{"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/multi-head-attention/papers/21","list_of":"/method/multi-head-attention","method":"Multi-Head 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":21,"pages_in_order":249,"rows_per_page":100,"rows":[2001,2100],"of":24855,"counts":{"archive_papers_tagged":24855,"with_a_code_link":11214,"where_syntology_ran_a_sample":3454,"not_listed_spam_title":0,"listed":24855,"listed_where_code_ran":3454,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2916,"every_run_a_failure_of_syntologys_instrument":538,"listed_with_a_run_with_no_instrument_failure":2916,"listed_every_run_a_failure_of_syntologys_instrument":538,"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/multi-head-attention","prev":"/method/multi-head-attention/papers/20","next":"/method/multi-head-attention/papers/22","papers":[{"paper":null,"slug":"vfx-creator-animated-visual-effect-generation","title":"VFX Creator: Animated Visual Effect Generation with Controllable Diffusion Transformer","date":"2025-02-09","arxiv_id":"2502.05979","n_code_links":0,"syntology":null},{"paper":null,"slug":"2502-05400","title":"Dynamic Noise Preference Optimization for LLM Self-Improvement via Synthetic Data","date":"2025-02-08","arxiv_id":"2502.05400","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-convolutional-free-method-for-3d","title":"A Novel Convolutional-Free Method for 3D Medical Imaging Segmentation","date":"2025-02-08","arxiv_id":"2502.05396","n_code_links":0,"syntology":null},{"paper":"/paper/ape-faster-and-longer-context-augmented","slug":"ape-faster-and-longer-context-augmented","title":"APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding","date":"2025-02-08","arxiv_id":"2502.05431","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["infini-ai-lab/ape"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/event-stream-based-visual-object-tracking","slug":"event-stream-based-visual-object-tracking","title":"Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition Benchmark","date":"2025-02-08","arxiv_id":"2502.05574","n_code_links":1,"syntology":null},{"paper":null,"slug":"flow-based-conformal-prediction-for-multi","title":"Flow-based Conformal Prediction for Multi-dimensional Time Series","date":"2025-02-08","arxiv_id":"2502.05709","n_code_links":0,"syntology":null},{"paper":null,"slug":"flowing-through-layers-a-continuous-dynamical","title":"Flowing Through Layers: A Continuous Dynamical Systems Perspective on Transformers","date":"2025-02-08","arxiv_id":"2502.05656","n_code_links":0,"syntology":null},{"paper":null,"slug":"forbidden-science-dual-use-ai-challenge","title":"Forbidden Science: Dual-Use AI Challenge Benchmark and Scientific Refusal Tests","date":"2025-02-08","arxiv_id":"2502.06867","n_code_links":0,"syntology":null},{"paper":null,"slug":"gwrf-a-generalizable-wireless-radiance-field","title":"GWRF: A Generalizable Wireless Radiance Field for Wireless Signal Propagation Modeling","date":"2025-02-08","arxiv_id":"2502.05708","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-graph-guided-retrieval-augmented","slug":"knowledge-graph-guided-retrieval-augmented","title":"Knowledge Graph-Guided Retrieval Augmented Generation","date":"2025-02-08","arxiv_id":"2502.06864","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-scale-masked-autoencoder-for","title":"Multi-scale Masked Autoencoder for Electrocardiogram Anomaly Detection","date":"2025-02-08","arxiv_id":"2502.05494","n_code_links":0,"syntology":null},{"paper":null,"slug":"nomanet-a-graph-neural-network-enabled-power","title":"NOMANet: A Graph Neural Network Enabled Power Allocation Scheme for NOMA","date":"2025-02-08","arxiv_id":"2502.05592","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-effectiveness-of-large-language-models-3","title":"On the Effectiveness of Large Language Models in Automating Categorization of Scientific Texts","date":"2025-02-08","arxiv_id":"2502.15745","n_code_links":0,"syntology":null},{"paper":"/paper/the-odyssey-of-the-fittest-can-agents-survive","slug":"the-odyssey-of-the-fittest-can-agents-survive","title":"The Odyssey of the Fittest: Can Agents Survive and Still Be Good?","date":"2025-02-08","arxiv_id":"2502.05442","n_code_links":1,"syntology":null},{"paper":null,"slug":"topological-derivative-approach-for-deep","title":"Topological derivative approach for deep neural network architecture adaptation","date":"2025-02-08","arxiv_id":"2502.06885","n_code_links":0,"syntology":null},{"paper":"/paper/towards-trustworthy-retrieval-augmented","slug":"towards-trustworthy-retrieval-augmented","title":"Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey","date":"2025-02-08","arxiv_id":"2502.06872","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-deep-learning-framework-integrating-cnn-and","title":"A Deep Learning Framework Integrating CNN and BiLSTM for Financial Systemic Risk Analysis and Prediction","date":"2025-02-07","arxiv_id":"2502.06847","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-models-understand-1","title":"Can Large Language Models Understand Intermediate Representations?","date":"2025-02-07","arxiv_id":"2502.06854","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-encoder-rediscovers-a-semantic-variant","title":"Cross-Encoder Rediscovers a Semantic Variant of BM25","date":"2025-02-07","arxiv_id":"2502.04645","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-of-llm-generated-java-code-using","title":"Detection of LLM-Generated Java Code Using Discretized Nested Bigrams","date":"2025-02-07","arxiv_id":"2502.15740","n_code_links":0,"syntology":null},{"paper":null,"slug":"eap-gp-mitigating-saturation-effect-in","title":"EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification","date":"2025-02-07","arxiv_id":"2502.06852","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-knowledge-feeding-to-language","title":"Efficient Knowledge Feeding to Language Models: A Novel Integrated Encoder-Decoder Architecture","date":"2025-02-07","arxiv_id":"2502.05233","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-pre-trained-decision-transformers","title":"Enhancing Pre-Trained Decision Transformers with Prompt-Tuning Bandits","date":"2025-02-07","arxiv_id":"2502.04979","n_code_links":0,"syntology":null},{"paper":null,"slug":"hetssnet-spatial-spectral-heterogeneous-graph","title":"HetSSNet: Spatial-Spectral Heterogeneous Graph Learning Network for Panchromatic and Multispectral Images Fusion","date":"2025-02-07","arxiv_id":"2502.04623","n_code_links":0,"syntology":null},{"paper":null,"slug":"humandit-pose-guided-diffusion-transformer","title":"HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation","date":"2025-02-07","arxiv_id":"2502.04847","n_code_links":0,"syntology":null},{"paper":null,"slug":"koel-tts-enhancing-llm-based-speech","title":"Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance","date":"2025-02-07","arxiv_id":"2502.05236","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-the-language-of-nvme-streams-for","title":"Learning the Language of NVMe Streams for Ransomware Detection","date":"2025-02-07","arxiv_id":"2502.05011","n_code_links":0,"syntology":null},{"paper":null,"slug":"medmimic-physician-inspired-multimodal-fusion","title":"MedMimic: Physician-Inspired Multimodal Fusion for Early Diagnosis of Fever of Unknown Origin","date":"2025-02-07","arxiv_id":"2502.04794","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-internal-representations-of-multi","title":"Probing Internal Representations of Multi-Word Verbs in Large Language Models","date":"2025-02-07","arxiv_id":"2502.04789","n_code_links":0,"syntology":null},{"paper":"/paper/selafd-seamless-adaptation-of-vision","slug":"selafd-seamless-adaptation-of-vision","title":"SelaFD:Seamless Adaptation of Vision Transformer Fine-tuning for Radar-based Human Activity","date":"2025-02-07","arxiv_id":"2502.04740","n_code_links":1,"syntology":null},{"paper":"/paper/swin-mstp-swin-transformer-with-multi-scale","slug":"swin-mstp-swin-transformer-with-multi-scale","title":"Swin-MSTP: Swin transformer with multi-scale temporal perception for continuous sign language recognition","date":"2025-02-07","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-classification-system-approach-in","title":"A Classification System Approach in Predicting Chinese Censorship","date":"2025-02-06","arxiv_id":"2502.04234","n_code_links":0,"syntology":null},{"paper":"/paper/a-decoding-algorithm-for-length-control","slug":"a-decoding-algorithm-for-length-control","title":"A Decoding Algorithm for Length-Control Summarization Based on Directed Acyclic Transformers","date":"2025-02-06","arxiv_id":"2502.04535","n_code_links":1,"syntology":null},{"paper":"/paper/a-retrospective-systematic-study-on","slug":"a-retrospective-systematic-study-on","title":"A Retrospective Systematic Study on Hierarchical Sparse Query Transformer-assisted Ultrasound Screening for Early Hepatocellular Carcinoma","date":"2025-02-06","arxiv_id":"2502.03772","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-self-supervised-multimodal-deep-learning","title":"A Self-supervised Multimodal Deep Learning Approach to Differentiate Post-radiotherapy Progression from Pseudoprogression in Glioblastoma","date":"2025-02-06","arxiv_id":"2502.03999","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-the-final-layer-hierarchical-query","slug":"beyond-the-final-layer-hierarchical-query","title":"Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance Segmentation","date":"2025-02-06","arxiv_id":"2502.04139","n_code_links":0,"syntology":null},{"paper":null,"slug":"building-a-unified-ai-centric-language-system","title":"Building A Unified AI-centric Language System: analysis, framework and future work","date":"2025-02-06","arxiv_id":"2502.04488","n_code_links":0,"syntology":null},{"paper":null,"slug":"ditar-diffusion-transformer-autoregressive","title":"DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation","date":"2025-02-06","arxiv_id":"2502.03930","n_code_links":0,"syntology":null},{"paper":null,"slug":"expanding-training-data-for-endoscopic","title":"Expanding Training Data for Endoscopic Phenotyping of Eosinophilic Esophagitis","date":"2025-02-06","arxiv_id":"2502.04199","n_code_links":0,"syntology":null},{"paper":null,"slug":"experiments-with-large-language-models-on","title":"Experiments with Large Language Models on Retrieval-Augmented Generation for Closed-Source Simulation Software","date":"2025-02-06","arxiv_id":"2502.03916","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-vulnerable-is-my-policy-adversarial","title":"How vulnerable is my policy? Adversarial attacks on modern behavior cloning policies","date":"2025-02-06","arxiv_id":"2502.03698","n_code_links":0,"syntology":null},{"paper":null,"slug":"icgnn-graph-neural-network-enabled-scalable","title":"ICGNN: Graph Neural Network Enabled Scalable Beamforming for MISO Interference Channels","date":"2025-02-06","arxiv_id":"2502.03936","n_code_links":0,"syntology":null},{"paper":"/paper/improvnet-generating-controllable-musical","slug":"improvnet-generating-controllable-musical","title":"ImprovNet -- Generating Controllable Musical Improvisations with Iterative Corruption Refinement","date":"2025-02-06","arxiv_id":"2502.04522","n_code_links":1,"syntology":null},{"paper":"/paper/llasa-scaling-train-time-and-inference-time","slug":"llasa-scaling-train-time-and-inference-time","title":"Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis","date":"2025-02-06","arxiv_id":"2502.04128","n_code_links":1,"syntology":null},{"paper":null,"slug":"llms-to-support-a-domain-specific-knowledge","title":"LLMs to Support a Domain Specific Knowledge Assistant","date":"2025-02-06","arxiv_id":"2502.04095","n_code_links":0,"syntology":null},{"paper":"/paper/md-bert-action-recognition-in-dark-videos-via","slug":"md-bert-action-recognition-in-dark-videos-via","title":"MD-BERT: Action Recognition in Dark Videos via Dynamic Multi-Stream Fusion and Temporal Modeling","date":"2025-02-06","arxiv_id":"2502.03724","n_code_links":1,"syntology":null},{"paper":"/paper/medgnn-towards-multi-resolution","slug":"medgnn-towards-multi-resolution","title":"MedGNN: Towards Multi-resolution Spatiotemporal Graph Learning for Medical Time Series Classification","date":"2025-02-06","arxiv_id":"2502.04515","n_code_links":1,"syntology":null},{"paper":"/paper/medrag-enhancing-retrieval-augmented","slug":"medrag-enhancing-retrieval-augmented","title":"MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot","date":"2025-02-06","arxiv_id":"2502.04413","n_code_links":1,"syntology":null},{"paper":"/paper/mramg-bench-a-beyondtext-benchmark-for","slug":"mramg-bench-a-beyondtext-benchmark-for","title":"MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation","date":"2025-02-06","arxiv_id":"2502.04176","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-non-autoregressive-machine","slug":"multilingual-non-autoregressive-machine","title":"Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation","date":"2025-02-06","arxiv_id":"2502.04537","n_code_links":1,"syntology":null},{"paper":null,"slug":"psyplay-personality-infused-role-playing","title":"PsyPlay: Personality-Infused Role-Playing Conversational Agents","date":"2025-02-06","arxiv_id":"2502.03821","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-feature-division-multiple-access-for-1","title":"Semantic Feature Division Multiple Access for Digital Semantic Broadcast Channels","date":"2025-02-06","arxiv_id":"2502.03949","n_code_links":0,"syntology":null},{"paper":"/paper/smi-an-information-theoretic-metric-for","slug":"smi-an-information-theoretic-metric-for","title":"SMI: An Information-Theoretic Metric for Predicting Model Knowledge Solely from Pre-Training Signals","date":"2025-02-06","arxiv_id":"2502.04066","n_code_links":1,"syntology":null},{"paper":null,"slug":"swiptnet-a-unified-deep-learning-framework","title":"SWIPTNet: A Unified Deep Learning Framework for SWIPT based on GNN and Transfer Learning","date":"2025-02-06","arxiv_id":"2502.03928","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-integrated-llms-for-autonomous-driving","title":"Vision-Integrated LLMs for Autonomous Driving Assistance : Human Performance Comparison and Trust Evaluation","date":"2025-02-06","arxiv_id":"2502.06843","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-meta-learning-for-tabular","title":"Zero-shot Meta-learning for Tabular Prediction Tasks with Adversarially Pre-trained Transformer","date":"2025-02-06","arxiv_id":"2502.04573","n_code_links":0,"syntology":null},{"paper":null,"slug":"cache-craft-managing-chunk-caches-for","title":"Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation","date":"2025-02-05","arxiv_id":"2502.15734","n_code_links":0,"syntology":null},{"paper":null,"slug":"every-angle-is-worth-a-second-glance-mining","title":"Every Angle Is Worth A Second Glance: Mining Kinematic Skeletal Structures from Multi-view Joint Cloud","date":"2025-02-05","arxiv_id":"2502.02936","n_code_links":0,"syntology":null},{"paper":null,"slug":"label-anything-an-interpretable-high-fidelity","title":"Label Anything: An Interpretable, High-Fidelity and Prompt-Free Annotator","date":"2025-02-05","arxiv_id":"2502.02972","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-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":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":"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":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":"/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":"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":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/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/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":"/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":"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":"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":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":"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":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":"/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":"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":"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":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/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":"/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":"/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":"/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":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":"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}],"record_sha256":"0f56d6b7ee1115067591518061163f66ab345e33015e9ca532c8ed008c6d9608","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}