{"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/softmax/papers/39","list_of":"/method/softmax","method":"Softmax","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":39,"pages_in_order":375,"rows_per_page":100,"rows":[3801,3900],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/38","next":"/method/softmax/papers/40","papers":[{"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":null,"slug":"remote-sensing-image-classification-using-1","title":"Remote Sensing Image Classification Using Convolutional Neural Network (CNN) and Transfer Learning Techniques","date":"2025-03-04","arxiv_id":"2503.02510","n_code_links":0,"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},{"paper":"/paper/wyckoff-transformer-generation-of-symmetric","slug":"wyckoff-transformer-generation-of-symmetric","title":"Wyckoff Transformer: Generation of Symmetric Crystals","date":"2025-03-04","arxiv_id":"2503.02407","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-multi-label-classification-of","title":"Zero-Shot Multi-Label Classification of Bangla Documents: Large Decoders Vs. Classic Encoders","date":"2025-03-04","arxiv_id":"2503.02993","n_code_links":0,"syntology":null},{"paper":"/paper/2503-01306","slug":"2503-01306","title":"From Claims to Evidence: A Unified Framework and Critical Analysis of CNN vs. Transformer vs. Mamba in Medical Image Segmentation","date":"2025-03-03","arxiv_id":"2503.01306","n_code_links":1,"syntology":null},{"paper":"/paper/2503-01329","slug":"2503-01329","title":"Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning","date":"2025-03-03","arxiv_id":"2503.01329","n_code_links":0,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":null}},{"paper":null,"slug":"2503-01394","title":"Enhancing Social Media Rumor Detection: A Semantic and Graph Neural Network Approach for the 2024 Global Election","date":"2025-03-03","arxiv_id":"2503.01394","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-01453","title":"AC-Lite : A Lightweight Image Captioning Model for Low-Resource Assamese Language","date":"2025-03-03","arxiv_id":"2503.01453","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-01458","title":"SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning","date":"2025-03-03","arxiv_id":"2503.01458","n_code_links":0,"syntology":null},{"paper":"/paper/2503-01496","slug":"2503-01496","title":"Liger: Linearizing Large Language Models to Gated Recurrent Structures","date":"2025-03-03","arxiv_id":"2503.01496","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["opensparsellms/linearization"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"2503-01592","title":"An Efficient Approach to Detecting Lung Nodules Using Swin Transformer","date":"2025-03-03","arxiv_id":"2503.01592","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-01630","title":"Machine Learners Should Acknowledge the Legal Implications of Large Language Models as Personal Data","date":"2025-03-03","arxiv_id":"2503.01630","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-01713","title":"SAGE: A Framework of Precise Retrieval for RAG","date":"2025-03-03","arxiv_id":"2503.01713","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-01814","title":"LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendation","date":"2025-03-03","arxiv_id":"2503.01814","n_code_links":0,"syntology":null},{"paper":"/paper/a-generalized-theory-of-mixup-for-structure","slug":"a-generalized-theory-of-mixup-for-structure","title":"A Generalized Theory of Mixup for Structure-Preserving Synthetic Data","date":"2025-03-03","arxiv_id":"2503.02645","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-hybrid-cnn-transformer-model-for-heart","title":"A Hybrid CNN-Transformer Model for Heart Disease Prediction Using Life History Data","date":"2025-03-03","arxiv_id":"2503.02124","n_code_links":0,"syntology":null},{"paper":null,"slug":"accord-alleviating-concept-coupling-through","title":"ACCORD: Alleviating Concept Coupling through Dependence Regularization for Text-to-Image Diffusion Personalization","date":"2025-03-03","arxiv_id":"2503.01122","n_code_links":0,"syntology":null},{"paper":"/paper/architectural-and-inferential-inductive","slug":"architectural-and-inferential-inductive","title":"Architectural and Inferential Inductive Biases For Exchangeable Sequence Modeling","date":"2025-03-03","arxiv_id":"2503.01215","n_code_links":1,"syntology":null},{"paper":null,"slug":"asktoact-enhancing-llms-tool-use-via-self","title":"AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification","date":"2025-03-03","arxiv_id":"2503.01940","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-condensation-via-sparsity-induced","title":"Attention Condensation via Sparsity Induced Regularized Training","date":"2025-03-03","arxiv_id":"2503.01564","n_code_links":0,"syntology":null},{"paper":null,"slug":"boolean-aware-attention-for-dense-retrieval","title":"Boolean-aware Attention for Dense Retrieval","date":"2025-03-03","arxiv_id":"2503.01753","n_code_links":0,"syntology":null},{"paper":"/paper/cancer-type-stage-and-prognosis-assessment","slug":"cancer-type-stage-and-prognosis-assessment","title":"Cancer Type, Stage and Prognosis Assessment from Pathology Reports using LLMs","date":"2025-03-03","arxiv_id":"2503.01194","n_code_links":1,"syntology":null},{"paper":null,"slug":"dementia-insights-a-context-based-multimodal","title":"Dementia Insights: A Context-Based MultiModal Approach","date":"2025-03-03","arxiv_id":"2503.01226","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-or-powerful-trade-offs-between","title":"Efficient or Powerful? Trade-offs Between Machine Learning and Deep Learning for Mental Illness Detection on Social Media","date":"2025-03-03","arxiv_id":"2503.01082","n_code_links":0,"syntology":null},{"paper":null,"slug":"every-sam-drop-counts-embracing-semantic","title":"Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond","date":"2025-03-03","arxiv_id":"2503.01210","n_code_links":0,"syntology":null},{"paper":null,"slug":"fault-localization-and-state-estimation-of","title":"Fault Localization and State Estimation of Power Grid under Parallel Cyber-Physical Attacks","date":"2025-03-03","arxiv_id":"2503.05797","n_code_links":0,"syntology":null},{"paper":"/paper/forgetting-transformer-softmax-attention-with","slug":"forgetting-transformer-softmax-attention-with","title":"Forgetting Transformer: Softmax Attention with a Forget Gate","date":"2025-03-03","arxiv_id":"2503.02130","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":9,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhixuan-lin/forgetting-transformer"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/grain-exact-graph-reconstruction-from","slug":"grain-exact-graph-reconstruction-from","title":"GRAIN: Exact Graph Reconstruction from Gradients","date":"2025-03-03","arxiv_id":"2503.01838","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["insait-institute/grain"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"handrawer-leveraging-spatial-information-to","title":"HanDrawer: Leveraging Spatial Information to Render Realistic Hands Using a Conditional Diffusion Model in Single Stage","date":"2025-03-03","arxiv_id":"2503.02127","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-causal-transformer-with","title":"HeterRec: Heterogeneous Information Transformer for Scalable Sequential Recommendation","date":"2025-03-03","arxiv_id":"2503.01469","n_code_links":0,"syntology":null},{"paper":"/paper/hoh-a-dynamic-benchmark-for-evaluating-the","slug":"hoh-a-dynamic-benchmark-for-evaluating-the","title":"HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation","date":"2025-03-03","arxiv_id":"2503.04800","n_code_links":0,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"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":null}},{"paper":null,"slug":"hop-heterogeneous-topology-based-multimodal","title":"HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation","date":"2025-03-03","arxiv_id":"2503.01175","n_code_links":0,"syntology":null},{"paper":"/paper/how-simple-can-you-go-an-off-the-shelf","slug":"how-simple-can-you-go-an-off-the-shelf","title":"How simple can you go? An off-the-shelf transformer approach to molecular dynamics","date":"2025-03-03","arxiv_id":"2503.01431","n_code_links":1,"syntology":null},{"paper":"/paper/interactive-gadolinium-free-mri-synthesis-a","slug":"interactive-gadolinium-free-mri-synthesis-a","title":"Interactive Gadolinium-Free MRI Synthesis: A Transformer with Localization Prompt Learning","date":"2025-03-03","arxiv_id":"2503.01265","n_code_links":1,"syntology":null},{"paper":"/paper/label-ranker-self-aware-preference-for","slug":"label-ranker-self-aware-preference-for","title":"Label Ranker: Self-Aware Preference for Classification Label Position in Visual Masked Self-Supervised Pre-Trained Model","date":"2025-03-03","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/linear-representations-of-political","slug":"linear-representations-of-political","title":"Linear Representations of Political Perspective Emerge in Large Language Models","date":"2025-03-03","arxiv_id":"2503.02080","n_code_links":1,"syntology":null},{"paper":"/paper/maps-motivation-aware-personalized-search-via","slug":"maps-motivation-aware-personalized-search-via","title":"MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment","date":"2025-03-03","arxiv_id":"2503.01711","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":7,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["e-qin/maps"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"meshpad-interactive-sketch-conditioned","title":"MeshPad: Interactive Sketch-Conditioned Artist-Designed Mesh Generation and Editing","date":"2025-03-03","arxiv_id":"2503.01425","n_code_links":0,"syntology":null},{"paper":"/paper/mi-detr-an-object-detection-model-with-multi","slug":"mi-detr-an-object-detection-model-with-multi","title":"MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism","date":"2025-03-03","arxiv_id":"2503.01463","n_code_links":1,"syntology":null},{"paper":"/paper/mri-super-resolution-reconstruction-using","slug":"mri-super-resolution-reconstruction-using","title":"MRI super-resolution reconstruction using efficient diffusion probabilistic model with residual shifting","date":"2025-03-03","arxiv_id":"2503.01576","n_code_links":1,"syntology":null},{"paper":null,"slug":"object-aware-video-matting-with-cross-frame","title":"Object-Aware Video Matting with Cross-Frame Guidance","date":"2025-03-03","arxiv_id":"2503.01262","n_code_links":0,"syntology":null},{"paper":null,"slug":"open-set-recognition-of-novel-species-in","title":"Open-Set Recognition of Novel Species in Biodiversity Monitoring","date":"2025-03-03","arxiv_id":"2503.01691","n_code_links":0,"syntology":null},{"paper":null,"slug":"primer-c-vae-an-interpretable-deep-learning","title":"Primer C-VAE: An interpretable deep learning primer design method to detect emerging virus variants","date":"2025-03-03","arxiv_id":"2503.01459","n_code_links":0,"syntology":null},{"paper":null,"slug":"primus-enforcing-attention-usage-for-3d","title":"Primus: Enforcing Attention Usage for 3D Medical Image Segmentation","date":"2025-03-03","arxiv_id":"2503.01835","n_code_links":0,"syntology":null}],"record_sha256":"8ed4bdf68d4104a6c94b1585e96df47716bc7e85b4e44ded858c5f2afc9ce60d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}