{"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/50","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":50,"pages_in_order":316,"rows_per_page":100,"rows":[4901,5000],"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/49","next":"/method/attention/papers/51","papers":[{"paper":"/paper/causal-graphs-meet-thoughts-enhancing-complex","slug":"causal-graphs-meet-thoughts-enhancing-complex","title":"Causal Graphs Meet Thoughts: Enhancing Complex Reasoning in Graph-Augmented LLMs","date":"2025-01-24","arxiv_id":"2501.14892","n_code_links":1,"syntology":null},{"paper":null,"slug":"chain-of-retrieval-augmented-generation","title":"Chain-of-Retrieval Augmented Generation","date":"2025-01-24","arxiv_id":"2501.14342","n_code_links":0,"syntology":null},{"paper":null,"slug":"characteristic-specific-partial-fine-tuning","title":"Characteristic-Specific Partial Fine-Tuning for Efficient Emotion and Speaker Adaptation in Codec Language Text-to-Speech Models","date":"2025-01-24","arxiv_id":"2501.14273","n_code_links":0,"syntology":null},{"paper":null,"slug":"darkmind-latent-chain-of-thought-backdoor-in","title":"DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs","date":"2025-01-24","arxiv_id":"2501.18617","n_code_links":0,"syntology":null},{"paper":"/paper/depressionx-knowledge-infused-residual","slug":"depressionx-knowledge-infused-residual","title":"DepressionX: Knowledge Infused Residual Attention for Explainable Depression Severity Assessment","date":"2025-01-24","arxiv_id":"2501.14985","n_code_links":1,"syntology":null},{"paper":null,"slug":"diffusion-based-text-to-music-generation-with","title":"Diffusion based Text-to-Music Generation with Global and Local Text based Conditioning","date":"2025-01-24","arxiv_id":"2501.14680","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-token-reduction-during-generation-for","title":"Dynamic Token Reduction during Generation for Vision Language Models","date":"2025-01-24","arxiv_id":"2501.14204","n_code_links":0,"syntology":null},{"paper":"/paper/fast-think-on-graph-wider-deeper-and-faster","slug":"fast-think-on-graph-wider-deeper-and-faster","title":"Fast Think-on-Graph: Wider, Deeper and Faster Reasoning of Large Language Model on Knowledge Graph","date":"2025-01-24","arxiv_id":"2501.14300","n_code_links":1,"syntology":null},{"paper":null,"slug":"global-semantic-guided-sub-image-feature","title":"Global Semantic-Guided Sub-image Feature Weight Allocation in High-Resolution Large Vision-Language Models","date":"2025-01-24","arxiv_id":"2501.14276","n_code_links":0,"syntology":null},{"paper":"/paper/grappi-a-retrieve-divide-solve-graphrag","slug":"grappi-a-retrieve-divide-solve-graphrag","title":"GraPPI: A Retrieve-Divide-Solve GraphRAG Framework for Large-scale Protein-protein Interaction Exploration","date":"2025-01-24","arxiv_id":"2501.16382","n_code_links":1,"syntology":null},{"paper":"/paper/hermes-a-unified-self-driving-world-model-for","slug":"hermes-a-unified-self-driving-world-model-for","title":"HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation","date":"2025-01-24","arxiv_id":"2501.14729","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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":["lmd0311/hermes"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"idiom-detection-in-sorani-kurdish-texts","title":"Idiom Detection in Sorani Kurdish Texts","date":"2025-01-24","arxiv_id":"2501.14528","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-feature-space-optimization-through","title":"Iterative Feature Space Optimization through Incremental Adaptive Evaluation","date":"2025-01-24","arxiv_id":"2501.14889","n_code_links":0,"syntology":null},{"paper":null,"slug":"light3r-sfm-towards-feed-forward-structure","title":"Light3R-SfM: Towards Feed-forward Structure-from-Motion","date":"2025-01-24","arxiv_id":"2501.14914","n_code_links":0,"syntology":null},{"paper":"/paper/low-rank-prompt-interaction-for-continual","slug":"low-rank-prompt-interaction-for-continual","title":"Low-rank Prompt Interaction for Continual Vision-Language Retrieval","date":"2025-01-24","arxiv_id":"2501.14369","n_code_links":1,"syntology":null},{"paper":null,"slug":"motion-enhancement-to-echocardiography","title":"Motion-enhancement to Echocardiography Segmentation via Inserting a Temporal Attention Module: An Efficient, Adaptable, and Scalable Approach","date":"2025-01-24","arxiv_id":"2501.14929","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-locality-bias-and-results-in-the-long","title":"On the locality bias and results in the Long Range Arena","date":"2025-01-24","arxiv_id":"2501.14850","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-human-pose-estimation-through","title":"Optimizing Human Pose Estimation Through Focused Human and Joint Regions","date":"2025-01-24","arxiv_id":"2501.14439","n_code_links":0,"syntology":null},{"paper":null,"slug":"post-hoc-spurious-correlation-neutralization","title":"Post-hoc Spurious Correlation Neutralization with Single-Weight Fictitious Class Unlearning","date":"2025-01-24","arxiv_id":"2501.14182","n_code_links":0,"syntology":null},{"paper":null,"slug":"predictive-position-estimation-for-remote","title":"Predictive Position Estimation for Remote Surgery under Packet Loss Using the Informer Framework","date":"2025-01-24","arxiv_id":"2501.14664","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-based-cost-effective-evaluation-and","title":"Prompt-Based Cost-Effective Evaluation and Operation of ChatGPT as a Computer Programming Teaching Assistant","date":"2025-01-24","arxiv_id":"2501.17176","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-table-instruction-tuning","slug":"rethinking-table-instruction-tuning","title":"Rethinking Table Instruction Tuning","date":"2025-01-24","arxiv_id":"2501.14693","n_code_links":1,"syntology":null},{"paper":null,"slug":"surface-vision-mamba-leveraging-bidirectional","title":"Surface Vision Mamba: Leveraging Bidirectional State Space Model for Efficient Spherical Manifold Representation","date":"2025-01-24","arxiv_id":"2501.14679","n_code_links":0,"syntology":null},{"paper":null,"slug":"test-time-code-switching-for-cross-lingual","title":"Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction","date":"2025-01-24","arxiv_id":"2501.14144","n_code_links":0,"syntology":null},{"paper":"/paper/tfg-flow-training-free-guidance-in-multimodal","slug":"tfg-flow-training-free-guidance-in-multimodal","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","date":"2025-01-24","arxiv_id":"2501.14216","n_code_links":1,"syntology":null},{"paper":null,"slug":"uditqc-u-net-style-diffusion-transformer-for","title":"UDiTQC: U-Net-Style Diffusion Transformer for Quantum Circuit Synthesis","date":"2025-01-24","arxiv_id":"2501.16380","n_code_links":0,"syntology":null},{"paper":null,"slug":"ultralightsqueezenet-a-deep-learning","title":"UltraLightSqueezeNet: A Deep Learning Architecture for Malaria Classification with up to 54x fewer trainable parameters for resource constrained devices","date":"2025-01-24","arxiv_id":"2501.14172","n_code_links":0,"syntology":null},{"paper":"/paper/vardrop-enhancing-training-efficiency-by","slug":"vardrop-enhancing-training-efficiency-by","title":"VarDrop: Enhancing Training Efficiency by Reducing Variate Redundancy in Periodic Time Series Forecasting","date":"2025-01-24","arxiv_id":"2501.14183","n_code_links":1,"syntology":null},{"paper":"/paper/videoshield-regulating-diffusion-based-video","slug":"videoshield-regulating-diffusion-based-video","title":"VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking","date":"2025-01-24","arxiv_id":"2501.14195","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hurunyi/videoshield"],"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","unlocated"]}}},{"paper":null,"slug":"zeta-leveraging-z-order-curves-for-efficient","title":"ZETA: Leveraging Z-order Curves for Efficient Top-k Attention","date":"2025-01-24","arxiv_id":"2501.14577","n_code_links":0,"syntology":null},{"paper":"/paper/5g-ldpc-linear-transformer-for-channel","slug":"5g-ldpc-linear-transformer-for-channel","title":"5G LDPC Linear Transformer for Channel Decoding","date":"2025-01-23","arxiv_id":"2501.14102","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-study-of-the-plausibility-of-attention","title":"A Study of the Plausibility of Attention between RNN Encoders in Natural Language Inference","date":"2025-01-23","arxiv_id":"2501.13735","n_code_links":0,"syntology":null},{"paper":"/paper/a-transformer-based-autoregressive-decoder","slug":"a-transformer-based-autoregressive-decoder","title":"A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification","date":"2025-01-23","arxiv_id":"2501.13598","n_code_links":1,"syntology":null},{"paper":"/paper/an-efficient-diffusion-based-non","slug":"an-efficient-diffusion-based-non","title":"An Efficient Diffusion-based Non-Autoregressive Solver for Traveling Salesman Problem","date":"2025-01-23","arxiv_id":"2501.13767","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["deitsp/deitsp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bmg-q-localized-bipartite-match-graph","title":"BMG-Q: Localized Bipartite Match Graph Attention Q-Learning for Ride-Pooling Order Dispatch","date":"2025-01-23","arxiv_id":"2501.13448","n_code_links":0,"syntology":null},{"paper":null,"slug":"caprag-a-large-language-model-solution-for","title":"CAPRAG: A Large Language Model Solution for Customer Service and Automatic Reporting using Vector and Graph Retrieval-Augmented Generation","date":"2025-01-23","arxiv_id":"2501.13993","n_code_links":0,"syntology":null},{"paper":null,"slug":"chain-of-grounded-objectives-bridging-process","title":"Chain of Grounded Objectives: Bridging Process and Goal-oriented Prompting for Code Generation","date":"2025-01-23","arxiv_id":"2501.13978","n_code_links":0,"syntology":null},{"paper":null,"slug":"contrast-a-hybrid-architecture-of","title":"Contrast: A Hybrid Architecture of Transformers and State Space Models for Low-Level Vision","date":"2025-01-23","arxiv_id":"2501.13353","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusion-based-perceptual-neural-video","title":"Diffusion-based Perceptual Neural Video Compression with Temporal Diffusion Information Reuse","date":"2025-01-23","arxiv_id":"2501.13528","n_code_links":0,"syntology":null},{"paper":null,"slug":"document-level-sentiment-analysis-of-urdu","title":"Document-Level Sentiment Analysis of Urdu Text Using Deep Learning Techniques","date":"2025-01-23","arxiv_id":"2501.17175","n_code_links":0,"syntology":null},{"paper":"/paper/egohand-ego-centric-hand-pose-estimation-and","slug":"egohand-ego-centric-hand-pose-estimation-and","title":"EgoHand: Ego-centric Hand Pose Estimation and Gesture Recognition with Head-mounted Millimeter-wave Radar and IMUs","date":"2025-01-23","arxiv_id":"2501.13805","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhanced-pec-yolo-for-detecting-improper","title":"Enhanced PEC-YOLO for Detecting Improper Safety Gear Wearing Among Power Line Workers","date":"2025-01-23","arxiv_id":"2501.13981","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-biomedical-relation-extraction-with-1","slug":"enhancing-biomedical-relation-extraction-with-1","title":"Enhancing Biomedical Relation Extraction with Directionality","date":"2025-01-23","arxiv_id":"2501.14079","n_code_links":1,"syntology":null},{"paper":"/paper/ensuring-medical-ai-safety-explainable-ai","slug":"ensuring-medical-ai-safety-explainable-ai","title":"Ensuring Medical AI Safety: Explainable AI-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data","date":"2025-01-23","arxiv_id":"2501.13818","n_code_links":1,"syntology":null},{"paper":null,"slug":"eye-gaze-as-a-signal-for-conveying-user","title":"Eye Gaze as a Signal for Conveying User Attention in Contextual AI Systems","date":"2025-01-23","arxiv_id":"2501.13878","n_code_links":0,"syntology":null},{"paper":"/paper/freeformer-frequency-enhanced-transformer-for","slug":"freeformer-frequency-enhanced-transformer-for","title":"FreEformer: Frequency Enhanced Transformer for Multivariate Time Series Forecasting","date":"2025-01-23","arxiv_id":"2501.13989","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"pointer_only":10,"phrase":"7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","official":{"repos":["jackyue1994/FreEformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"graphrag-under-fire","title":"GraphRAG under Fire","date":"2025-01-23","arxiv_id":"2501.14050","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-contextual-faithfulness-of-large","title":"Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization","date":"2025-01-23","arxiv_id":"2501.13573","n_code_links":0,"syntology":null},{"paper":"/paper/kaa-kolmogorov-arnold-attention-for-enhancing","slug":"kaa-kolmogorov-arnold-attention-for-enhancing","title":"KAA: Kolmogorov-Arnold Attention for Enhancing Attentive Graph Neural Networks","date":"2025-01-23","arxiv_id":"2501.13456","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["luckytiger123/kaa"],"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":"knowledge-informed-multi-agent-trajectory","title":"Knowledge-Informed Multi-Agent Trajectory Prediction at Signalized Intersections for Infrastructure-to-Everything","date":"2025-01-23","arxiv_id":"2501.13461","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-are-vulnerable-to-malicious-prompts","title":"LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language","date":"2025-01-23","arxiv_id":"2501.14073","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-can-plan-only-if-we-tell-them","title":"LLMs Can Plan Only If We Tell Them","date":"2025-01-23","arxiv_id":"2501.13545","n_code_links":0,"syntology":null},{"paper":"/paper/m3pt-a-transformer-for-multimodal-multi-party","slug":"m3pt-a-transformer-for-multimodal-multi-party","title":"M3PT: A Transformer for Multimodal, Multi-Party Social Signal Prediction with Person-aware Blockwise Attention","date":"2025-01-23","arxiv_id":"2501.13416","n_code_links":1,"syntology":null},{"paper":null,"slug":"mambaquant-quantizing-the-mamba-family-with","title":"MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods","date":"2025-01-23","arxiv_id":"2501.13484","n_code_links":0,"syntology":null},{"paper":"/paper/me-cpt-multi-task-enhanced-cross-temporal","slug":"me-cpt-multi-task-enhanced-cross-temporal","title":"ME-CPT: Multi-Task Enhanced Cross-Temporal Point Transformer for Urban 3D Change Detection","date":"2025-01-23","arxiv_id":"2501.14004","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-level-attention-and-contrastive","title":"Multi-Level Attention and Contrastive Learning for Enhanced Text Classification with an Optimized Transformer","date":"2025-01-23","arxiv_id":"2501.13467","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-storage-neural-network-augmented","title":"On Storage Neural Network Augmented Approximate Nearest Neighbor Search","date":"2025-01-23","arxiv_id":"2501.16375","n_code_links":0,"syntology":null},{"paper":null,"slug":"polyhedra-encoding-transformers-enhancing","title":"Polyhedra Encoding Transformers: Enhancing Diffusion MRI Analysis Beyond Voxel and Volumetric Embedding","date":"2025-01-23","arxiv_id":"2501.13352","n_code_links":0,"syntology":null},{"paper":null,"slug":"promptmono-cross-prompting-attention-for-self","title":"PromptMono: Cross Prompting Attention for Self-Supervised Monocular Depth Estimation in Challenging Environments","date":"2025-01-23","arxiv_id":"2501.13796","n_code_links":0,"syntology":null},{"paper":null,"slug":"qmamba-post-training-quantization-for-vision","title":"QMamba: Post-Training Quantization for Vision State Space Models","date":"2025-01-23","arxiv_id":"2501.13624","n_code_links":0,"syntology":null},{"paper":"/paper/quantized-spike-driven-transformer","slug":"quantized-spike-driven-transformer","title":"Quantized Spike-driven Transformer","date":"2025-01-23","arxiv_id":"2501.13492","n_code_links":1,"syntology":{"ran":13,"of":25,"n_ran_checked":13,"n_instrument":0,"unverified":12,"pointer_only":25,"phrase":"13 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified","official":{"repos":["bollossom/qsd-transformer"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":9,"n_ran_no_instrument_failure":11,"n_unverified":12,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"question-answering-on-patient-medical-records","title":"Question Answering on Patient Medical Records with Private Fine-Tuned LLMs","date":"2025-01-23","arxiv_id":"2501.13687","n_code_links":0,"syntology":null},{"paper":"/paper/ramqa-a-unified-framework-for-retrieval","slug":"ramqa-a-unified-framework-for-retrieval","title":"RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering","date":"2025-01-23","arxiv_id":"2501.13297","n_code_links":1,"syntology":null},{"paper":null,"slug":"retrievals-can-be-detrimental-a-contrastive","title":"Retrievals Can Be Detrimental: A Contrastive Backdoor Attack Paradigm on Retrieval-Augmented Diffusion Models","date":"2025-01-23","arxiv_id":"2501.13340","n_code_links":0,"syntology":null},{"paper":null,"slug":"rpo-retrieval-preference-optimization-for","title":"RPO: Retrieval Preference Optimization for Robust Retrieval-Augmented Generation","date":"2025-01-23","arxiv_id":"2501.13726","n_code_links":0,"syntology":null},{"paper":"/paper/safr-neuron-redistribution-for","slug":"safr-neuron-redistribution-for","title":"SAFR: Neuron Redistribution for Interpretability","date":"2025-01-23","arxiv_id":"2501.16374","n_code_links":1,"syntology":null},{"paper":null,"slug":"sigma-differential-rescaling-of-query-key-and","title":"Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models","date":"2025-01-23","arxiv_id":"2501.13629","n_code_links":0,"syntology":null},{"paper":null,"slug":"softplus-attention-with-re-weighting-boosts","title":"Softplus Attention with Re-weighting Boosts Length Extrapolation in Large Language Models","date":"2025-01-23","arxiv_id":"2501.13428","n_code_links":0,"syntology":null},{"paper":null,"slug":"streamingrag-real-time-contextual-retrieval","title":"StreamingRAG: Real-time Contextual Retrieval and Generation Framework","date":"2025-01-23","arxiv_id":"2501.14101","n_code_links":0,"syntology":null},{"paper":"/paper/text-driven-online-action-detection","slug":"text-driven-online-action-detection","title":"Text-driven Online Action Detection","date":"2025-01-23","arxiv_id":"2501.13518","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlearning-clients-features-and-samples-in","title":"Unlearning Clients, Features and Samples in Vertical Federated Learning","date":"2025-01-23","arxiv_id":"2501.13683","n_code_links":0,"syntology":null},{"paper":"/paper/unveiling-discrete-clues-superior-healthcare","slug":"unveiling-discrete-clues-superior-healthcare","title":"Unveiling Discrete Clues: Superior Healthcare Predictions for Rare Diseases","date":"2025-01-23","arxiv_id":"2501.16373","n_code_links":1,"syntology":null},{"paper":"/paper/utilizing-evolution-strategies-to-train","slug":"utilizing-evolution-strategies-to-train","title":"Utilizing Evolution Strategies to Train Transformers in Reinforcement Learning","date":"2025-01-23","arxiv_id":"2501.13883","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":["mafi412/evolution-strategies-and-decision-transformers"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/a-novel-scene-coupling-semantic-mask-network","slug":"a-novel-scene-coupling-semantic-mask-network","title":"A Novel Scene Coupling Semantic Mask Network for Remote Sensing Image Segmentation","date":"2025-01-22","arxiv_id":"2501.13130","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"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":{"repos":["xwmaxwma/rssegmentation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/adaptive-retrieval-without-self-knowledge","slug":"adaptive-retrieval-without-self-knowledge","title":"Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home","date":"2025-01-22","arxiv_id":"2501.12835","n_code_links":0,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":5,"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) · 0 unverified","official":null}},{"paper":null,"slug":"an-ensemble-model-with-attention-based","title":"An Ensemble Model with Attention Based Mechanism for Image Captioning","date":"2025-01-22","arxiv_id":"2501.14828","n_code_links":0,"syntology":null},{"paper":null,"slug":"applications-and-challenges-of-ai-and","title":"Applications and Challenges of AI and Microscopy in Life Science Research: A Review","date":"2025-01-22","arxiv_id":"2501.13135","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-driven-hierarchical-reinforcement","title":"Attention-Driven Hierarchical Reinforcement Learning with Particle Filtering for Source Localization in Dynamic Fields","date":"2025-01-22","arxiv_id":"2501.13084","n_code_links":0,"syntology":null},{"paper":null,"slug":"computational-modelling-of-biological-systems","title":"Computational modelling of biological systems now and then: revisiting tools and visions from the beginning of the century","date":"2025-01-22","arxiv_id":"2501.13142","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamics-of-toxicity-in-political-podcasts","title":"Dynamics of Toxicity in Political Podcasts","date":"2025-01-22","arxiv_id":"2501.12640","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-prompt-compression-with-evaluator","title":"Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference","date":"2025-01-22","arxiv_id":"2501.12959","n_code_links":0,"syntology":null},{"paper":null,"slug":"ehrenfeucht-haussler-rank-and-chain-of","title":"Ehrenfeucht-Haussler Rank and Chain of Thought","date":"2025-01-22","arxiv_id":"2501.12997","n_code_links":0,"syntology":null},{"paper":null,"slug":"emoformer-a-text-independent-speech-emotion","title":"EmoFormer: A Text-Independent Speech Emotion Recognition using a Hybrid Transformer-CNN model","date":"2025-01-22","arxiv_id":"2501.12682","n_code_links":0,"syntology":null},{"paper":null,"slug":"evidencemap-unleashing-the-power-of-small","title":"EvidenceMap: Learning Evidence Analysis to Unleash the Power of Small Language Models for Biomedical Question Answering","date":"2025-01-22","arxiv_id":"2501.12746","n_code_links":0,"syntology":null},{"paper":"/paper/explicit-eigenvalue-regularization-improves","slug":"explicit-eigenvalue-regularization-improves","title":"Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization","date":"2025-01-22","arxiv_id":"2501.12666","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-gpt-s-ability-as-a-judge-in-music","slug":"exploring-gpt-s-ability-as-a-judge-in-music","title":"Exploring GPT's Ability as a Judge in Music Understanding","date":"2025-01-22","arxiv_id":"2501.13261","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-diverse-q-a-benchmarks-for-rag","title":"Generating Diverse Q&A Benchmarks for RAG Evaluation with DataMorgana","date":"2025-01-22","arxiv_id":"2501.12789","n_code_links":0,"syntology":null},{"paper":null,"slug":"grama-adaptive-graph-autoregressive-moving","title":"GRAMA: Adaptive Graph Autoregressive Moving Average Models","date":"2025-01-22","arxiv_id":"2501.12732","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybridization-of-attention-unet-with-repeated","title":"Hybridization of Attention UNet with Repeated Atrous Spatial Pyramid Pooling for Improved Brain Tumour Segmentation","date":"2025-01-22","arxiv_id":"2501.13129","n_code_links":0,"syntology":null},{"paper":"/paper/learning-graph-node-embeddings-by-smooth-pair","slug":"learning-graph-node-embeddings-by-smooth-pair","title":"Learning Graph Node Embeddings by Smooth Pair Sampling","date":"2025-01-22","arxiv_id":"2501.12884","n_code_links":1,"syntology":null},{"paper":"/paper/let-ssms-be-convnets-state-space-modeling","slug":"let-ssms-be-convnets-state-space-modeling","title":"Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions","date":"2025-01-22","arxiv_id":"2501.13230","n_code_links":0,"syntology":null},{"paper":null,"slug":"lit-delving-into-a-simplified-linear","title":"LiT: Delving into a Simplified Linear Diffusion Transformer for Image Generation","date":"2025-01-22","arxiv_id":"2501.12976","n_code_links":0,"syntology":null},{"paper":"/paper/multi-instance-partial-label-learning-with","slug":"multi-instance-partial-label-learning-with","title":"Multi-Instance Partial-Label Learning with Margin Adjustment","date":"2025-01-22","arxiv_id":"2501.12597","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tangw-seu/miplma"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multimodal-ai-on-wound-images-and-clinical","title":"Multimodal AI on Wound Images and Clinical Notes for Home Patient Referral","date":"2025-01-22","arxiv_id":"2501.13247","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-tradeoffs-in-learning-augmented-algorithms","title":"On Tradeoffs in Learning-Augmented Algorithms","date":"2025-01-22","arxiv_id":"2501.12770","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-reward-optimizing-rag-with-reward","title":"RAG-Reward: Optimizing RAG with Reward Modeling and RLHF","date":"2025-01-22","arxiv_id":"2501.13264","n_code_links":0,"syntology":null},{"paper":"/paper/regularization-semi-supervision-and","slug":"regularization-semi-supervision-and","title":"Regularization, Semi-supervision, and Supervision for a Plausible Attention-Based Explanation","date":"2025-01-22","arxiv_id":"2501.12775","n_code_links":1,"syntology":null},{"paper":null,"slug":"separated-inter-intra-modal-fusion-prompts","title":"Separated Inter/Intra-Modal Fusion Prompts for Compositional Zero-Shot Learning","date":"2025-01-22","arxiv_id":"2501.17171","n_code_links":0,"syntology":null},{"paper":"/paper/srmt-shared-memory-for-multi-agent-lifelong","slug":"srmt-shared-memory-for-multi-agent-lifelong","title":"SRMT: Shared Memory for Multi-agent Lifelong Pathfinding","date":"2025-01-22","arxiv_id":"2501.13200","n_code_links":1,"syntology":null},{"paper":"/paper/t-graphormer-using-transformers-for","slug":"t-graphormer-using-transformers-for","title":"T-Graphormer: Using Transformers for Spatiotemporal Forecasting","date":"2025-01-22","arxiv_id":"2501.13274","n_code_links":1,"syntology":null}],"record_sha256":"91d5e5ab0faa8d29f4360f332ce11a1f35e025c12aa18541617f183bb060251a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}