{"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/35","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":35,"pages_in_order":316,"rows_per_page":100,"rows":[3401,3500],"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/34","next":"/method/attention/papers/36","papers":[{"paper":null,"slug":"high-precision-transformer-based-visual","title":"High-Precision Transformer-Based Visual Servoing for Humanoid Robots in Aligning Tiny Objects","date":"2025-03-06","arxiv_id":"2503.04862","n_code_links":0,"syntology":null},{"paper":null,"slug":"hilgen-hierarchically-informed-data","title":"HILGEN: Hierarchically-Informed Data Generation for Biomedical NER Using Knowledgebases and Large Language Models","date":"2025-03-06","arxiv_id":"2503.04930","n_code_links":0,"syntology":null},{"paper":"/paper/hybridnorm-towards-stable-and-efficient","slug":"hybridnorm-towards-stable-and-efficient","title":"HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization","date":"2025-03-06","arxiv_id":"2503.04598","n_code_links":1,"syntology":null},{"paper":null,"slug":"in-depth-analysis-of-graph-based-rag-in-a","title":"In-depth Analysis of Graph-based RAG in a Unified Framework","date":"2025-03-06","arxiv_id":"2503.04338","n_code_links":0,"syntology":null},{"paper":null,"slug":"incentivizing-multi-tenant-split-federated","title":"Incentivizing Multi-Tenant Split Federated Learning for Foundation Models at the Network Edge","date":"2025-03-06","arxiv_id":"2503.04971","n_code_links":0,"syntology":null},{"paper":null,"slug":"interpretable-transformation-and-analysis-of","title":"Interpretable Transformation and Analysis of Timelines through Learning via Surprisability","date":"2025-03-06","arxiv_id":"2503.04502","n_code_links":0,"syntology":null},{"paper":"/paper/joint-masked-reconstruction-and-contrastive","slug":"joint-masked-reconstruction-and-contrastive","title":"Joint Masked Reconstruction and Contrastive Learning for Mining Interactions Between Proteins","date":"2025-03-06","arxiv_id":"2503.04650","n_code_links":1,"syntology":null},{"paper":null,"slug":"layer-specific-scaling-of-positional","title":"Layer-Specific Scaling of Positional Encodings for Superior Long-Context Modeling","date":"2025-03-06","arxiv_id":"2503.04355","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-transformer-based-world-models-with","title":"Learning Transformer-based World Models with Contrastive Predictive Coding","date":"2025-03-06","arxiv_id":"2503.04416","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-wideband-user-scheduling-and-hybrid","title":"Learning Wideband User Scheduling and Hybrid Precoding with Graph Neural Networks","date":"2025-03-06","arxiv_id":"2503.04233","n_code_links":0,"syntology":null},{"paper":null,"slug":"ledit-your-length-extrapolatable-diffusion","title":"LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding","date":"2025-03-06","arxiv_id":"2503.04344","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-large-language-models-to-address","slug":"leveraging-large-language-models-to-address","title":"Leveraging Large Language Models to Address Data Scarcity in Machine Learning: Applications in Graphene Synthesis","date":"2025-03-06","arxiv_id":"2503.04870","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-modal-summarization-in-model-based","title":"Multi-modal Summarization in Model-Based Engineering: Automotive Software Development Case Study","date":"2025-03-06","arxiv_id":"2503.04506","n_code_links":0,"syntology":null},{"paper":null,"slug":"scale-invariant-adversarial-attack-against","title":"Scale-Invariant Adversarial Attack against Arbitrary-scale Super-resolution","date":"2025-03-06","arxiv_id":"2503.04385","n_code_links":0,"syntology":null},{"paper":"/paper/toward-lightweight-and-fast-decoders-for","slug":"toward-lightweight-and-fast-decoders-for","title":"Toward Lightweight and Fast Decoders for Diffusion Models in Image and Video Generation","date":"2025-03-06","arxiv_id":"2503.04871","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-autonomous-reinforcement-learning-for","title":"Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation with Large Language Models","date":"2025-03-06","arxiv_id":"2503.04280","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multimodal-framework-for-topic-propagation","title":"A Multimodal Framework for Topic Propagation Classification in Social Networks","date":"2025-03-05","arxiv_id":"2503.03112","n_code_links":0,"syntology":null},{"paper":"/paper/addressing-overprescribing-challenges-fine","slug":"addressing-overprescribing-challenges-fine","title":"Addressing Overprescribing Challenges: Fine-Tuning Large Language Models for Medication Recommendation Tasks","date":"2025-03-05","arxiv_id":"2503.03687","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["zzhustc2016/lamo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"afford-x-generalizable-and-slim-affordance","title":"Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation","date":"2025-03-05","arxiv_id":"2503.03556","n_code_links":0,"syntology":null},{"paper":null,"slug":"ahcptq-accurate-and-hardware-compatible-post","title":"AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model","date":"2025-03-05","arxiv_id":"2503.03088","n_code_links":0,"syntology":null},{"paper":"/paper/all-atom-diffusion-transformers-unified","slug":"all-atom-diffusion-transformers-unified","title":"All-atom Diffusion Transformers: Unified generative modelling of molecules and materials","date":"2025-03-05","arxiv_id":"2503.03965","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":5,"n_instrument":1,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["facebookresearch/all-atom-diffusion-transformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/an-aspect-extraction-framework-using","slug":"an-aspect-extraction-framework-using","title":"An Aspect Extraction Framework using Different Embedding Types, Learning Models, and Dependency Structure","date":"2025-03-05","arxiv_id":"2503.03512","n_code_links":1,"syntology":null},{"paper":"/paper/analogical-reasoning-inside-large-language","slug":"analogical-reasoning-inside-large-language","title":"Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction","date":"2025-03-05","arxiv_id":"2503.03666","n_code_links":1,"syntology":null},{"paper":"/paper/banet-bilateral-aggregation-network-for","slug":"banet-bilateral-aggregation-network-for","title":"BANet: Bilateral Aggregation Network for Mobile Stereo Matching","date":"2025-03-05","arxiv_id":"2503.03259","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":6,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"8 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["gangweix/banet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":4,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-frontier-llms-replace-annotators-in","slug":"can-frontier-llms-replace-annotators-in","title":"Can Frontier LLMs Replace Annotators in Biomedical Text Mining? Analyzing Challenges and Exploring Solutions","date":"2025-03-05","arxiv_id":"2503.03261","n_code_links":1,"syntology":null},{"paper":null,"slug":"conformal-transformations-for-symmetric-power","title":"Conformal Transformations for Symmetric Power Transformers","date":"2025-03-05","arxiv_id":"2503.03269","n_code_links":0,"syntology":null},{"paper":null,"slug":"da-stgcn-4d-trajectory-prediction-based-on","title":"DA-STGCN: 4D Trajectory Prediction Based on Spatiotemporal Feature Extraction","date":"2025-03-05","arxiv_id":"2503.04823","n_code_links":0,"syntology":null},{"paper":null,"slug":"deictic-codes-demonstratives-and-reference-a","title":"Deictic Codes, Demonstratives, and Reference: A Step Toward Solving the Grounding Problem","date":"2025-03-05","arxiv_id":"2503.03495","n_code_links":0,"syntology":null},{"paper":null,"slug":"dtu-net-a-multi-scale-dilated-transformer","title":"DTU-Net: A Multi-Scale Dilated Transformer Network for Nonlinear Hyperspectral Unmixing","date":"2025-03-05","arxiv_id":"2503.03465","n_code_links":0,"syntology":null},{"paper":"/paper/dualdiff-dual-branch-diffusion-for-high","slug":"dualdiff-dual-branch-diffusion-for-high","title":"DualDiff+: Dual-Branch Diffusion for High-Fidelity Video Generation with Reward Guidance","date":"2025-03-05","arxiv_id":"2503.03689","n_code_links":1,"syntology":null},{"paper":null,"slug":"intermediate-task-transfer-learning","title":"Intermediate-Task Transfer Learning: Leveraging Sarcasm Detection for Stance Detection","date":"2025-03-05","arxiv_id":"2503.03172","n_code_links":0,"syntology":null},{"paper":null,"slug":"introduction-to-artificial-consciousness","title":"Introduction to Artificial Consciousness: History, Current Trends and Ethical Challenges","date":"2025-03-05","arxiv_id":"2503.05823","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-augmentation-in-federation","title":"Knowledge Augmentation in Federation: Rethinking What Collaborative Learning Can Bring Back to Decentralized Data","date":"2025-03-05","arxiv_id":"2503.03140","n_code_links":0,"syntology":null},{"paper":null,"slug":"l2r-learning-to-reduce-search-space-for","title":"Learning to Reduce Search Space for Generalizable Neural Routing Solver","date":"2025-03-05","arxiv_id":"2503.03137","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-in-finance-estimating","title":"Large language models in finance : what is financial sentiment?","date":"2025-03-05","arxiv_id":"2503.03612","n_code_links":0,"syntology":null},{"paper":"/paper/ma-lot-multi-agent-lean-based-long-chain-of","slug":"ma-lot-multi-agent-lean-based-long-chain-of","title":"MA-LoT: Multi-Agent Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving","date":"2025-03-05","arxiv_id":"2503.03205","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-view-depth-consistent-image-generation","title":"Multi-View Depth Consistent Image Generation Using Generative AI Models: Application on Architectural Design of University Buildings","date":"2025-03-05","arxiv_id":"2503.03068","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-relation-between-speech-quality-and","title":"On the Relation Between Speech Quality and Quantized Latent Representations of Neural Codecs","date":"2025-03-05","arxiv_id":"2503.03304","n_code_links":0,"syntology":null},{"paper":null,"slug":"partial-convolution-meets-visual-attention","title":"Partial Convolution Meets Visual Attention","date":"2025-03-05","arxiv_id":"2503.03148","n_code_links":0,"syntology":null},{"paper":null,"slug":"pathrwkv-enabling-whole-slide-prediction-with","title":"PathRWKV: Enabling Whole Slide Prediction with Recurrent-Transformer","date":"2025-03-05","arxiv_id":"2503.03199","n_code_links":0,"syntology":null},{"paper":null,"slug":"personalized-federated-fine-tuning-for","title":"Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA","date":"2025-03-05","arxiv_id":"2503.03920","n_code_links":0,"syntology":null},{"paper":null,"slug":"petri-timo","title":"Petri Timo","date":"2025-03-05","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"powerattention-exponentially-scaling-of","title":"PowerAttention: Exponentially Scaling of Receptive Fields for Effective Sparse Attention","date":"2025-03-05","arxiv_id":"2503.03588","n_code_links":0,"syntology":null},{"paper":null,"slug":"pretrained-llms-as-real-time-controllers-for","title":"Pretrained LLMs as Real-Time Controllers for Robot Operated Serial Production Line","date":"2025-03-05","arxiv_id":"2503.03889","n_code_links":0,"syntology":null},{"paper":null,"slug":"qieemo-speech-is-all-you-need-in-the-emotion","title":"Qieemo: Speech Is All You Need in the Emotion Recognition in Conversations","date":"2025-03-05","arxiv_id":"2503.22687","n_code_links":0,"syntology":null},{"paper":null,"slug":"riskagent-autonomous-medical-ai-copilot-for","title":"RiskAgent: Autonomous Medical AI Copilot for Generalist Risk Prediction","date":"2025-03-05","arxiv_id":"2503.03802","n_code_links":0,"syntology":null},{"paper":null,"slug":"rtfusion-a-depth-estimation-network-based-on","title":"RGB-Thermal Infrared Fusion for Robust Depth Estimation in Complex Environments","date":"2025-03-05","arxiv_id":"2503.04821","n_code_links":0,"syntology":null},{"paper":null,"slug":"rvafm-re-parameterizing-vertical-attention","title":"RVAFM: Re-parameterizing Vertical Attention Fusion Module for Handwritten Paragraph Text Recognition","date":"2025-03-05","arxiv_id":"2503.03104","n_code_links":0,"syntology":null},{"paper":null,"slug":"sarcasm-detection-as-a-catalyst-improving","title":"Sarcasm Detection as a Catalyst: Improving Stance Detection with Cross-Target Capabilities","date":"2025-03-05","arxiv_id":"2503.03787","n_code_links":0,"syntology":null},{"paper":"/paper/scalefusionnet-transformer-guided-multi-scale","slug":"scalefusionnet-transformer-guided-multi-scale","title":"ScaleFusionNet: Transformer-Guided Multi-Scale Feature Fusion for Skin Lesion Segmentation","date":"2025-03-05","arxiv_id":"2503.03327","n_code_links":1,"syntology":null},{"paper":null,"slug":"see-what-you-are-told-visual-attention-sink","title":"See What You Are Told: Visual Attention Sink in Large Multimodal Models","date":"2025-03-05","arxiv_id":"2503.03321","n_code_links":0,"syntology":null},{"paper":"/paper/the-box-is-in-the-pen-evaluating-commonsense-1","slug":"the-box-is-in-the-pen-evaluating-commonsense-1","title":"The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation","date":"2025-03-05","arxiv_id":"2503.03308","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-signed-two-space-proximity-model-for","title":"The Signed Two-Space Proximity Model for Learning Representations in Protein-Protein Interaction Networks","date":"2025-03-05","arxiv_id":"2503.03904","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-joint-visual-compression-and-perception","title":"A Joint Visual Compression and Perception Framework for Neuralmorphic Spiking Camera","date":"2025-03-04","arxiv_id":"2503.02725","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-transformer-model-for-predicting-chemical","title":"A Transformer Model for Predicting Chemical Reaction Products from Generic Templates","date":"2025-03-04","arxiv_id":"2503.05810","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-decoder-based-language-models-for","title":"Adapting Decoder-Based Language Models for Diverse Encoder Downstream Tasks","date":"2025-03-04","arxiv_id":"2503.02656","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-bootstrapping-for-multi-modal-test","title":"Attention Bootstrapping for Multi-Modal Test-Time Adaptation","date":"2025-03-04","arxiv_id":"2503.02221","n_code_links":0,"syntology":null},{"paper":null,"slug":"bdslw401-transformer-based-word-level-bangla","title":"BdSLW401: Transformer-Based Word-Level Bangla Sign Language Recognition Using Relative Quantization Encoding (RQE)","date":"2025-03-04","arxiv_id":"2503.02360","n_code_links":0,"syntology":null},{"paper":"/paper/bhvit-binarized-hybrid-vision-transformer","slug":"bhvit-binarized-hybrid-vision-transformer","title":"BHViT: Binarized Hybrid Vision Transformer","date":"2025-03-04","arxiv_id":"2503.02394","n_code_links":1,"syntology":{"ran":16,"of":29,"n_ran_checked":15,"n_instrument":1,"unverified":13,"pointer_only":0,"phrase":"16 ran (of which 13 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 13 unverified","official":{"repos":["IMRL/BHViT"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":13,"n_ran_no_instrument_failure":15,"n_unverified":13,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"boltzmann-attention-sampling-for-image","title":"Boltzmann Attention Sampling for Image Analysis with Small Objects","date":"2025-03-04","arxiv_id":"2503.02841","n_code_links":0,"syntology":null},{"paper":"/paper/controllable-motion-generation-via-diffusion","slug":"controllable-motion-generation-via-diffusion","title":"Controllable Motion Generation via Diffusion Modal Coupling","date":"2025-03-04","arxiv_id":"2503.02353","n_code_links":1,"syntology":null},{"paper":null,"slug":"coserve-efficient-collaboration-of-experts","title":"CoServe: Efficient Collaboration-of-Experts (CoE) Model Inference with Limited Memory","date":"2025-03-04","arxiv_id":"2503.02354","n_code_links":0,"syntology":null},{"paper":null,"slug":"crystalframer-rethinking-the-role-of-frames","title":"CrystalFramer: Rethinking the Role of Frames for SE(3)-Invariant Crystal Structure Modeling","date":"2025-03-04","arxiv_id":"2503.02209","n_code_links":0,"syntology":null},{"paper":null,"slug":"developing-a-pet-ct-foundation-model-for","title":"Developing a PET/CT Foundation Model for Cross-Modal Anatomical and Functional Imaging","date":"2025-03-04","arxiv_id":"2503.02824","n_code_links":0,"syntology":null},{"paper":"/paper/disentangled-knowledge-tracing-for","slug":"disentangled-knowledge-tracing-for","title":"Disentangled Knowledge Tracing for Alleviating Cognitive Bias","date":"2025-03-04","arxiv_id":"2503.02539","n_code_links":2,"syntology":null},{"paper":null,"slug":"effectively-steer-llm-to-follow-preference","title":"Effectively Steer LLM To Follow Preference via Building Confident Directions","date":"2025-03-04","arxiv_id":"2503.02989","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-long-sequential-low-rank-adaptive","title":"LREA: Low-Rank Efficient Attention on Modeling Long-Term User Behaviors for CTR Prediction","date":"2025-03-04","arxiv_id":"2503.02542","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-token-level-augmentation-in-vision","slug":"exploring-token-level-augmentation-in-vision","title":"Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic Segmentation","date":"2025-03-04","arxiv_id":"2503.02459","n_code_links":1,"syntology":null},{"paper":null,"slug":"extrapolating-the-long-term-seasonal","title":"Extrapolating the long-term seasonal component of electricity prices for forecasting in the day-ahead market","date":"2025-03-04","arxiv_id":"2503.02518","n_code_links":0,"syntology":null},{"paper":null,"slug":"fair-play-in-the-fast-lane-integrating","title":"Fair Play in the Fast Lane: Integrating Sportsmanship into Autonomous Racing Systems","date":"2025-03-04","arxiv_id":"2503.03774","n_code_links":0,"syntology":null},{"paper":null,"slug":"fouriernat-a-fourier-mixing-based-non","title":"FourierNAT: A Fourier-Mixing-Based Non-Autoregressive Transformer for Parallel Sequence Generation","date":"2025-03-04","arxiv_id":"2503.07630","n_code_links":0,"syntology":null},{"paper":"/paper/graph-transformer-with-disease-subgraph","slug":"graph-transformer-with-disease-subgraph","title":"Graph Transformer with Disease Subgraph Positional Encoding for Improved Comorbidity Prediction","date":"2025-03-04","arxiv_id":"2503.03046","n_code_links":1,"syntology":null},{"paper":"/paper/haste-makes-waste-evaluating-planning","slug":"haste-makes-waste-evaluating-planning","title":"Haste Makes Waste: Evaluating Planning Abilities of LLMs for Efficient and Feasible Multitasking with Time Constraints Between Actions","date":"2025-03-04","arxiv_id":"2503.02238","n_code_links":1,"syntology":null},{"paper":null,"slug":"interpretable-few-shot-retinal-disease","title":"Interpretable Few-Shot Retinal Disease Diagnosis with Concept-Guided Prompting of Vision-Language Models","date":"2025-03-04","arxiv_id":"2503.02917","n_code_links":0,"syntology":null},{"paper":null,"slug":"jpds-nn-reinforcement-learning-based-dynamic","title":"JPDS-NN: Reinforcement Learning-Based Dynamic Task Allocation for Agricultural Vehicle Routing Optimization","date":"2025-03-04","arxiv_id":"2503.02369","n_code_links":0,"syntology":null},{"paper":null,"slug":"ladm-long-context-training-data-selection","title":"LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs","date":"2025-03-04","arxiv_id":"2503.02502","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-precoding-in-multi-user-multi","title":"Learning Precoding in Multi-user Multi-antenna Systems: Transformer or Graph Transformer?","date":"2025-03-04","arxiv_id":"2503.02998","n_code_links":0,"syntology":null},{"paper":null,"slug":"llave-large-language-and-vision-embedding","title":"LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning","date":"2025-03-04","arxiv_id":"2503.04812","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-misalignment-via-adversarial-rlhf","title":"LLM Misalignment via Adversarial RLHF Platforms","date":"2025-03-04","arxiv_id":"2503.03039","n_code_links":0,"syntology":null},{"paper":"/paper/multilingualism-transnationality-and-k-pop-in","slug":"multilingualism-transnationality-and-k-pop-in","title":"Multilingualism, Transnationality, and K-pop in the Online #StopAsianHate Movement","date":"2025-03-04","arxiv_id":"2503.02707","n_code_links":1,"syntology":null},{"paper":null,"slug":"network-traffic-classification-using-machine","title":"Network Traffic Classification Using Machine Learning, Transformer, and Large Language Models","date":"2025-03-04","arxiv_id":"2503.02141","n_code_links":0,"syntology":null},{"paper":null,"slug":"nodenas-node-specific-graph-neural","title":"NodeNAS: Node-Specific Graph Neural Architecture Search for Out-of-Distribution Generalization","date":"2025-03-04","arxiv_id":"2503.02448","n_code_links":0,"syntology":null},{"paper":null,"slug":"numerical-methods-for-two-dimensional-g-heat","title":"Numerical methods for two-dimensional G-heat equation","date":"2025-03-04","arxiv_id":"2503.02395","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-open-domain-question-answering","title":"Optimizing open-domain question answering with graph-based retrieval augmented generation","date":"2025-03-04","arxiv_id":"2503.02922","n_code_links":0,"syntology":null},{"paper":null,"slug":"panguir-technical-report-for-ntcir-18-aeollm","title":"PanguIR Technical Report for NTCIR-18 AEOLLM Task","date":"2025-03-04","arxiv_id":"2503.04809","n_code_links":0,"syntology":null},{"paper":null,"slug":"pennylang-pioneering-llm-based-quantum-code","title":"PennyLang: Pioneering LLM-Based Quantum Code Generation with a Novel PennyLane-Centric Dataset","date":"2025-03-04","arxiv_id":"2503.02497","n_code_links":0,"syntology":null},{"paper":"/paper/q-filters-leveraging-qk-geometry-for","slug":"q-filters-leveraging-qk-geometry-for","title":"Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression","date":"2025-03-04","arxiv_id":"2503.02812","n_code_links":1,"syntology":null},{"paper":"/paper/racnn-residual-attention-convolutional-neural","slug":"racnn-residual-attention-convolutional-neural","title":"RACNN: Residual Attention Convolutional Neural Network for Near-Field Channel Estimation in 6G Wireless Communications","date":"2025-03-04","arxiv_id":"2503.02299","n_code_links":1,"syntology":null},{"paper":"/paper/resource-efficient-affordance-grounding-with","slug":"resource-efficient-affordance-grounding-with","title":"Resource-Efficient Affordance Grounding with Complementary Depth and Semantic Prompts","date":"2025-03-04","arxiv_id":"2503.02600","n_code_links":1,"syntology":null},{"paper":"/paper/seeing-is-understanding-unlocking-causal","slug":"seeing-is-understanding-unlocking-causal","title":"Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs","date":"2025-03-04","arxiv_id":"2503.02597","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":5,"n_instrument":1,"unverified":6,"pointer_only":12,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["sony/aki"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sparse-meets-dense-unified-generative","title":"Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations","date":"2025-03-04","arxiv_id":"2503.02453","n_code_links":0,"syntology":null},{"paper":null,"slug":"staa-snn-spatial-temporal-attention","title":"STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks","date":"2025-03-04","arxiv_id":"2503.02689","n_code_links":0,"syntology":null},{"paper":null,"slug":"tabby-tabular-data-synthesis-with-language","title":"Tabby: Tabular Data Synthesis with Language Models","date":"2025-03-04","arxiv_id":"2503.02152","n_code_links":0,"syntology":null},{"paper":null,"slug":"target-return-optimizer-for-multi-game","title":"Target Return Optimizer for Multi-Game Decision Transformer","date":"2025-03-04","arxiv_id":"2503.02311","n_code_links":0,"syntology":null},{"paper":null,"slug":"tetra-vpr-a-ternary-transformer-approach-for","title":"TeTRA-VPR: A Ternary Transformer Approach for Compact Visual Place Recognition","date":"2025-03-04","arxiv_id":"2503.02511","n_code_links":0,"syntology":null},{"paper":"/paper/towards-robust-multi-uav-collaboration-marl","slug":"towards-robust-multi-uav-collaboration-marl","title":"Towards Robust Multi-UAV Collaboration: MARL with Noise-Resilient Communication and Attention Mechanisms","date":"2025-03-04","arxiv_id":"2503.02913","n_code_links":1,"syntology":null},{"paper":"/paper/union-of-experts-adapting-hierarchical","slug":"union-of-experts-adapting-hierarchical","title":"Union of Experts: Adapting Hierarchical Routing to Equivalently Decomposed Transformer","date":"2025-03-04","arxiv_id":"2503.02495","n_code_links":1,"syntology":null},{"paper":null,"slug":"use-me-wisely-ai-driven-assessment-for-llm","title":"Use Me Wisely: AI-Driven Assessment for LLM Prompting Skills Development","date":"2025-03-04","arxiv_id":"2503.02532","n_code_links":0,"syntology":null},{"paper":null,"slug":"weak-to-strong-generalization-even-in-random","title":"Weak-to-Strong Generalization Even in Random Feature Networks, Provably","date":"2025-03-04","arxiv_id":"2503.02877","n_code_links":0,"syntology":null},{"paper":"/paper/wikipedia-in-the-era-of-llms-evolution-and","slug":"wikipedia-in-the-era-of-llms-evolution-and","title":"Wikipedia in the Era of LLMs: Evolution and Risks","date":"2025-03-04","arxiv_id":"2503.02879","n_code_links":1,"syntology":null}],"record_sha256":"e51cbdf715d0916c81385bf5ceb3f4bb825e29659a91757a9a41c9215f63e808","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}