{"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/4","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":4,"pages_in_order":316,"rows_per_page":100,"rows":[301,400],"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/3","next":"/method/attention/papers/5","papers":[{"paper":null,"slug":"attention-aided-mmse-for-ofdm-channel","title":"Attention-Aided MMSE for OFDM Channel Estimation: Learning Linear Filters with Attention","date":"2025-05-31","arxiv_id":"2506.00452","n_code_links":0,"syntology":null},{"paper":null,"slug":"blockchain-enabled-privacy-preserving-second","title":"Blockchain-Enabled Privacy-Preserving Second-Order Federated Edge Learning in Personalized Healthcare","date":"2025-05-31","arxiv_id":"2506.00416","n_code_links":0,"syntology":null},{"paper":null,"slug":"channel-imposed-fusion-a-simple-yet-effective","title":"Channel-Imposed Fusion: A Simple yet Effective Method for Medical Time Series Classification","date":"2025-05-31","arxiv_id":"2506.00337","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-robot-policies-in-a-world-model","title":"Evaluating Robot Policies in a World Model","date":"2025-05-31","arxiv_id":"2506.00613","n_code_links":0,"syntology":null},{"paper":null,"slug":"finbert2-a-specialized-bidirectional-encoder","title":"FinBERT2: A Specialized Bidirectional Encoder for Bridging the Gap in Finance-Specific Deployment of Large Language Models","date":"2025-05-31","arxiv_id":"2506.06335","n_code_links":0,"syntology":null},{"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":"multi-objective-neural-network-assisted","title":"Multi-Objective Neural Network Assisted Design Optimization of Soft Fin-Ray Grippers for Enhanced Grasping Performance","date":"2025-05-31","arxiv_id":"2506.00494","n_code_links":0,"syntology":null},{"paper":null,"slug":"position-olfaction-standardization-is","title":"Position: Olfaction Standardization is Essential for the Advancement of Embodied Artificial Intelligence","date":"2025-05-31","arxiv_id":"2506.00398","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":null,"slug":"towards-graph-based-privacy-preserving","title":"Towards Graph-Based Privacy-Preserving Federated Learning: ModelNet -- A ResNet-based Model Classification Dataset","date":"2025-05-31","arxiv_id":"2506.00476","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":"/paper/using-diffusion-ensembles-to-estimate","slug":"using-diffusion-ensembles-to-estimate","title":"Using Diffusion Ensembles to Estimate Uncertainty for End-to-End Autonomous Driving","date":"2025-05-31","arxiv_id":"2506.00560","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-lora-merge-with-parameter-pruning","slug":"adaptive-lora-merge-with-parameter-pruning","title":"Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation","date":"2025-05-30","arxiv_id":"2505.24174","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":null,"slug":"bayesian-data-sketching-for-varying","title":"Bayesian Data Sketching for Varying Coefficient Regression Models","date":"2025-05-30","arxiv_id":"2506.00270","n_code_links":0,"syntology":null},{"paper":null,"slug":"cloud-optical-thickness-retrievals-using","title":"Cloud Optical Thickness Retrievals Using Angle Invariant Attention Based Deep Learning Models","date":"2025-05-30","arxiv_id":"2505.24638","n_code_links":0,"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":"decoding-knowledge-attribution-in-mixture-of","title":"Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis","date":"2025-05-30","arxiv_id":"2505.24593","n_code_links":0,"syntology":null},{"paper":null,"slug":"deformable-attention-mechanisms-applied-to","title":"Deformable Attention Mechanisms Applied to Object Detection, case of Remote Sensing","date":"2025-05-30","arxiv_id":"2505.24489","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-text-encoders-for-labor-market","title":"Efficient Text Encoders for Labor Market Analysis","date":"2025-05-30","arxiv_id":"2505.24640","n_code_links":0,"syntology":null},{"paper":null,"slug":"explainable-depression-detection-using-masked","title":"Explainable Depression Detection using Masked Hard Instance Mining","date":"2025-05-30","arxiv_id":"2505.24609","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-hallucinations-to-jailbreaks-rethinking","title":"From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models","date":"2025-05-30","arxiv_id":"2505.24232","n_code_links":0,"syntology":null},{"paper":"/paper/helm-hyperbolic-large-language-models-via","slug":"helm-hyperbolic-large-language-models-via","title":"HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts","date":"2025-05-30","arxiv_id":"2505.24722","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["graph-and-geometric-learning/helm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"interactive-video-generation-via-domain","title":"Interactive Video Generation via Domain Adaptation","date":"2025-05-30","arxiv_id":"2505.24253","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":"/paper/large-language-models-are-locally-linear","slug":"large-language-models-are-locally-linear","title":"Large Language Models are Locally Linear Mappings","date":"2025-05-30","arxiv_id":"2505.24293","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":"lightweight-relational-embedding-in-task","title":"Lightweight Relational Embedding in Task-Interpolated Few-Shot Networks for Enhanced Gastrointestinal Disease Classification","date":"2025-05-30","arxiv_id":"2505.24792","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":"/paper/recalkv-low-rank-kv-cache-compression-via","slug":"recalkv-low-rank-kv-cache-compression-via","title":"ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration","date":"2025-05-30","arxiv_id":"2505.24357","n_code_links":1,"syntology":null},{"paper":"/paper/s3ce-net-spike-guided-spatiotemporal-semantic","slug":"s3ce-net-spike-guided-spatiotemporal-semantic","title":"S3CE-Net: Spike-guided Spatiotemporal Semantic Coupling and Expansion Network for Long Sequence Event Re-Identification","date":"2025-05-30","arxiv_id":"2505.24401","n_code_links":1,"syntology":null},{"paper":"/paper/sale-low-bit-estimation-for-efficient-sparse","slug":"sale-low-bit-estimation-for-efficient-sparse","title":"SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling","date":"2025-05-30","arxiv_id":"2505.24179","n_code_links":1,"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":"/paper/star-net-an-interpretable-model-aided-network","slug":"star-net-an-interpretable-model-aided-network","title":"STAR-Net: An Interpretable Model-Aided Network for Remote Sensing Image Denoising","date":"2025-05-30","arxiv_id":"2505.24327","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-hype-index-an-nlp-driven-measure-of","title":"The Hype Index: an NLP-driven Measure of Market News Attention","date":"2025-05-30","arxiv_id":"2506.06329","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-are-universally-consistent","title":"Transformers Are Universally Consistent","date":"2025-05-30","arxiv_id":"2505.24531","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-failure-modes-of-deep-transformers-and","title":"Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation","date":"2025-05-30","arxiv_id":"2505.24333","n_code_links":0,"syntology":null},{"paper":null,"slug":"unigeo-taming-video-diffusion-for-unified","title":"UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation","date":"2025-05-30","arxiv_id":"2505.24521","n_code_links":0,"syntology":null},{"paper":null,"slug":"visual-embodied-brain-let-multimodal-large","title":"Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces","date":"2025-05-30","arxiv_id":"2506.00123","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":null,"slug":"2506-03177","title":"Deep Learning-Based Breast Cancer Detection in Mammography: A Multi-Center Validation Study in Thai Population","date":"2025-05-29","arxiv_id":"2506.03177","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerated-training-of-federated-learning","title":"Accelerated Training of Federated Learning via Second-Order Methods","date":"2025-05-29","arxiv_id":"2505.23588","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":"/paper/anchorattention-difference-aware-sparse","slug":"anchorattention-difference-aware-sparse","title":"AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity","date":"2025-05-29","arxiv_id":"2505.23520","n_code_links":1,"syntology":null},{"paper":null,"slug":"argus-vision-centric-reasoning-with-grounded","title":"Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought","date":"2025-05-29","arxiv_id":"2505.23766","n_code_links":0,"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":"bayesian-optimization-from-human-feedback","title":"Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds","date":"2025-05-29","arxiv_id":"2505.23673","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-geometric-and-semantic-foundation","title":"Bridging Geometric and Semantic Foundation Models for Generalized Monocular Depth Estimation","date":"2025-05-29","arxiv_id":"2505.23400","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":"characterizing-the-expressivity-of","title":"Characterizing the Expressivity of Transformer Language Models","date":"2025-05-29","arxiv_id":"2505.23623","n_code_links":0,"syntology":null},{"paper":null,"slug":"clac-at-semeval-2025-task-6-a-multi","title":"CLaC at SemEval-2025 Task 6: A Multi-Architecture Approach for Corporate Environmental Promise Verification","date":"2025-05-29","arxiv_id":"2505.23538","n_code_links":0,"syntology":null},{"paper":null,"slug":"clip-ae-clip-assisted-cross-view-audio-visual","title":"CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization","date":"2025-05-29","arxiv_id":"2505.23524","n_code_links":0,"syntology":null},{"paper":"/paper/cora-correspondence-aware-image-editing-using","slug":"cora-correspondence-aware-image-editing-using","title":"Cora: Correspondence-aware image editing using few step diffusion","date":"2025-05-29","arxiv_id":"2505.23907","n_code_links":1,"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":"dimension-reduction-attack-video-generative","title":"Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis","date":"2025-05-29","arxiv_id":"2505.23325","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":"does-machine-unlearning-truly-remove-model","title":"Does Machine Unlearning Truly Remove Model Knowledge? A Framework for Auditing Unlearning in LLMs","date":"2025-05-29","arxiv_id":"2505.23270","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":null,"slug":"generating-fit-check-videos-with-a-handheld","title":"Generating Fit Check Videos with a Handheld Camera","date":"2025-05-29","arxiv_id":"2505.23886","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-positional-autoencoders-as-self","title":"Graph Positional Autoencoders as Self-supervised Learners","date":"2025-05-29","arxiv_id":"2505.23345","n_code_links":0,"syntology":null},{"paper":"/paper/grounded-reinforcement-learning-for-visual","slug":"grounded-reinforcement-learning-for-visual","title":"Grounded Reinforcement Learning for Visual Reasoning","date":"2025-05-29","arxiv_id":"2505.23678","n_code_links":1,"syntology":null},{"paper":null,"slug":"grower-in-the-loop-interactive-reinforcement","title":"Grower-in-the-Loop Interactive Reinforcement Learning for Greenhouse Climate Control","date":"2025-05-29","arxiv_id":"2505.23355","n_code_links":0,"syntology":null},{"paper":"/paper/how-does-response-length-affect-long-form","slug":"how-does-response-length-affect-long-form","title":"How Does Response Length Affect Long-Form Factuality","date":"2025-05-29","arxiv_id":"2505.23295","n_code_links":1,"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":"identity-resolution-of-software-metadata","title":"Identity resolution of software metadata using Large Language Models","date":"2025-05-29","arxiv_id":"2505.23500","n_code_links":0,"syntology":null},{"paper":"/paper/improving-time-series-forecasting-via","slug":"improving-time-series-forecasting-via","title":"Improving Time Series Forecasting via Instance-aware Post-hoc Revision","date":"2025-05-29","arxiv_id":"2505.23583","n_code_links":0,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"interspeech-2025-urgent-speech-enhancement","title":"Interspeech 2025 URGENT Speech Enhancement Challenge","date":"2025-05-29","arxiv_id":"2505.23212","n_code_links":0,"syntology":null},{"paper":"/paper/kvzip-query-agnostic-kv-cache-compression","slug":"kvzip-query-agnostic-kv-cache-compression","title":"KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction","date":"2025-05-29","arxiv_id":"2505.23416","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":4,"n_instrument":5,"unverified":3,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","official":{"repos":["snu-mllab/kvzip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["community","official","unlocated"]}}},{"paper":null,"slug":"layerpeeler-autoregressive-peeling-for-layer","title":"LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization","date":"2025-05-29","arxiv_id":"2505.23740","n_code_links":0,"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":"/paper/lemore-learn-more-details-for-lightweight","slug":"lemore-learn-more-details-for-lightweight","title":"LeMoRe: Learn More Details for Lightweight Semantic Segmentation","date":"2025-05-29","arxiv_id":"2505.23093","n_code_links":1,"syntology":null},{"paper":null,"slug":"let-s-reason-formally-natural-formal-hybrid","title":"Let's Reason Formally: Natural-Formal Hybrid Reasoning Enhances LLM's Math Capability","date":"2025-05-29","arxiv_id":"2505.23703","n_code_links":0,"syntology":null},{"paper":null,"slug":"lola-low-rank-linear-attention-with-sparse","title":"LoLA: Low-Rank Linear Attention With Sparse Caching","date":"2025-05-29","arxiv_id":"2505.23666","n_code_links":0,"syntology":null},{"paper":null,"slug":"mangoleafvit-leveraging-lightweight-vision","title":"MangoLeafViT: Leveraging Lightweight Vision Transformer with Runtime Augmentation for Efficient Mango Leaf Disease Classification","date":"2025-05-29","arxiv_id":"2505.23961","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":"mcfnet-a-multimodal-collaborative-fusion","title":"MCFNet: A Multimodal Collaborative Fusion Network for Fine-Grained Semantic Classification","date":"2025-05-29","arxiv_id":"2505.23365","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}],"record_sha256":"a2d4364eff6259da9f38ae6ba58295ae85555b80424caee52fe0911c2f13e462","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}