{"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/50","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":50,"pages_in_order":375,"rows_per_page":100,"rows":[4901,5000],"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/49","next":"/method/softmax/papers/51","papers":[{"paper":null,"slug":"learning-to-synthesize-compatible-fashion","title":"Learning to Synthesize Compatible Fashion Items Using Semantic Alignment and Collocation Classification: An Outfit Generation Framework","date":"2025-02-05","arxiv_id":"2502.06827","n_code_links":0,"syntology":null},{"paper":null,"slug":"marage-transferable-multi-model-adversarial","title":"MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction","date":"2025-02-05","arxiv_id":"2502.04360","n_code_links":0,"syntology":null},{"paper":null,"slug":"maximizing-the-position-embedding-for-vision","title":"Maximizing the Position Embedding for Vision Transformers with Global Average Pooling","date":"2025-02-05","arxiv_id":"2502.02919","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-brain-computer-interfaces-ai","title":"Multimodal Brain-Computer Interfaces: AI-powered Decoding Methodologies","date":"2025-02-05","arxiv_id":"2502.02830","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-transformer-models-for-turn-taking","title":"Multimodal Transformer Models for Turn-taking Prediction: Effects on Conversational Dynamics of Human-Agent Interaction during Cooperative Gameplay","date":"2025-02-05","arxiv_id":"2503.16432","n_code_links":0,"syntology":null},{"paper":null,"slug":"omni-dna-a-unified-genomic-foundation-model","title":"Omni-DNA: A Unified Genomic Foundation Model for Cross-Modal and Multi-Task Learning","date":"2025-02-05","arxiv_id":"2502.03499","n_code_links":0,"syntology":null},{"paper":"/paper/on-device-sora-enabling-diffusion-based-text","slug":"on-device-sora-enabling-diffusion-based-text","title":"On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices","date":"2025-02-05","arxiv_id":"2502.04363","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-zero-initialized-attention-optimal-prompt","title":"On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation","date":"2025-02-05","arxiv_id":"2502.03029","n_code_links":0,"syntology":null},{"paper":null,"slug":"optic-optimizing-patient-provider-triaging","title":"OPTIC: Optimizing Patient-Provider Triaging & Improving Communications in Clinical Operations using GPT-4 Data Labeling and Model Distillation","date":"2025-02-05","arxiv_id":"2503.05701","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-robustness-and-accuracy-in-mixture","title":"Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach","date":"2025-02-05","arxiv_id":"2502.06832","n_code_links":0,"syntology":null},{"paper":null,"slug":"path-planning-for-masked-diffusion-model","title":"Path Planning for Masked Diffusion Model Sampling","date":"2025-02-05","arxiv_id":"2502.03540","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-laws-in-wearable-human-activity","title":"Scaling laws in wearable human activity recognition","date":"2025-02-05","arxiv_id":"2502.03364","n_code_links":0,"syntology":null},{"paper":null,"slug":"single-antenna-terahertz-sensing-using","title":"Single Antenna Terahertz Sensing using Preconfigured Metasurfaces","date":"2025-02-05","arxiv_id":"2502.03291","n_code_links":0,"syntology":null},{"paper":"/paper/spacegnn-multi-space-graph-neural-network-for","slug":"spacegnn-multi-space-graph-neural-network-for","title":"SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labels","date":"2025-02-05","arxiv_id":"2502.03201","n_code_links":1,"syntology":null},{"paper":null,"slug":"structured-token-retention-and-computational","title":"Structured Token Retention and Computational Memory Paths in Large Language Models","date":"2025-02-05","arxiv_id":"2502.03102","n_code_links":0,"syntology":null},{"paper":null,"slug":"truepose-human-parsing-guided-attention","title":"TruePose: Human-Parsing-guided Attention Diffusion for Full-ID Preserving Pose Transfer","date":"2025-02-05","arxiv_id":"2502.03426","n_code_links":0,"syntology":null},{"paper":null,"slug":"type-2-tobit-sample-selection-models-with","title":"Type 2 Tobit Sample Selection Models with Bayesian Additive Regression Trees","date":"2025-02-05","arxiv_id":"2502.03600","n_code_links":0,"syntology":null},{"paper":null,"slug":"zisvfm-zero-shot-object-instance-segmentation","title":"ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments with Vision Foundation Models","date":"2025-02-05","arxiv_id":"2502.03266","n_code_links":0,"syntology":null},{"paper":"/paper/a-training-free-length-extrapolation-approach","slug":"a-training-free-length-extrapolation-approach","title":"A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)","date":"2025-02-04","arxiv_id":"2502.02659","n_code_links":1,"syntology":null},{"paper":"/paper/aad-dce-an-aggregated-multimodal-attention","slug":"aad-dce-an-aggregated-multimodal-attention","title":"AAD-DCE: An Aggregated Multimodal Attention Mechanism for Early and Late Dynamic Contrast Enhanced Prostate MRI Synthesis","date":"2025-02-04","arxiv_id":"2502.02555","n_code_links":1,"syntology":null},{"paper":"/paper/adaptive-voxel-weighted-loss-using-l1-norms","slug":"adaptive-voxel-weighted-loss-using-l1-norms","title":"Adaptive Voxel-Weighted Loss Using L1 Norms in Deep Neural Networks for Detection and Segmentation of Prostate Cancer Lesions in PET/CT Images","date":"2025-02-04","arxiv_id":"2502.02756","n_code_links":1,"syntology":null},{"paper":null,"slug":"aligning-human-and-machine-attention-for","title":"Aligning Human and Machine Attention for Enhanced Supervised Learning","date":"2025-02-04","arxiv_id":"2502.06811","n_code_links":0,"syntology":null},{"paper":null,"slug":"astromer-2","title":"Astromer 2","date":"2025-02-04","arxiv_id":"2502.02717","n_code_links":0,"syntology":null},{"paper":null,"slug":"autogui-scaling-gui-grounding-with-automatic","title":"AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs","date":"2025-02-04","arxiv_id":"2502.01977","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-maintain-fundamental-abilities-under","title":"Can LLMs Maintain Fundamental Abilities under KV Cache Compression?","date":"2025-02-04","arxiv_id":"2502.01941","n_code_links":0,"syntology":null},{"paper":null,"slug":"coat-chain-of-associated-thoughts-framework","title":"CoAT: Chain-of-Associated-Thoughts Framework for Enhancing Large Language Models Reasoning","date":"2025-02-04","arxiv_id":"2502.02390","n_code_links":0,"syntology":null},{"paper":"/paper/codesteer-symbolic-augmented-language-models","slug":"codesteer-symbolic-augmented-language-models","title":"CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance","date":"2025-02-04","arxiv_id":"2502.04350","n_code_links":1,"syntology":null},{"paper":null,"slug":"constrained-belief-updates-explain-geometric","title":"Constrained belief updates explain geometric structures in transformer representations","date":"2025-02-04","arxiv_id":"2502.01954","n_code_links":0,"syntology":null},{"paper":null,"slug":"contextual-memory-reweaving-in-large-language","title":"Contextual Memory Reweaving in Large Language Models Using Layered Latent State Reconstruction","date":"2025-02-04","arxiv_id":"2502.02046","n_code_links":0,"syntology":null},{"paper":null,"slug":"conversation-ai-dialog-for-medicare-powered","title":"Conversation AI Dialog for Medicare powered by Finetuning and Retrieval Augmented Generation","date":"2025-02-04","arxiv_id":"2502.02249","n_code_links":0,"syntology":null},{"paper":"/paper/diff9d-diffusion-based-domain-generalized","slug":"diff9d-diffusion-based-domain-generalized","title":"Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation","date":"2025-02-04","arxiv_id":"2502.02525","n_code_links":1,"syntology":null},{"paper":null,"slug":"diffusion-instruction-tuning","title":"Diffusion Instruction Tuning","date":"2025-02-04","arxiv_id":"2502.06814","n_code_links":0,"syntology":null},{"paper":null,"slug":"distribution-transformers-fast-approximate","title":"Distribution Transformers: Fast Approximate Bayesian Inference With On-The-Fly Prior Adaptation","date":"2025-02-04","arxiv_id":"2502.02463","n_code_links":0,"syntology":null},{"paper":"/paper/dual-ensembled-multiagent-q-learning-with","slug":"dual-ensembled-multiagent-q-learning-with","title":"Dual Ensembled Multiagent Q-Learning with Hypernet Regularizer","date":"2025-02-04","arxiv_id":"2502.02018","n_code_links":1,"syntology":null},{"paper":"/paper/dual-flow-transferable-multi-target-instance","slug":"dual-flow-transferable-multi-target-instance","title":"Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimization","date":"2025-02-04","arxiv_id":"2502.02096","n_code_links":0,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":null}},{"paper":null,"slug":"edgegfl-rethinking-edge-information-in-graph","title":"EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning","date":"2025-02-04","arxiv_id":"2502.02302","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-effectiveness-of-llms-in-1","title":"Evaluating the Effectiveness of LLMs in Fixing Maintainability Issues in Real-World Projects","date":"2025-02-04","arxiv_id":"2502.02368","n_code_links":0,"syntology":null},{"paper":null,"slug":"exact-sequence-classification-with-hardmax","title":"Exact Sequence Classification with Hardmax Transformers","date":"2025-02-04","arxiv_id":"2502.02270","n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-ensemble-learning-for-cross-view","slug":"exploiting-ensemble-learning-for-cross-view","title":"Exploiting Ensemble Learning for Cross-View Isolated Sign Language Recognition","date":"2025-02-04","arxiv_id":"2502.02196","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-panorama-of-anxiety-levels-a","title":"Exploring the Panorama of Anxiety Levels: A Multi-Scenario Study Based on Human-Centric Anxiety Level Detection and Personalized Guidance","date":"2025-02-04","arxiv_id":"2503.15527","n_code_links":0,"syntology":null},{"paper":"/paper/fewtopner-integrating-few-shot-learning-with","slug":"fewtopner-integrating-few-shot-learning-with","title":"FewTopNER: Integrating Few-Shot Learning with Topic Modeling and Named Entity Recognition in a Multilingual Framework","date":"2025-02-04","arxiv_id":"2502.02391","n_code_links":1,"syntology":null},{"paper":null,"slug":"imdprompter-adapting-sam-to-image","title":"IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt Learning","date":"2025-02-04","arxiv_id":"2502.02454","n_code_links":0,"syntology":null},{"paper":"/paper/incepformernet-a-multi-scale-multi-head","slug":"incepformernet-a-multi-scale-multi-head","title":"IncepFormerNet: A multi-scale multi-head attention network for SSVEP classification","date":"2025-02-04","arxiv_id":"2502.13972","n_code_links":1,"syntology":null},{"paper":"/paper/llmer-crafting-interactive-extended-reality","slug":"llmer-crafting-interactive-extended-reality","title":"LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models","date":"2025-02-04","arxiv_id":"2502.02441","n_code_links":1,"syntology":null},{"paper":null,"slug":"lv-xattn-distributed-cross-attention-for-long","title":"LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models","date":"2025-02-04","arxiv_id":"2502.02406","n_code_links":0,"syntology":null},{"paper":"/paper/mass-editing-memory-with-attention-in","slug":"mass-editing-memory-with-attention-in","title":"Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge","date":"2025-02-04","arxiv_id":"2502.02173","n_code_links":1,"syntology":null},{"paper":"/paper/matcnn-infrared-and-visible-image-fusion","slug":"matcnn-infrared-and-visible-image-fusion","title":"MATCNN: Infrared and Visible Image Fusion Method Based on Multi-scale CNN with Attention Transformer","date":"2025-02-04","arxiv_id":"2502.01959","n_code_links":1,"syntology":null},{"paper":null,"slug":"memory-efficient-transformer-adapter-for","title":"Memory Efficient Transformer Adapter for Dense Predictions","date":"2025-02-04","arxiv_id":"2502.01962","n_code_links":0,"syntology":null},{"paper":"/paper/mind-the-gap-evaluating-patch-embeddings-from","slug":"mind-the-gap-evaluating-patch-embeddings-from","title":"Mind the Gap: Evaluating Patch Embeddings from General-Purpose and Histopathology Foundation Models for Cell Segmentation and Classification","date":"2025-02-04","arxiv_id":"2502.02471","n_code_links":1,"syntology":null},{"paper":null,"slug":"mitigating-object-hallucinations-in-large-1","title":"Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration","date":"2025-02-04","arxiv_id":"2502.01969","n_code_links":0,"syntology":null},{"paper":null,"slug":"motionlab-unified-human-motion-generation-and","title":"MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm","date":"2025-02-04","arxiv_id":"2502.02358","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-emergence-of-position-bias-in","title":"On the Emergence of Position Bias in Transformers","date":"2025-02-04","arxiv_id":"2502.01951","n_code_links":0,"syntology":null},{"paper":"/paper/one-diffusion-step-to-real-world-super","slug":"one-diffusion-step-to-real-world-super","title":"One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation","date":"2025-02-04","arxiv_id":"2502.01993","n_code_links":1,"syntology":null},{"paper":null,"slug":"open-foundation-models-in-healthcare","title":"Open Foundation Models in Healthcare: Challenges, Paradoxes, and Opportunities with GenAI Driven Personalized Prescription","date":"2025-02-04","arxiv_id":"2502.04356","n_code_links":0,"syntology":null},{"paper":"/paper/overthinking-slowdown-attacks-on-reasoning","slug":"overthinking-slowdown-attacks-on-reasoning","title":"OverThink: Slowdown Attacks on Reasoning LLMs","date":"2025-02-04","arxiv_id":"2502.02542","n_code_links":1,"syntology":null},{"paper":"/paper/pandas-improving-many-shot-jailbreaking-via","slug":"pandas-improving-many-shot-jailbreaking-via","title":"PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling","date":"2025-02-04","arxiv_id":"2502.01925","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["averyma/pandas"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"peri-ln-revisiting-layer-normalization-in-the","title":"Peri-LN: Revisiting Layer Normalization in the Transformer Architecture","date":"2025-02-04","arxiv_id":"2502.02732","n_code_links":0,"syntology":null},{"paper":"/paper/rankify-a-comprehensive-python-toolkit-for","slug":"rankify-a-comprehensive-python-toolkit-for","title":"Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation","date":"2025-02-04","arxiv_id":"2502.02464","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-homogeneity-of-vision-and-text","title":"Rethinking Homogeneity of Vision and Text Tokens in Large Vision-and-Language Models","date":"2025-02-04","arxiv_id":"2502.01906","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-and-secure-code-watermarking-for-large","title":"Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesign","date":"2025-02-04","arxiv_id":"2502.02068","n_code_links":0,"syntology":null},{"paper":"/paper/saisa-towards-multimodal-large-language","slug":"saisa-towards-multimodal-large-language","title":"SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency","date":"2025-02-04","arxiv_id":"2502.02458","n_code_links":1,"syntology":null},{"paper":"/paper/simbev-a-synthetic-multi-task-multi-sensor","slug":"simbev-a-synthetic-multi-task-multi-sensor","title":"SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and Dataset","date":"2025-02-04","arxiv_id":"2502.01894","n_code_links":1,"syntology":null},{"paper":null,"slug":"spatial-rag-spatial-retrieval-augmented","title":"Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions","date":"2025-02-04","arxiv_id":"2502.18470","n_code_links":0,"syntology":null},{"paper":null,"slug":"spatio-temporal-transformer-to-support","title":"Spatio-temporal transformer to support automatic sign language translation","date":"2025-02-04","arxiv_id":"2502.02587","n_code_links":0,"syntology":null},{"paper":null,"slug":"stable-port-hamiltonian-neural-networks","title":"Stable Port-Hamiltonian Neural Networks","date":"2025-02-04","arxiv_id":"2502.02480","n_code_links":0,"syntology":null},{"paper":"/paper/the-skin-game-revolutionizing-standards-for","slug":"the-skin-game-revolutionizing-standards-for","title":"The Skin Game: Revolutionizing Standards for AI Dermatology Model Comparison","date":"2025-02-04","arxiv_id":"2502.02500","n_code_links":1,"syntology":null},{"paper":null,"slug":"topic-modeling-in-marathi","title":"Topic Modeling in Marathi","date":"2025-02-04","arxiv_id":"2502.02100","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-risk-map-mitigating-pixel-level","title":"Transfer Risk Map: Mitigating Pixel-level Negative Transfer in Medical Segmentation","date":"2025-02-04","arxiv_id":"2502.02340","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformdas-mapping-ph-otdr-signals-to","title":"RIE-SenseNet: Riemannian Manifold Embedding of Multi-Source Industrial Sensor Signals for Robust Pattern Recognition","date":"2025-02-04","arxiv_id":"2502.02428","n_code_links":0,"syntology":null},{"paper":null,"slug":"twilight-adaptive-attention-sparsity-with","title":"Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning","date":"2025-02-04","arxiv_id":"2502.02770","n_code_links":0,"syntology":null},{"paper":null,"slug":"unigaze-towards-universal-gaze-estimation-via","title":"UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training","date":"2025-02-04","arxiv_id":"2502.02307","n_code_links":0,"syntology":null},{"paper":"/paper/unip-rethinking-pre-trained-attention","slug":"unip-rethinking-pre-trained-attention","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","date":"2025-02-04","arxiv_id":"2502.02257","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["casiatao/unip"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/vertenet-a-multi-context-hybrid-cnn","slug":"vertenet-a-multi-context-hybrid-cnn","title":"VerteNet -- A Multi-Context Hybrid CNN Transformer for Accurate Vertebral Landmark Localization in Lateral Spine DXA Images","date":"2025-02-04","arxiv_id":"2502.02097","n_code_links":1,"syntology":null},{"paper":null,"slug":"wavelet-based-positional-representation-for","title":"Wavelet-based Positional Representation for Long Context","date":"2025-02-04","arxiv_id":"2502.02004","n_code_links":0,"syntology":null},{"paper":null,"slug":"bare-combining-base-and-instruction-tuned","title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation","date":"2025-02-03","arxiv_id":"2502.01697","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-message-passing-gnn-approximate","title":"Message-Passing GNNs Fail to Approximate Sparse Triangular Factorizations","date":"2025-02-03","arxiv_id":"2502.01397","n_code_links":0,"syntology":null},{"paper":"/paper/cove-context-and-veracity-prediction-for-out","slug":"cove-context-and-veracity-prediction-for-out","title":"COVE: COntext and VEracity prediction for out-of-context images","date":"2025-02-03","arxiv_id":"2502.01194","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ukplab/naacl2025-cove"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"docking-aware-attention-dynamic-protein","title":"Docking-Aware Attention: Dynamic Protein Representations through Molecular Context Integration","date":"2025-02-03","arxiv_id":"2502.01461","n_code_links":0,"syntology":null},{"paper":"/paper/explaining-context-length-scaling-and-bounds","slug":"explaining-context-length-scaling-and-bounds","title":"Explaining Context Length Scaling and Bounds for Language Models","date":"2025-02-03","arxiv_id":"2502.01481","n_code_links":1,"syntology":null},{"paper":"/paper/fastkv-kv-cache-compression-for-fast-long","slug":"fastkv-kv-cache-compression-for-fast-long","title":"FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation","date":"2025-02-03","arxiv_id":"2502.01068","n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-discrete-diffusion-models-with","slug":"fine-tuning-discrete-diffusion-models-with","title":"Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods","date":"2025-02-03","arxiv_id":"2502.01384","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":6,"phrase":"7 ran (of which 0 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) · 1 unverified","official":{"repos":["ozekri/SEPO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gaucho-gaussian-distributions-with-cholesky","title":"GauCho: Gaussian Distributions with Cholesky Decomposition for Oriented Object Detection","date":"2025-02-03","arxiv_id":"2502.01565","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-multi-image-synthetic-data-for","title":"Generating Multi-Image Synthetic Data for Text-to-Image Customization","date":"2025-02-03","arxiv_id":"2502.01720","n_code_links":0,"syntology":null},{"paper":"/paper/gfm-rag-graph-foundation-model-for-retrieval","slug":"gfm-rag-graph-foundation-model-for-retrieval","title":"GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation","date":"2025-02-03","arxiv_id":"2502.01113","n_code_links":1,"syntology":{"ran":3,"of":12,"n_ran_checked":1,"n_instrument":2,"unverified":9,"pointer_only":2,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified","official":{"repos":["RManLuo/gfm-rag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":9,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/gnn-dt-graph-neural-network-enhanced-decision","slug":"gnn-dt-graph-neural-network-enhanced-decision","title":"GNN-DT: Graph Neural Network Enhanced Decision Transformer for Efficient Optimization in Dynamic Environments","date":"2025-02-03","arxiv_id":"2502.01778","n_code_links":1,"syntology":null},{"paper":null,"slug":"hamming-attention-distillation-binarizing","title":"Hamming Attention Distillation: Binarizing Keys and Queries for Efficient Long-Context Transformers","date":"2025-02-03","arxiv_id":"2502.01770","n_code_links":0,"syntology":null},{"paper":"/paper/harmonic-loss-trains-interpretable-ai-models","slug":"harmonic-loss-trains-interpretable-ai-models","title":"Harmonic Loss Trains Interpretable AI Models","date":"2025-02-03","arxiv_id":"2502.01628","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-machine-learning-model-for-detecting","title":"Hybrid Machine Learning Model for Detecting Bangla Smishing Text Using BERT and Character-Level CNN","date":"2025-02-03","arxiv_id":"2502.01518","n_code_links":0,"syntology":null},{"paper":"/paper/joint-localization-and-activation-editing-for","slug":"joint-localization-and-activation-editing-for","title":"Joint Localization and Activation Editing for Low-Resource Fine-Tuning","date":"2025-02-03","arxiv_id":"2502.01179","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowing-when-to-stop-dynamic-context-cutoff","title":"Knowing When to Stop: Dynamic Context Cutoff for Large Language Models","date":"2025-02-03","arxiv_id":"2502.01025","n_code_links":0,"syntology":null},{"paper":"/paper/learnable-polynomial-trigonometric-and","slug":"learnable-polynomial-trigonometric-and","title":"Polynomial, trigonometric, and tropical activations","date":"2025-02-03","arxiv_id":"2502.01247","n_code_links":1,"syntology":null},{"paper":"/paper/massive-values-in-self-attention-modules-are","slug":"massive-values-in-self-attention-modules-are","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","date":"2025-02-03","arxiv_id":"2502.01563","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mingyuj666/rope_with_llm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"meursault-as-a-data-point","title":"Meursault as a Data Point","date":"2025-02-03","arxiv_id":"2502.01364","n_code_links":0,"syntology":null},{"paper":null,"slug":"molecular-odor-prediction-based-on-multi","title":"Molecular Odor Prediction Based on Multi-Feature Graph Attention Networks","date":"2025-02-03","arxiv_id":"2502.01430","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-inverse-attention-network-with","title":"Multimodal Inverse Attention Network with Intrinsic Discriminant Feature Exploitation for Fake News Detection","date":"2025-02-03","arxiv_id":"2502.01699","n_code_links":0,"syntology":null},{"paper":"/paper/partial-channel-network-compute-fewer-perform","slug":"partial-channel-network-compute-fewer-perform","title":"Partial Channel Network: Compute Fewer, Perform Better","date":"2025-02-03","arxiv_id":"2502.01303","n_code_links":1,"syntology":null},{"paper":"/paper/preference-leakage-a-contamination-problem-in","slug":"preference-leakage-a-contamination-problem-in","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","date":"2025-02-03","arxiv_id":"2502.01534","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["david-li0406/preference-leakage"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"scalable-language-models-with-posterior","title":"Scalable Language Models with Posterior Inference of Latent Thought Vectors","date":"2025-02-03","arxiv_id":"2502.01567","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-videogen-accelerating-video-diffusion","title":"Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity","date":"2025-02-03","arxiv_id":"2502.01776","n_code_links":0,"syntology":null},{"paper":null,"slug":"spffnet-strip-perception-and-feature-fusion","title":"SPFFNet: Strip Perception and Feature Fusion Spatial Pyramid Pooling for Fabric Defect Detection","date":"2025-02-03","arxiv_id":"2502.01445","n_code_links":0,"syntology":null}],"record_sha256":"bae10600925a1d970b05df7022bbbdf3a6383e1aac6e2b8c58c64645ab3a594b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}