{"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/9","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":9,"pages_in_order":316,"rows_per_page":100,"rows":[801,900],"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/8","next":"/method/attention/papers/10","papers":[{"paper":"/paper/hdlxgraph-bridging-large-language-models-and","slug":"hdlxgraph-bridging-large-language-models-and","title":"HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databases","date":"2025-05-21","arxiv_id":"2505.15701","n_code_links":1,"syntology":null},{"paper":null,"slug":"higher-order-structure-boosts-link-prediction","title":"Higher-order Structure Boosts Link Prediction on Temporal Graphs","date":"2025-05-21","arxiv_id":"2505.15746","n_code_links":0,"syntology":null},{"paper":null,"slug":"hunyuan-turbos-advancing-large-language","title":"Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought","date":"2025-05-21","arxiv_id":"2505.15431","n_code_links":0,"syntology":null},{"paper":null,"slug":"infodeepseek-benchmarking-agentic-information","title":"InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation","date":"2025-05-21","arxiv_id":"2505.15872","n_code_links":0,"syntology":null},{"paper":null,"slug":"internal-and-external-impacts-of-natural","title":"Internal and External Impacts of Natural Language Processing Papers","date":"2025-05-21","arxiv_id":"2505.16061","n_code_links":0,"syntology":null},{"paper":null,"slug":"interspatial-attention-for-efficient-4d-human","title":"Interspatial Attention for Efficient 4D Human Video Generation","date":"2025-05-21","arxiv_id":"2505.15800","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-foundation-models-for-multimodal","title":"Leveraging Foundation Models for Multimodal Graph-Based Action Recognition","date":"2025-05-21","arxiv_id":"2505.15192","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-command","title":"Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: An Empirical Study on Popular Open-Source Projects","date":"2025-05-21","arxiv_id":"2505.15088","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-the-powerful-attention-of-a-pre","slug":"leveraging-the-powerful-attention-of-a-pre","title":"Leveraging the Powerful Attention of a Pre-trained Diffusion Model for Exemplar-based Image Colorization","date":"2025-05-21","arxiv_id":"2505.15812","n_code_links":1,"syntology":null},{"paper":null,"slug":"lftf-locating-first-and-then-fine-tuning-for","title":"LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models","date":"2025-05-21","arxiv_id":"2505.15475","n_code_links":0,"syntology":null},{"paper":"/paper/logicase-effective-test-case-generation-from","slug":"logicase-effective-test-case-generation-from","title":"LogiCase: Effective Test Case Generation from Logical Description in Competitive Programming","date":"2025-05-21","arxiv_id":"2505.15039","n_code_links":0,"syntology":{"ran":11,"of":19,"n_ran_checked":5,"n_instrument":6,"unverified":8,"pointer_only":19,"phrase":"11 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","official":null}},{"paper":null,"slug":"lossless-token-merging-even-without-fine","title":"Lossless Token Merging Even Without Fine-Tuning in Vision Transformers","date":"2025-05-21","arxiv_id":"2505.15160","n_code_links":0,"syntology":null},{"paper":null,"slug":"maxpoolbert-enhancing-bert-classification-via","title":"MaxPoolBERT: Enhancing BERT Classification via Layer- and Token-Wise Aggregation","date":"2025-05-21","arxiv_id":"2505.15696","n_code_links":0,"syntology":null},{"paper":null,"slug":"mechanistic-insights-into-grokking-from-the","title":"Mechanistic Insights into Grokking from the Embedding Layer","date":"2025-05-21","arxiv_id":"2505.15624","n_code_links":0,"syntology":null},{"paper":null,"slug":"mitigating-spurious-correlations-with-causal","title":"Mitigating Spurious Correlations with Causal Logit Perturbation","date":"2025-05-21","arxiv_id":"2505.15246","n_code_links":0,"syntology":null},{"paper":"/paper/monosplat-generalizable-3d-gaussian-splatting","slug":"monosplat-generalizable-3d-gaussian-splatting","title":"MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models","date":"2025-05-21","arxiv_id":"2505.15185","n_code_links":1,"syntology":{"ran":1,"of":6,"n_ran_checked":1,"n_instrument":0,"unverified":5,"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) · 5 unverified","official":{"repos":["cuhk-aim-group/monosplat"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/moonbeam-a-midi-foundation-model-using-both","slug":"moonbeam-a-midi-foundation-model-using-both","title":"Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes","date":"2025-05-21","arxiv_id":"2505.15559","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":null}},{"paper":null,"slug":"nl-debugging-exploiting-natural-language-as","title":"NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging","date":"2025-05-21","arxiv_id":"2505.15356","n_code_links":0,"syntology":null},{"paper":null,"slug":"oversmoothing-oversquashing-heterophily-long","title":"Oversmoothing, \"Oversquashing\", Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning","date":"2025-05-21","arxiv_id":"2505.15547","n_code_links":0,"syntology":null},{"paper":null,"slug":"ranking-free-rag-replacing-re-ranking-with","title":"Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains","date":"2025-05-21","arxiv_id":"2505.16014","n_code_links":0,"syntology":null},{"paper":null,"slug":"reppl-recalibrating-perplexity-by-uncertainty","title":"RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detection","date":"2025-05-21","arxiv_id":"2505.15386","n_code_links":0,"syntology":null},{"paper":null,"slug":"reranking-with-compressed-document","title":"Reranking with Compressed Document Representation","date":"2025-05-21","arxiv_id":"2505.15394","n_code_links":0,"syntology":null},{"paper":"/paper/rlbenchnet-the-right-network-for-the-right","slug":"rlbenchnet-the-right-network-for-the-right","title":"RLBenchNet: The Right Network for the Right Reinforcement Learning Task","date":"2025-05-21","arxiv_id":"2505.15040","n_code_links":1,"syntology":null},{"paper":null,"slug":"robo-dm-data-management-for-large-robot","title":"Robo-DM: Data Management For Large Robot Datasets","date":"2025-05-21","arxiv_id":"2505.15558","n_code_links":0,"syntology":null},{"paper":null,"slug":"rot-enhancing-table-reasoning-with-iterative","title":"RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals","date":"2025-05-21","arxiv_id":"2505.15110","n_code_links":0,"syntology":null},{"paper":"/paper/sama-unet-enhancing-medical-image","slug":"sama-unet-enhancing-medical-image","title":"SAMA-UNet: Enhancing Medical Image Segmentation with Self-Adaptive Mamba-Like Attention and Causal-Resonance Learning","date":"2025-05-21","arxiv_id":"2505.15234","n_code_links":1,"syntology":null},{"paper":"/paper/scaling-diffusion-transformers-efficiently","slug":"scaling-diffusion-transformers-efficiently","title":"Scaling Diffusion Transformers Efficiently via $μ$P","date":"2025-05-21","arxiv_id":"2505.15270","n_code_links":1,"syntology":null},{"paper":null,"slug":"seeing-the-trees-for-the-forest-rethinking","title":"Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding","date":"2025-05-21","arxiv_id":"2505.15123","n_code_links":0,"syntology":null},{"paper":null,"slug":"set-llm-a-permutation-invariant-llm","title":"Set-LLM: A Permutation-Invariant LLM","date":"2025-05-21","arxiv_id":"2505.15433","n_code_links":0,"syntology":null},{"paper":null,"slug":"short-range-dependency-effects-on-transformer","title":"Short-Range Dependency Effects on Transformer Instability and a Decomposed Attention Solution","date":"2025-05-21","arxiv_id":"2505.15548","n_code_links":0,"syntology":null},{"paper":"/paper/silent-leaks-implicit-knowledge-extraction","slug":"silent-leaks-implicit-knowledge-extraction","title":"Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries","date":"2025-05-21","arxiv_id":"2505.15420","n_code_links":1,"syntology":null},{"paper":null,"slug":"single-llm-multiple-roles-a-unified-retrieval","title":"Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization","date":"2025-05-21","arxiv_id":"2505.15444","n_code_links":0,"syntology":null},{"paper":null,"slug":"small-language-models-in-the-real-world","title":"Small Language Models in the Real World: Insights from Industrial Text Classification","date":"2025-05-21","arxiv_id":"2505.16078","n_code_links":0,"syntology":null},{"paper":"/paper/sonnet-spectral-operator-neural-network-for","slug":"sonnet-spectral-operator-neural-network-for","title":"Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting","date":"2025-05-21","arxiv_id":"2505.15312","n_code_links":1,"syntology":null},{"paper":null,"slug":"sus-backprop-linear-backpropagation-algorithm","title":"SUS backprop: linear backpropagation algorithm for long inputs in transformers","date":"2025-05-21","arxiv_id":"2505.15080","n_code_links":0,"syntology":null},{"paper":"/paper/the-atlas-of-in-context-learning-how","slug":"the-atlas-of-in-context-learning-how","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","date":"2025-05-21","arxiv_id":"2505.15807","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["pkhdipraja/in-context-atlas"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"time-tracker-mixture-of-experts-enhanced","title":"Time Tracker: Mixture-of-Experts-Enhanced Foundation Time Series Forecasting Model with Decoupled Training Pipelines","date":"2025-05-21","arxiv_id":"2505.15151","n_code_links":0,"syntology":null},{"paper":null,"slug":"uav-flow-colosseo-a-real-world-benchmark-for","title":"UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning","date":"2025-05-21","arxiv_id":"2505.15725","n_code_links":0,"syntology":null},{"paper":null,"slug":"unified-cross-modal-attention-mixer-based","title":"Unified Cross-Modal Attention-Mixer Based Structural-Functional Connectomics Fusion for Neuropsychiatric Disorder Diagnosis","date":"2025-05-21","arxiv_id":"2505.15139","n_code_links":0,"syntology":null},{"paper":null,"slug":"when-can-large-reasoning-models-save-thinking","title":"When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning","date":"2025-05-21","arxiv_id":"2505.15276","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-direct-comparison-of-simultaneously","title":"A Direct Comparison of Simultaneously Recorded Scalp, Around-Ear, and In-Ear EEG for Neural Selective Auditory Attention Decoding to Speech","date":"2025-05-20","arxiv_id":"2505.14478","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-logic-of-general-attention-using-edge","title":"A Logic of General Attention Using Edge-Conditioned Event Models (Extended Version)","date":"2025-05-20","arxiv_id":"2505.14539","n_code_links":0,"syntology":null},{"paper":null,"slug":"aapo-enhance-the-reasoning-capabilities-of","title":"AAPO: Enhance the Reasoning Capabilities of LLMs with Advantage Momentum","date":"2025-05-20","arxiv_id":"2505.14264","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-empowered-channel-estimation-for-block","title":"AI-empowered Channel Estimation for Block-based Active IRS-enhanced Hybrid-field IoT Network","date":"2025-05-20","arxiv_id":"2505.14098","n_code_links":0,"syntology":null},{"paper":null,"slug":"aligning-attention-distribution-to","title":"Aligning Attention Distribution to Information Flow for Hallucination Mitigation in Large Vision-Language Models","date":"2025-05-20","arxiv_id":"2505.14257","n_code_links":0,"syntology":null},{"paper":"/paper/articulatory-feature-prediction-from-surface","slug":"articulatory-feature-prediction-from-surface","title":"Articulatory Feature Prediction from Surface EMG during Speech Production","date":"2025-05-20","arxiv_id":"2505.13814","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-quality-evaluation-of-cervical","title":"Automated Quality Evaluation of Cervical Cytopathology Whole Slide Images Based on Content Analysis","date":"2025-05-20","arxiv_id":"2505.13875","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-dataset-generation-for-knowledge","title":"Automatic Dataset Generation for Knowledge Intensive Question Answering Tasks","date":"2025-05-20","arxiv_id":"2505.14212","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-text-unveiling-privacy-vulnerabilities","title":"Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation","date":"2025-05-20","arxiv_id":"2505.13957","n_code_links":0,"syntology":null},{"paper":"/paper/breaking-bad-tokens-detoxification-of-llms","slug":"breaking-bad-tokens-detoxification-of-llms","title":"Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders","date":"2025-05-20","arxiv_id":"2505.14536","n_code_links":0,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":null}},{"paper":"/paper/cad-coder-an-open-source-vision-language","slug":"cad-coder-an-open-source-vision-language","title":"CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation","date":"2025-05-20","arxiv_id":"2505.14646","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["anniedoris/cad-coder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"choosing-a-model-shaping-a-future-comparing","title":"Choosing a Model, Shaping a Future: Comparing LLM Perspectives on Sustainability and its Relationship with AI","date":"2025-05-20","arxiv_id":"2505.14435","n_code_links":0,"syntology":null},{"paper":null,"slug":"cost-augmented-monte-carlo-tree-search-for","title":"Cost-Augmented Monte Carlo Tree Search for LLM-Assisted Planning","date":"2025-05-20","arxiv_id":"2505.14656","n_code_links":0,"syntology":null},{"paper":null,"slug":"csagc-ids-a-dual-module-deep-learning-network","title":"CSAGC-IDS: A Dual-Module Deep Learning Network Intrusion Detection Model for Complex and Imbalanced Data","date":"2025-05-20","arxiv_id":"2505.14027","n_code_links":0,"syntology":null},{"paper":null,"slug":"disentangled-multi-span-evolutionary-network","title":"Disentangled Multi-span Evolutionary Network against Temporal Knowledge Graph Reasoning","date":"2025-05-20","arxiv_id":"2505.14020","n_code_links":0,"syntology":null},{"paper":null,"slug":"divide-by-question-conquer-by-agent-split-rag","title":"Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning","date":"2025-05-20","arxiv_id":"2505.13994","n_code_links":0,"syntology":null},{"paper":"/paper/do-language-models-use-their-depth","slug":"do-language-models-use-their-depth","title":"Do Language Models Use Their Depth Efficiently?","date":"2025-05-20","arxiv_id":"2505.13898","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["robertcsordas/llm_effective_depth"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dsmentor-enhancing-data-science-agents-with","title":"DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation","date":"2025-05-20","arxiv_id":"2505.14163","n_code_links":0,"syntology":null},{"paper":"/paper/eeg-to-text-translation-a-model-for","slug":"eeg-to-text-translation-a-model-for","title":"EEG-to-Text Translation: A Model for Deciphering Human Brain Activity","date":"2025-05-20","arxiv_id":"2505.13936","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficientllm-efficiency-in-large-language","title":"EfficientLLM: Efficiency in Large Language Models","date":"2025-05-20","arxiv_id":"2505.13840","n_code_links":0,"syntology":null},{"paper":null,"slug":"embedded-mean-field-reinforcement-learning","title":"Embedded Mean Field Reinforcement Learning for Perimeter-defense Game","date":"2025-05-20","arxiv_id":"2505.14209","n_code_links":0,"syntology":null},{"paper":null,"slug":"energy-efficient-deep-reinforcement-learning","title":"Energy-Efficient Deep Reinforcement Learning with Spiking Transformers","date":"2025-05-20","arxiv_id":"2505.14533","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-abstractive-summarization-of","slug":"enhancing-abstractive-summarization-of","title":"Enhancing Abstractive Summarization of Scientific Papers Using Structure Information","date":"2025-05-20","arxiv_id":"2505.14179","n_code_links":1,"syntology":null},{"paper":null,"slug":"eva-red-teaming-gui-agents-via-evolving","title":"EVA: Red-Teaming GUI Agents via Evolving Indirect Prompt Injection","date":"2025-05-20","arxiv_id":"2505.14289","n_code_links":0,"syntology":null},{"paper":null,"slug":"every-pixel-tells-a-story-end-to-end-urdu","title":"Every Pixel Tells a Story: End-to-End Urdu Newspaper OCR","date":"2025-05-20","arxiv_id":"2505.13943","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-image-quality-assessment-from-a-new","title":"Exploring Image Quality Assessment from a New Perspective: Pupil Size","date":"2025-05-20","arxiv_id":"2505.13841","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-jailbreak-attacks-on-llms-through","title":"Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion","date":"2025-05-20","arxiv_id":"2505.14316","n_code_links":0,"syntology":null},{"paper":null,"slug":"flash-d-flashattention-with-hidden-softmax","title":"FLASH-D: FlashAttention with Hidden Softmax Division","date":"2025-05-20","arxiv_id":"2505.14201","n_code_links":0,"syntology":null},{"paper":"/paper/flashkat-understanding-and-addressing","slug":"flashkat-understanding-and-addressing","title":"FlashKAT: Understanding and Addressing Performance Bottlenecks in the Kolmogorov-Arnold Transformer","date":"2025-05-20","arxiv_id":"2505.13813","n_code_links":1,"syntology":null},{"paper":null,"slug":"flowq-energy-guided-flow-policies-for-offline","title":"FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning","date":"2025-05-20","arxiv_id":"2505.14139","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-at-the-crossroads-light-bulb","title":"Generative AI at the Crossroads: Light Bulb, Dynamo, or Microscope?","date":"2025-05-20","arxiv_id":"2505.14588","n_code_links":0,"syntology":null},{"paper":"/paper/grouping-first-attending-smartly-training","slug":"grouping-first-attending-smartly-training","title":"Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers","date":"2025-05-20","arxiv_id":"2505.14687","n_code_links":1,"syntology":null},{"paper":null,"slug":"hausanlp-current-status-challenges-and-future","title":"HausaNLP: Current Status, Challenges and Future Directions for Hausa Natural Language Processing","date":"2025-05-20","arxiv_id":"2505.14311","n_code_links":0,"syntology":null},{"paper":"/paper/informatics-for-food-processing","slug":"informatics-for-food-processing","title":"Informatics for Food Processing","date":"2025-05-20","arxiv_id":"2505.17087","n_code_links":1,"syntology":null},{"paper":"/paper/jolt-sql-joint-loss-tuning-of-text-to-sql","slug":"jolt-sql-joint-loss-tuning-of-text-to-sql","title":"JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling","date":"2025-05-20","arxiv_id":"2505.14305","n_code_links":1,"syntology":{"ran":16,"of":18,"n_ran_checked":12,"n_instrument":4,"unverified":2,"pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 3 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["songjw133/joint-loss-tuning-of-text-to-sql"],"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":"large-language-model-driven-distributed","title":"Large Language Model-Driven Distributed Integrated Multimodal Sensing and Semantic Communications","date":"2025-05-20","arxiv_id":"2505.18194","n_code_links":0,"syntology":null},{"paper":"/paper/latent-flow-transformer","slug":"latent-flow-transformer","title":"Latent Flow Transformer","date":"2025-05-20","arxiv_id":"2505.14513","n_code_links":1,"syntology":null},{"paper":null,"slug":"leancode-understanding-models-better-for-code","title":"LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models","date":"2025-05-20","arxiv_id":"2505.14759","n_code_links":0,"syntology":null},{"paper":"/paper/learning-spatio-temporal-dynamics-for","slug":"learning-spatio-temporal-dynamics-for","title":"Learning Spatio-Temporal Dynamics for Trajectory Recovery via Time-Aware Transformer","date":"2025-05-20","arxiv_id":"2505.13857","n_code_links":2,"syntology":null},{"paper":"/paper/lod1-3d-city-model-from-lidar-the-impact-of","slug":"lod1-3d-city-model-from-lidar-the-impact-of","title":"LOD1 3D City Model from LiDAR: The Impact of Segmentation Accuracy on Quality of Urban 3D Modeling and Morphology Extraction","date":"2025-05-20","arxiv_id":"2505.14747","n_code_links":1,"syntology":null},{"paper":null,"slug":"low-cost-flashattention-with-fused","title":"Low-Cost FlashAttention with Fused Exponential and Multiplication Hardware Operators","date":"2025-05-20","arxiv_id":"2505.14314","n_code_links":0,"syntology":null},{"paper":null,"slug":"mechanistic-fine-tuning-for-in-context","title":"Mechanistic Fine-tuning for In-context Learning","date":"2025-05-20","arxiv_id":"2505.14233","n_code_links":0,"syntology":null},{"paper":"/paper/mgstream-motion-aware-3d-gaussian-for","slug":"mgstream-motion-aware-3d-gaussian-for","title":"MGStream: Motion-aware 3D Gaussian for Streamable Dynamic Scene Reconstruction","date":"2025-05-20","arxiv_id":"2505.13839","n_code_links":1,"syntology":null},{"paper":"/paper/modrwkv-transformer-multimodality-in-linear","slug":"modrwkv-transformer-multimodality-in-linear","title":"ModRWKV: Transformer Multimodality in Linear Time","date":"2025-05-20","arxiv_id":"2505.14505","n_code_links":1,"syntology":null},{"paper":null,"slug":"msdformer-multi-scale-discrete-transformer","title":"MSDformer: Multi-scale Discrete Transformer For Time Series Generation","date":"2025-05-20","arxiv_id":"2505.14202","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-channel-swin-transformer-framework-for","title":"Multi-Channel Swin Transformer Framework for Bearing Remaining Useful Life Prediction","date":"2025-05-20","arxiv_id":"2505.14897","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-rag-driven-anomaly-detection-and","title":"Multimodal RAG-driven Anomaly Detection and Classification in Laser Powder Bed Fusion using Large Language Models","date":"2025-05-20","arxiv_id":"2505.13828","n_code_links":0,"syntology":null},{"paper":"/paper/omnistyle-filtering-high-quality-style","slug":"omnistyle-filtering-high-quality-style","title":"OmniStyle: Filtering High Quality Style Transfer Data at Scale","date":"2025-05-20","arxiv_id":"2505.14028","n_code_links":1,"syntology":null},{"paper":null,"slug":"out-of-distribution-generalization-of-in","title":"Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective","date":"2025-05-20","arxiv_id":"2505.14808","n_code_links":0,"syntology":null},{"paper":"/paper/pierce-the-mists-greet-the-sky-decipher","slug":"pierce-the-mists-greet-the-sky-decipher","title":"Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis","date":"2025-05-20","arxiv_id":"2505.14406","n_code_links":0,"syntology":{"ran":7,"of":7,"n_ran_checked":2,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"plane-geometry-problem-solving-with-multi","title":"Plane Geometry Problem Solving with Multi-modal Reasoning: A Survey","date":"2025-05-20","arxiv_id":"2505.14340","n_code_links":0,"syntology":null},{"paper":"/paper/polar-sparsity-high-throughput-batched-llm","slug":"polar-sparsity-high-throughput-batched-llm","title":"Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity","date":"2025-05-20","arxiv_id":"2505.14884","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["susavlsh10/polar-sparsity"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"predicting-neo-adjuvant-chemotherapy-response","title":"Predicting Neo-Adjuvant Chemotherapy Response in Triple-Negative Breast Cancer Using Pre-Treatment Histopathologic Images","date":"2025-05-20","arxiv_id":"2505.14730","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-bert-for-german-compound-semantics","title":"Probing BERT for German Compound Semantics","date":"2025-05-20","arxiv_id":"2505.14130","n_code_links":0,"syntology":null},{"paper":"/paper/process-vs-outcome-reward-which-is-better-for","slug":"process-vs-outcome-reward-which-is-better-for","title":"Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning","date":"2025-05-20","arxiv_id":"2505.14069","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":["wlzhang2020/reasonrag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/reactdiff-latent-diffusion-for-facial","slug":"reactdiff-latent-diffusion-for-facial","title":"ReactDiff: Latent Diffusion for Facial Reaction Generation","date":"2025-05-20","arxiv_id":"2505.14151","n_code_links":1,"syntology":null},{"paper":"/paper/s3-you-don-t-need-that-much-data-to-train-a","slug":"s3-you-don-t-need-that-much-data-to-train-a","title":"s3: You Don't Need That Much Data to Train a Search Agent via RL","date":"2025-05-20","arxiv_id":"2505.14146","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":3,"n_instrument":4,"unverified":2,"pointer_only":0,"phrase":"7 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; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["pat-jj/s3"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sae-fire-enhancing-earnings-surprise","title":"SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection","date":"2025-05-20","arxiv_id":"2505.14420","n_code_links":0,"syntology":null},{"paper":null,"slug":"safepath-preventing-harmful-reasoning-in","title":"SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment","date":"2025-05-20","arxiv_id":"2505.14667","n_code_links":0,"syntology":null},{"paper":"/paper/sample-and-computationally-efficient-1","slug":"sample-and-computationally-efficient-1","title":"Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation","date":"2025-05-20","arxiv_id":"2505.14821","n_code_links":1,"syntology":null}],"record_sha256":"c49380dab2694338762298e1e8da988e6a8ea8ad77bb04bb6f924d83c2a115c6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}