformer Model Features for Dermatoscopic Image Classification","date":"2025-05-22","arxiv_id":"2505.16338","n_code_links":0,"syntology":null},{"paper":"/paper/generative-ai-and-creativity-a-systematic","slug":"generative-ai-and-creativity-a-systematic","title":"Generative AI and Creativity: A Systematic Literature Review and Meta-Analysis","date":"2025-05-22","arxiv_id":"2505.17241","n_code_links":1,"syntology":null},{"paper":"/paper/hierarchical-safety-realignment-lightweight","slug":"hierarchical-safety-realignment-lightweight","title":"Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models","date":"2025-05-22","arxiv_id":"2505.16104","n_code_links":1,"syntology":null},{"paper":null,"slug":"internal-bias-in-reasoning-models-leads-to","title":"Internal Bias in Reasoning Models leads to Overthinking","date":"2025-05-22","arxiv_id":"2505.16448","n_code_links":0,"syntology":null},{"paper":"/paper/janusdna-a-powerful-bi-directional-hybrid-dna","slug":"janusdna-a-powerful-bi-directional-hybrid-dna","title":"JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model","date":"2025-05-22","arxiv_id":"2505.17257","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["qihao-duan/janusdna"],"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":"joint-flow-and-feature-refinement-using","title":"Joint Flow And Feature Refinement Using Attention For Video Restoration","date":"2025-05-22","arxiv_id":"2505.16434","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-normal-patterns-in-musical-loops","title":"Learning Normal Patterns in Musical Loops","date":"2025-05-22","arxiv_id":"2505.23784","n_code_links":0,"syntology":null},{"paper":"/paper/linea-fast-and-accurate-line-detection-using","slug":"linea-fast-and-accurate-line-detection-using","title":"LINEA: Fast and Accurate Line Detection Using Scalable Transformers","date":"2025-05-22","arxiv_id":"2505.16264","n_code_links":1,"syntology":null},{"paper":null,"slug":"m2svid-end-to-end-inpainting-and-refinement","title":"M2SVid: End-to-End Inpainting and Refinement for Monocular-to-Stereo Video Conversion","date":"2025-05-22","arxiv_id":"2505.16565","n_code_links":0,"syntology":null},{"paper":null,"slug":"mage-a-multi-task-architecture-for-gaze","title":"MAGE: A Multi-task Architecture for Gaze Estimation with an Efficient Calibration Module","date":"2025-05-22","arxiv_id":"2505.16384","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-reinforcement-learning-with-minimum","title":"Meta-reinforcement learning with minimum attention","date":"2025-05-22","arxiv_id":"2505.16741","n_code_links":0,"syntology":null},{"paper":"/paper/mitigating-hallucinations-in-vision-language","slug":"mitigating-hallucinations-in-vision-language","title":"Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression","date":"2025-05-22","arxiv_id":"2505.16411","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-generative-ai-for-story-point","title":"Multimodal Generative AI for Story Point Estimation in Software Development","date":"2025-05-22","arxiv_id":"2505.16290","n_code_links":0,"syntology":null},{"paper":null,"slug":"native-segmentation-vision-transformers","title":"Native Segmentation Vision Transformers","date":"2025-05-22","arxiv_id":"2505.16993","n_code_links":0,"syntology":null},{"paper":null,"slug":"only-large-weights-and-not-skip-connections","title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","date":"2025-05-22","arxiv_id":"2505.16284","n_code_links":0,"syntology":null},{"paper":"/paper/openseg-r-improving-open-vocabulary","slug":"openseg-r-improving-open-vocabulary","title":"OpenSeg-R: Improving Open-Vocabulary Segmentation via Step-by-Step Visual Reasoning","date":"2025-05-22","arxiv_id":"2505.16974","n_code_links":1,"syntology":null},{"paper":null,"slug":"partitioning-and-observability-in-linear","title":"Partitioning and Observability in Linear Systems via Submodular Optimization","date":"2025-05-22","arxiv_id":"2505.16169","n_code_links":0,"syntology":null},{"paper":"/paper/path-attention-position-encoding-via","slug":"path-attention-position-encoding-via","title":"PaTH Attention: Position Encoding via Accumulating Householder Transformations","date":"2025-05-22","arxiv_id":"2505.16381","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fla-org/flash-linear-attention","sustcsonglin/flash-linear-attention"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"personalizing-student-agent-interactions","title":"Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval Augmented Generation (RAG)","date":"2025-05-22","arxiv_id":"2505.17238","n_code_links":0,"syntology":null},{"paper":null,"slug":"pursuing-temporal-consistent-video-virtual","title":"Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction","date":"2025-05-22","arxiv_id":"2505.16980","n_code_links":0,"syntology":null},{"paper":"/paper/r1-searcher-incentivizing-the-dynamic","slug":"r1-searcher-incentivizing-the-dynamic","title":"R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning","date":"2025-05-22","arxiv_id":"2505.17005","n_code_links":3,"syntology":{"ran":9,"of":10,"n_ran_checked":8,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"9 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rucaibox/r1-searcher-plus"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"rap-runtime-adaptive-pruning-for-llm","title":"RAP: Runtime-Adaptive Pruning for LLM Inference","date":"2025-05-22","arxiv_id":"2505.17138","n_code_links":0,"syntology":null},{"paper":null,"slug":"realistic-evaluation-of-tabpfn-v2-in-open","title":"Realistic Evaluation of TabPFN v2 in Open Environments","date":"2025-05-22","arxiv_id":"2505.16226","n_code_links":0,"syntology":null},{"paper":null,"slug":"reasoning-in-neurosymbolic-ai","title":"Reasoning in Neurosymbolic AI","date":"2025-05-22","arxiv_id":"2505.20313","n_code_links":0,"syntology":null},{"paper":"/paper/repa-works-until-it-doesn-t-early-stopped","slug":"repa-works-until-it-doesn-t-early-stopped","title":"REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training","date":"2025-05-22","arxiv_id":"2505.16792","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":["nus-hpc-ai-lab/haste"],"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":null,"slug":"representation-discrepancy-bridging-method","title":"Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval","date":"2025-05-22","arxiv_id":"2505.16756","n_code_links":0,"syntology":null},{"paper":null,"slug":"reward-aware-proto-representations-in","title":"Reward-Aware Proto-Representations in Reinforcement Learning","date":"2025-05-22","arxiv_id":"2505.16217","n_code_links":0,"syntology":null},{"paper":null,"slug":"safekey-amplifying-aha-moment-insights-for","title":"SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning","date":"2025-05-22","arxiv_id":"2505.16186","n_code_links":0,"syntology":null},{"paper":null,"slug":"samba-unet-synergizing-sam2-and-mamba-in-unet","title":"SAMba-UNet: Synergizing SAM2 and Mamba in UNet with Heterogeneous Aggregation for Cardiac MRI Segmentation","date":"2025-05-22","arxiv_id":"2505.16304","n_code_links":0,"syntology":null},{"paper":"/paper/scalable-graph-generative-modeling-via","slug":"scalable-graph-generative-modeling-via","title":"Scalable Graph Generative Modeling via Substructure Sequences","date":"2025-05-22","arxiv_id":"2505.16130","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":["zehong-wang/g2pm"],"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":"search-wisely-mitigating-sub-optimal-agentic","title":"Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty","date":"2025-05-22","arxiv_id":"2505.17281","n_code_links":0,"syntology":null},{"paper":null,"slug":"seeing-far-and-clearly-mitigating","title":"Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding","date":"2025-05-22","arxiv_id":"2505.16652","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-classification-enhancement-and","title":"Self-Classification Enhancement and Correction for Weakly Supervised Object Detection","date":"2025-05-22","arxiv_id":"2505.16294","n_code_links":0,"syntology":null},{"paper":"/paper/self-self-extend-the-context-length-with","slug":"self-self-extend-the-context-length-with","title":"SELF: Self-Extend the Context Length With Logistic Growth Function","date":"2025-05-22","arxiv_id":"2505.17296","n_code_links":1,"syntology":null},{"paper":null,"slug":"shade-compact-and-consistent-dynamic-3d","title":"SHaDe: Compact and Consistent Dynamic 3D Reconstruction via Tri-Plane Deformation and Latent Diffusion","date":"2025-05-22","arxiv_id":"2505.16535","n_code_links":0,"syntology":null},{"paper":null,"slug":"shadows-in-the-attention-contextual","title":"Shadows in the Attention: Contextual Perturbation and Representation Drift in the Dynamics of Hallucination in LLMs","date":"2025-05-22","arxiv_id":"2505.16894","n_code_links":0,"syntology":null},{"paper":"/paper/sketchy-bounding-box-supervision-for-3d","slug":"sketchy-bounding-box-supervision-for-3d","title":"Sketchy Bounding-box Supervision for 3D Instance Segmentation","date":"2025-05-22","arxiv_id":"2505.16399","n_code_links":1,"syntology":null},{"paper":null,"slug":"specmaskfoley-steering-pretrained-spectral","title":"SpecMaskFoley: Steering Pretrained Spectral Masked Generative Transformer Toward Synchronized Video-to-audio Synthesis via ControlNet","date":"2025-05-22","arxiv_id":"2505.16195","n_code_links":0,"syntology":null},{"paper":"/paper/style-transfer-with-diffusion-models-for","slug":"style-transfer-with-diffusion-models-for","title":"Style Transfer with Diffusion Models for Synthetic-to-Real Domain Adaptation","date":"2025-05-22","arxiv_id":"2505.16360","n_code_links":1,"syntology":null},{"paper":null,"slug":"swin-transformer-for-robust-cgi-images","title":"Swin Transformer for Robust CGI Images Detection: Intra- and Inter-Dataset Analysis across Multiple Color Spaces","date":"2025-05-22","arxiv_id":"2505.16253","n_code_links":0,"syntology":null},{"paper":null,"slug":"temporal-and-spatial-feature-fusion-framework","title":"Temporal and Spatial Feature Fusion Framework for Dynamic Micro Expression Recognition","date":"2025-05-22","arxiv_id":"2505.16372","n_code_links":0,"syntology":null},{"paper":null,"slug":"temporal-object-captioning-for-street-scene","title":"Temporal Object Captioning for Street Scene Videos from LiDAR Tracks","date":"2025-05-22","arxiv_id":"2505.16594","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-polar-express-optimal-matrix-sign-methods","title":"The Polar Express: Optimal Matrix Sign Methods and Their Application to the Muon Algorithm","date":"2025-05-22","arxiv_id":"2505.16932","n_code_links":0,"syntology":null},{"paper":null,"slug":"three-minds-one-legend-jailbreak-large","title":"Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers","date":"2025-05-22","arxiv_id":"2505.16241","n_code_links":0,"syntology":null},{"paper":"/paper/training-free-efficient-video-generation-via","slug":"training-free-efficient-video-generation-via","title":"Training-Free Efficient Video Generation via Dynamic Token Carving","date":"2025-05-22","arxiv_id":"2505.16864","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-free-reasoning-and-reflection-in","title":"Training-Free Reasoning and Reflection in MLLMs","date":"2025-05-22","arxiv_id":"2505.16151","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-brain-encoders-explain-human-high","slug":"transformer-brain-encoders-explain-human-high","title":"Transformer brain encoders explain human high-level visual responses","date":"2025-05-22","arxiv_id":"2505.17329","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-copilot-learning-from-the-mistake","slug":"transformer-copilot-learning-from-the-mistake","title":"Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning","date":"2025-05-22","arxiv_id":"2505.16270","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jiaruzouu/transformercopilot"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/tropical-attention-neural-algorithmic","slug":"tropical-attention-neural-algorithmic","title":"Tropical Attention: Neural Algorithmic Reasoning for Combinatorial Algorithms","date":"2025-05-22","arxiv_id":"2505.17190","n_code_links":0,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"understanding-differential-transformer","title":"Understanding Differential Transformer Unchains Pretrained Self-Attentions","date":"2025-05-22","arxiv_id":"2505.16333","n_code_links":0,"syntology":null},{"paper":null,"slug":"voxrag-a-step-toward-transcription-free-rag","title":"VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering","date":"2025-05-22","arxiv_id":"2505.17326","n_code_links":0,"syntology":null},{"paper":"/paper/walk-retrieve-simple-yet-effective-zero-shot","slug":"walk-retrieve-simple-yet-effective-zero-shot","title":"Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks","date":"2025-05-22","arxiv_id":"2505.16849","n_code_links":1,"syntology":null},{"paper":"/paper/when-do-llms-admit-their-mistakes","slug":"when-do-llms-admit-their-mistakes","title":"When Do LLMs Admit Their Mistakes? Understanding the Role of Model Belief in Retraction","date":"2025-05-22","arxiv_id":"2505.16170","n_code_links":1,"syntology":null},{"paper":null,"slug":"why-can-accurate-models-be-learned-from","title":"Why Can Accurate Models Be Learned from Inaccurate Annotations?","date":"2025-05-22","arxiv_id":"2505.16159","n_code_links":0,"syntology":null},{"paper":null,"slug":"zebra-llama-towards-extremely-efficient","title":"Zebra-Llama: Towards Extremely Efficient Hybrid Models","date":"2025-05-22","arxiv_id":"2505.17272","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-hyperspectral-pansharpening-using","slug":"zero-shot-hyperspectral-pansharpening-using","title":"Zero-Shot Hyperspectral Pansharpening Using Hysteresis-Based Tuning for Spectral Quality Control","date":"2025-05-22","arxiv_id":"2505.16658","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-taxonomy-of-structure-from-motion-methods","title":"A Taxonomy of Structure from Motion Methods","date":"2025-05-21","arxiv_id":"2505.15814","n_code_links":0,"syntology":null},{"paper":null,"slug":"adue-improving-uncertainty-estimation-head","title":"AdUE: Improving uncertainty estimation head for LoRA adapters in LLMs","date":"2025-05-21","arxiv_id":"2505.15443","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-efficient-private-gpt-never","title":"An Efficient Private GPT Never Autoregressively Decodes","date":"2025-05-21","arxiv_id":"2505.15252","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploratory-approach-towards-investigating","title":"An Exploratory Approach Towards Investigating and Explaining Vision Transformer and Transfer Learning for Brain Disease Detection","date":"2025-05-21","arxiv_id":"2505.16039","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-node-attention-multi-scale-harmonic","title":"Beyond Node Attention: Multi-Scale Harmonic Encoding for Feature-Wise Graph Message Passing","date":"2025-05-21","arxiv_id":"2505.15015","n_code_links":0,"syntology":null},{"paper":null,"slug":"bountybench-dollar-impact-of-ai-agent","title":"BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems","date":"2025-05-21","arxiv_id":"2505.15216","n_code_links":0,"syntology":null},{"paper":null,"slug":"br-taxqa-r-a-dataset-for-question-answering","title":"BR-TaxQA-R: A Dataset for Question Answering with References for Brazilian Personal Income Tax Law, including case law","date":"2025-05-21","arxiv_id":"2505.15916","n_code_links":0,"syntology":null},{"paper":null,"slug":"cebsnet-change-excited-and-background","title":"CEBSNet: Change-Excited and Background-Suppressed Network with Temporal Dependency Modeling for Bitemporal Change Detection","date":"2025-05-21","arxiv_id":"2505.15322","n_code_links":0,"syntology":null},{"paper":"/paper/collaborative-problem-solving-in-an","slug":"collaborative-problem-solving-in-an","title":"Collaborative Problem-Solving in an Optimization Game","date":"2025-05-21","arxiv_id":"2505.15490","n_code_links":1,"syntology":null},{"paper":null,"slug":"convolutional-long-short-term-memory-neural","title":"Convolutional Long Short-Term Memory Neural Networks Based Numerical Simulation of Flow Field","date":"2025-05-21","arxiv_id":"2505.15533","n_code_links":0,"syntology":null},{"paper":null,"slug":"decouple-and-orthogonalize-a-data-free","title":"Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging","date":"2025-05-21","arxiv_id":"2505.15875","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusion-vs-autoregressive-language-models-a","title":"Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective","date":"2025-05-21","arxiv_id":"2505.15045","n_code_links":0,"syntology":null},{"paper":null,"slug":"disco-balances-the-scales-adaptive-domain-and","title":"DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data","date":"2025-05-21","arxiv_id":"2505.15074","n_code_links":0,"syntology":null},{"paper":"/paper/dkv-cache-the-cache-for-diffusion-language","slug":"dkv-cache-the-cache-for-diffusion-language","title":"dKV-Cache: The Cache for Diffusion Language Models","date":"2025-05-21","arxiv_id":"2505.15781","n_code_links":2,"syntology":null},{"paper":null,"slug":"domain-adaptive-skin-lesion-classification","title":"Domain Adaptive Skin Lesion Classification via Conformal Ensemble of Vision Transformers","date":"2025-05-21","arxiv_id":"2505.15997","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-innovation-opportunities-for","title":"Exploring the Innovation Opportunities for Pre-trained Models","date":"2025-05-21","arxiv_id":"2505.15790","n_code_links":0,"syntology":null},{"paper":null,"slug":"filtering-learning-histories-enhances-in","title":"Filtering Learning Histories Enhances In-Context Reinforcement Learning","date":"2025-05-21","arxiv_id":"2505.15143","n_code_links":0,"syntology":null},{"paper":null,"slug":"fourier-invertible-neural-encoder-fine-for","title":"Fourier-Invertible Neural Encoder (FINE) for Homogeneous Flows","date":"2025-05-21","arxiv_id":"2505.15329","n_code_links":0,"syntology":null},{"paper":"/paper/gated-integration-of-low-rank-adaptation-for","slug":"gated-integration-of-low-rank-adaptation-for","title":"Gated Integration of Low-Rank Adaptation for Continual Learning of Language Models","date":"2025-05-21","arxiv_id":"2505.15424","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["liangyanshuo/gainlora"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"guidelines-for-the-quality-assessment-of","title":"Guidelines for the Quality Assessment of Energy-Aware NAS Benchmarks","date":"2025-05-21","arxiv_id":"2505.15631","n_code_links":0,"syntology":null},{"paper":null,"slug":"hallucinate-at-the-last-in-long-response","title":"Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization","date":"2025-05-21","arxiv_id":"2505.15291","n_code_links":0,"syntology":null}],"record_sha256":"85d7fce241d51dd6fbddf824a55f801722074e138bcc6dcdf84a0c7c11813c6d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}