{"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/10","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":10,"pages_in_order":249,"rows_per_page":100,"rows":[901,1000],"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/9","next":"/method/multi-head-attention/papers/11","papers":[{"paper":null,"slug":"vdocrag-retrieval-augmented-generation-over","title":"VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents","date":"2025-04-14","arxiv_id":"2504.09795","n_code_links":0,"syntology":null},{"paper":"/paper/xy-cut-advanced-layout-ordering-via","slug":"xy-cut-advanced-layout-ordering-via","title":"XY-Cut++: Advanced Layout Ordering via Hierarchical Mask Mechanism on a Novel Benchmark","date":"2025-04-14","arxiv_id":"2504.10258","n_code_links":1,"syntology":null},{"paper":"/paper/clinicalgpt-r1-pushing-reasoning-capability","slug":"clinicalgpt-r1-pushing-reasoning-capability","title":"ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model","date":"2025-04-13","arxiv_id":"2504.09421","n_code_links":1,"syntology":null},{"paper":null,"slug":"controlnet-a-firewall-for-rag-based-llm","title":"ControlNET: A Firewall for RAG-based LLM System","date":"2025-04-13","arxiv_id":"2504.09593","n_code_links":0,"syntology":null},{"paper":null,"slug":"ditse-high-fidelity-generative-speech","title":"DiTSE: High-Fidelity Generative Speech Enhancement via Latent Diffusion Transformers","date":"2025-04-13","arxiv_id":"2504.09381","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-filterless-multi-color-vlc-via-qct","title":"Enhanced Filterless Multi-Color VLC via QCT","date":"2025-04-13","arxiv_id":"2504.09743","n_code_links":0,"syntology":null},{"paper":null,"slug":"ensemble-enhanced-graph-autoencoder-with-gat","title":"Ensemble-Enhanced Graph Autoencoder with GAT and Transformer-Based Encoders for Robust Fault Diagnosis","date":"2025-04-13","arxiv_id":"2504.09427","n_code_links":0,"syntology":null},{"paper":null,"slug":"hd-rag-retrieval-augmented-generation-for","title":"HD-RAG: Retrieval-Augmented Generation for Hybrid Documents Containing Text and Hierarchical Tables","date":"2025-04-13","arxiv_id":"2504.09554","n_code_links":0,"syntology":null},{"paper":"/paper/hm-rag-hierarchical-multi-agent-multimodal","slug":"hm-rag-hierarchical-multi-agent-multimodal","title":"HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation","date":"2025-04-13","arxiv_id":"2504.12330","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrating-large-language-models-for-1","title":"Integrating Large Language Models for Automated Structural Analysis","date":"2025-04-13","arxiv_id":"2504.09754","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-self-training-for-code-generation","title":"Iterative Self-Training for Code Generation via Reinforced Re-Ranking","date":"2025-04-13","arxiv_id":"2504.09643","n_code_links":0,"syntology":null},{"paper":"/paper/trajectory-guided-motion-perception-for","slug":"trajectory-guided-motion-perception-for","title":"Trajectory-guided Motion Perception for Facial Expression Quality Assessment in Neurological Disorders","date":"2025-04-13","arxiv_id":"2504.09530","n_code_links":1,"syntology":null},{"paper":null,"slug":"accurate-diagnosis-of-respiratory-viruses","title":"Accurate Diagnosis of Respiratory Viruses Using an Explainable Machine Learning with Mid-Infrared Biomolecular Fingerprinting of Nasopharyngeal Secretions","date":"2025-04-12","arxiv_id":"2504.09211","n_code_links":0,"syntology":null},{"paper":null,"slug":"amnet-an-acoustic-model-network-for-enhanced","title":"AMNet: An Acoustic Model Network for Enhanced Mandarin Speech Synthesis","date":"2025-04-12","arxiv_id":"2504.09225","n_code_links":0,"syntology":null},{"paper":null,"slug":"heterag-a-heterogeneous-retrieval-augmented","title":"HeteRAG: A Heterogeneous Retrieval-augmented Generation Framework with Decoupled Knowledge Representations","date":"2025-04-12","arxiv_id":"2504.10529","n_code_links":0,"syntology":null},{"paper":"/paper/learning-occlusion-robust-vision-transformers-1","slug":"learning-occlusion-robust-vision-transformers-1","title":"Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking","date":"2025-04-12","arxiv_id":"2504.09228","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["wuyou3474/ortrack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lumos-efficient-performance-modeling-and","title":"Lumos: Efficient Performance Modeling and Estimation for Large-scale LLM Training","date":"2025-04-12","arxiv_id":"2504.09307","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-modal-brain-tumor-segmentation-via-3d","title":"Multi-Modal Brain Tumor Segmentation via 3D Multi-Scale Self-attention and Cross-attention","date":"2025-04-12","arxiv_id":"2504.09088","n_code_links":0,"syntology":null},{"paper":"/paper/multi-scale-activation-refinement-and-1","slug":"multi-scale-activation-refinement-and-1","title":"Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition","date":"2025-04-12","arxiv_id":"2504.09215","n_code_links":0,"syntology":null},{"paper":"/paper/nettag-a-multimodal-rtl-and-layout-aligned","slug":"nettag-a-multimodal-rtl-and-layout-aligned","title":"NetTAG: A Multimodal RTL-and-Layout-Aligned Netlist Foundation Model via Text-Attributed Graph","date":"2025-04-12","arxiv_id":"2504.09260","n_code_links":1,"syntology":null},{"paper":"/paper/pneuma-leveraging-llms-for-tabular-data","slug":"pneuma-leveraging-llms-for-tabular-data","title":"Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System","date":"2025-04-12","arxiv_id":"2504.09207","n_code_links":1,"syntology":null},{"paper":null,"slug":"semantic-commit-helping-users-update-intent","title":"Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale","date":"2025-04-12","arxiv_id":"2504.09283","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-additive-parameter-updates-of-vision","title":"Adaptive Additive Parameter Updates of Vision Transformers for Few-Shot Continual Learning","date":"2025-04-11","arxiv_id":"2504.08982","n_code_links":0,"syntology":null},{"paper":null,"slug":"adopting-large-language-models-to-automated","title":"Adopting Large Language Models to Automated System Integration","date":"2025-04-11","arxiv_id":"2504.08490","n_code_links":0,"syntology":null},{"paper":null,"slug":"dreamfuse-adaptive-image-fusion-with","title":"DreamFuse: Adaptive Image Fusion with Diffusion Transformer","date":"2025-04-11","arxiv_id":"2504.08291","n_code_links":0,"syntology":null},{"paper":null,"slug":"drivaer-transformer-a-high-precision-and-fast","title":"DrivAer Transformer: A high-precision and fast prediction method for vehicle aerodynamic drag coefficient based on the DrivAerNet++ dataset","date":"2025-04-11","arxiv_id":"2504.08217","n_code_links":0,"syntology":null},{"paper":null,"slug":"examining-gpt-s-capability-to-generate-and","title":"Examining GPT's Capability to Generate and Map Course Concepts and Their Relationship","date":"2025-04-11","arxiv_id":"2504.08856","n_code_links":0,"syntology":null},{"paper":"/paper/hypercore-the-core-framework-for-building","slug":"hypercore-the-core-framework-for-building","title":"HyperCore: The Core Framework for Building Hyperbolic Foundation Models with Comprehensive Modules","date":"2025-04-11","arxiv_id":"2504.08912","n_code_links":1,"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":["graph-and-geometric-learning/hypercore"],"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":"hypergraph-vision-transformers-images-are","title":"Hypergraph Vision Transformers: Images are More than Nodes, More than Edges","date":"2025-04-11","arxiv_id":"2504.08710","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrated-ensemble-of-bert-and-features","title":"Integrated ensemble of BERT- and features-based models for authorship attribution in Japanese literary works","date":"2025-04-11","arxiv_id":"2504.08527","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-from-elders-making-an-llm-powered","title":"Learning from Elders: Making an LLM-powered Chatbot for Retirement Communities more Accessible through User-centered Design","date":"2025-04-11","arxiv_id":"2504.08985","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-for-comparative-narrative-analysis","title":"LLM for Comparative Narrative Analysis","date":"2025-04-11","arxiv_id":"2504.08211","n_code_links":0,"syntology":null},{"paper":null,"slug":"llmtaxo-leveraging-large-language-models-for","title":"LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Media","date":"2025-04-11","arxiv_id":"2504.12325","n_code_links":0,"syntology":null},{"paper":null,"slug":"millions-of-states-designing-a-scalable-moe","title":"Millions of States: Designing a Scalable MoE Architecture with RWKV-7 Meta-learner","date":"2025-04-11","arxiv_id":"2504.08247","n_code_links":0,"syntology":null},{"paper":null,"slug":"mineworld-a-real-time-and-open-source","title":"MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft","date":"2025-04-11","arxiv_id":"2504.08388","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixdit-accelerating-image-diffusion","title":"MixDiT: Accelerating Image Diffusion Transformer Inference with Mixed-Precision MX Quantization","date":"2025-04-11","arxiv_id":"2504.08398","n_code_links":0,"syntology":null},{"paper":null,"slug":"modernbert-or-debertav3-examining","title":"ModernBERT or DeBERTaV3? Examining Architecture and Data Influence on Transformer Encoder Models Performance","date":"2025-04-11","arxiv_id":"2504.08716","n_code_links":0,"syntology":null},{"paper":"/paper/out-of-style-rag-s-fragility-to-linguistic","slug":"out-of-style-rag-s-fragility-to-linguistic","title":"Out of Style: RAG's Fragility to Linguistic Variation","date":"2025-04-11","arxiv_id":"2504.08231","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":11,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["springcty/rag-fragility-to-linguistic-variation"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pca-rag-principal-component-analysis-for","title":"PCA-RAG: Principal Component Analysis for Efficient Retrieval-Augmented Generation","date":"2025-04-11","arxiv_id":"2504.08386","n_code_links":0,"syntology":null},{"paper":null,"slug":"rtlrepocoder-repository-level-rtl-code","title":"RTLRepoCoder: Repository-Level RTL Code Completion through the Combination of Fine-Tuning and Retrieval Augmentation","date":"2025-04-11","arxiv_id":"2504.08862","n_code_links":0,"syntology":null},{"paper":null,"slug":"sarformer-an-acquisition-parameter-aware","title":"SARFormer -- An Acquisition Parameter Aware Vision Transformer for Synthetic Aperture Radar Data","date":"2025-04-11","arxiv_id":"2504.08441","n_code_links":0,"syntology":null},{"paper":null,"slug":"steering-clip-s-vision-transformer-with","title":"Steering CLIP's vision transformer with sparse autoencoders","date":"2025-04-11","arxiv_id":"2504.08729","n_code_links":0,"syntology":null},{"paper":null,"slug":"swan-gpt-an-efficient-and-scalable-approach","title":"SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling","date":"2025-04-11","arxiv_id":"2504.08719","n_code_links":0,"syntology":null},{"paper":"/paper/the-other-side-of-the-coin-exploring-fairness","slug":"the-other-side-of-the-coin-exploring-fairness","title":"The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation","date":"2025-04-11","arxiv_id":"2504.12323","n_code_links":1,"syntology":null},{"paper":null,"slug":"vlmt-vision-language-multimodal-transformer","title":"VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering","date":"2025-04-11","arxiv_id":"2504.08269","n_code_links":0,"syntology":null},{"paper":null,"slug":"zipir-latent-pyramid-diffusion-transformer","title":"ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration","date":"2025-04-11","arxiv_id":"2504.08591","n_code_links":0,"syntology":null},{"paper":"/paper/a-system-for-comprehensive-assessment-of-rag","slug":"a-system-for-comprehensive-assessment-of-rag","title":"A System for Comprehensive Assessment of RAG Frameworks","date":"2025-04-10","arxiv_id":"2504.07803","n_code_links":1,"syntology":null},{"paper":"/paper/agentada-skill-adaptive-data-analytics-for","slug":"agentada-skill-adaptive-data-analytics-for","title":"AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery","date":"2025-04-10","arxiv_id":"2504.07421","n_code_links":1,"syntology":null},{"paper":null,"slug":"ai-coding-with-few-shot-prompting-for","title":"AI Coding with Few-Shot Prompting for Thematic Analysis","date":"2025-04-10","arxiv_id":"2504.07408","n_code_links":0,"syntology":null},{"paper":null,"slug":"apsq-additive-partial-sum-quantization-with","title":"APSQ: Additive Partial Sum Quantization with Algorithm-Hardware Co-Design","date":"2025-04-10","arxiv_id":"2505.03748","n_code_links":0,"syntology":null},{"paper":null,"slug":"attentiondefense-leveraging-system-prompt","title":"AttentionDefense: Leveraging System Prompt Attention for Explainable Defense Against Novel Jailbreaks","date":"2025-04-10","arxiv_id":"2504.12321","n_code_links":0,"syntology":null},{"paper":null,"slug":"beating-transformers-using-synthetic","title":"Beating Transformers using Synthetic Cognition","date":"2025-04-10","arxiv_id":"2504.07619","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-feature-importance-feature","title":"Beyond Feature Importance: Feature Interactions in Predicting Post-Stroke Rigidity with Graph Explainable AI","date":"2025-04-10","arxiv_id":"2504.08150","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-llms-a-linguistic-approach-to-causal","title":"Beyond LLMs: A Linguistic Approach to Causal Graph Generation from Narrative Texts","date":"2025-04-10","arxiv_id":"2504.07459","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-the-barriers-video-vision","title":"Breaking the Barriers: Video Vision Transformers for Word-Level Sign Language Recognition","date":"2025-04-10","arxiv_id":"2504.07792","n_code_links":0,"syntology":null},{"paper":"/paper/can-reasoning-llms-enhance-clinical-document","slug":"can-reasoning-llms-enhance-clinical-document","title":"Can Reasoning LLMs Enhance Clinical Document Classification?","date":"2025-04-10","arxiv_id":"2504.08040","n_code_links":1,"syntology":null},{"paper":null,"slug":"conceptformer-towards-efficient-use-of","title":"ConceptFormer: Towards Efficient Use of Knowledge-Graph Embeddings in Large Language Models","date":"2025-04-10","arxiv_id":"2504.07624","n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-meets-teleconnections-improving","slug":"deep-learning-meets-teleconnections-improving","title":"Deep Learning Meets Teleconnections: Improving S2S Predictions for European Winter Weather","date":"2025-04-10","arxiv_id":"2504.07625","n_code_links":1,"syntology":null},{"paper":null,"slug":"distilling-knowledge-from-heterogeneous","title":"Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation","date":"2025-04-10","arxiv_id":"2504.07691","n_code_links":0,"syntology":null},{"paper":null,"slug":"genetic-programming-with-reinforcement","title":"Genetic Programming with Reinforcement Learning Trained Transformer for Real-World Dynamic Scheduling Problems","date":"2025-04-10","arxiv_id":"2504.07779","n_code_links":0,"syntology":null},{"paper":null,"slug":"has-the-creativity-of-large-language-models","title":"Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variability","date":"2025-04-10","arxiv_id":"2504.12320","n_code_links":0,"syntology":null},{"paper":"/paper/heart-failure-prediction-using-modal","slug":"heart-failure-prediction-using-modal","title":"Heart Failure Prediction using Modal Decomposition and Masked Autoencoders for Scarce Echocardiography Databases","date":"2025-04-10","arxiv_id":"2504.07606","n_code_links":1,"syntology":null},{"paper":null,"slug":"jepa4rec-learning-effective-language","title":"JEPA4Rec: Learning Effective Language Representations for Sequential Recommendation via Joint Embedding Predictive Architecture","date":"2025-04-10","arxiv_id":"2504.10512","n_code_links":0,"syntology":null},{"paper":"/paper/mrd-rag-enhancing-medical-diagnosis-with","slug":"mrd-rag-enhancing-medical-diagnosis-with","title":"MRD-RAG: Enhancing Medical Diagnosis with Multi-Round Retrieval-Augmented Generation","date":"2025-04-10","arxiv_id":"2504.07724","n_code_links":1,"syntology":null},{"paper":null,"slug":"novel-pooling-based-vgg-lite-for-pneumonia","title":"Novel Pooling-based VGG-Lite for Pneumonia and Covid-19 Detection from Imbalanced Chest X-Ray Datasets","date":"2025-04-10","arxiv_id":"2504.07468","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-practice-of-deep-hierarchical-ensemble","title":"On the Practice of Deep Hierarchical Ensemble Network for Ad Conversion Rate Prediction","date":"2025-04-10","arxiv_id":"2504.08169","n_code_links":0,"syntology":null},{"paper":null,"slug":"pangu-ultra-pushing-the-limits-of-dense-large","title":"Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUs","date":"2025-04-10","arxiv_id":"2504.07866","n_code_links":0,"syntology":null},{"paper":null,"slug":"pogo-a-scalable-proof-of-useful-work-via","title":"PoGO: A Scalable Proof of Useful Work via Quantized Gradient Descent and Merkle Proofs","date":"2025-04-10","arxiv_id":"2504.07540","n_code_links":0,"syntology":null},{"paper":"/paper/radzero-similarity-based-cross-attention-for","slug":"radzero-similarity-based-cross-attention-for","title":"RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Radiology with Zero-Shot Multi-Task Capability","date":"2025-04-10","arxiv_id":"2504.07416","n_code_links":0,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"revisiting-prompt-optimization-with-large","title":"Revisiting Prompt Optimization with Large Reasoning Models-A Case Study on Event Extraction","date":"2025-04-10","arxiv_id":"2504.07357","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthetic-fluency-hallucinations","title":"Synthetic Fluency: Hallucinations, Confabulations, and the Creation of Irish Words in LLM-Generated Translations","date":"2025-04-10","arxiv_id":"2504.07680","n_code_links":0,"syntology":null},{"paper":"/paper/a-new-training-approach-for-text","slug":"a-new-training-approach-for-text","title":"A new training approach for text classification in Mental Health: LatentGLoss","date":"2025-04-09","arxiv_id":"2504.07245","n_code_links":1,"syntology":null},{"paper":null,"slug":"amad-automasked-attention-for-unsupervised","title":"AMAD: AutoMasked Attention for Unsupervised Multivariate Time Series Anomaly Detection","date":"2025-04-09","arxiv_id":"2504.06643","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-multimodal-cot-reward-model","slug":"benchmarking-multimodal-cot-reward-model","title":"Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program","date":"2025-04-09","arxiv_id":"2504.06606","n_code_links":1,"syntology":null},{"paper":"/paper/dydit-dynamic-diffusion-transformers-for","slug":"dydit-dynamic-diffusion-transformers-for","title":"DyDiT++: Dynamic Diffusion Transformers for Efficient Visual Generation","date":"2025-04-09","arxiv_id":"2504.06803","n_code_links":1,"syntology":null},{"paper":null,"slug":"endowing-embodied-agents-with-spatial","title":"Endowing Embodied Agents with Spatial Reasoning Capabilities for Vision-and-Language Navigation","date":"2025-04-09","arxiv_id":"2504.08806","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-retrieval-augmented-generative","title":"Evaluating Retrieval Augmented Generative Models for Document Queries in Transportation Safety","date":"2025-04-09","arxiv_id":"2504.07022","n_code_links":0,"syntology":null},{"paper":null,"slug":"face-llava-facial-expression-and-attribute","title":"Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning","date":"2025-04-09","arxiv_id":"2504.07198","n_code_links":0,"syntology":null},{"paper":null,"slug":"gendop-auto-regressive-camera-trajectory","title":"GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography","date":"2025-04-09","arxiv_id":"2504.07083","n_code_links":0,"syntology":null},{"paper":"/paper/kaleidoscope-in-language-exams-for-massively","slug":"kaleidoscope-in-language-exams-for-massively","title":"Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation","date":"2025-04-09","arxiv_id":"2504.07072","n_code_links":1,"syntology":null},{"paper":"/paper/linguistic-interpretability-of-transformer","slug":"linguistic-interpretability-of-transformer","title":"Linguistic Interpretability of Transformer-based Language Models: a systematic review","date":"2025-04-09","arxiv_id":"2504.08001","n_code_links":1,"syntology":null},{"paper":null,"slug":"poly-vector-retrieval-reference-and-content","title":"Poly-Vector Retrieval: Reference and Content Embeddings for Legal Documents","date":"2025-04-09","arxiv_id":"2504.10508","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-how-hyperparameters-impact-large","title":"Assessing how hyperparameters impact Large Language Models' sarcasm detection performance","date":"2025-04-08","arxiv_id":"2504.06166","n_code_links":0,"syntology":null},{"paper":null,"slug":"fusing-global-and-local-transformer-cnn","title":"Fusing Global and Local: Transformer-CNN Synergy for Next-Gen Current Estimation","date":"2025-04-08","arxiv_id":"2504.07996","n_code_links":0,"syntology":null},{"paper":"/paper/gaze-guided-learning-avoiding-shortcut-bias","slug":"gaze-guided-learning-avoiding-shortcut-bias","title":"Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification","date":"2025-04-08","arxiv_id":"2504.05583","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-based-approaches-and-functionalities-in","title":"Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey","date":"2025-04-08","arxiv_id":"2504.10499","n_code_links":0,"syntology":null},{"paper":"/paper/hrmedseg-unlocking-high-resolution-medical","slug":"hrmedseg-unlocking-high-resolution-medical","title":"HRMedSeg: Unlocking High-resolution Medical Image segmentation via Memory-efficient Attention Modeling","date":"2025-04-08","arxiv_id":"2504.06205","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-auto-distillation-and-generative","title":"Leveraging Auto-Distillation and Generative Self-Supervised Learning in Residual Graph Transformers for Enhanced Recommender Systems","date":"2025-04-08","arxiv_id":"2504.10500","n_code_links":0,"syntology":null},{"paper":null,"slug":"pathgpt-leveraging-large-language-models-for","title":"PathGPT: Leveraging Large Language Models for Personalized Route Generation","date":"2025-04-08","arxiv_id":"2504.05846","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-the-nested-u-net-approach","slug":"rethinking-the-nested-u-net-approach","title":"Rethinking the Nested U-Net Approach: Enhancing Biomarker Segmentation with Attention Mechanisms and Multiscale Feature Fusion","date":"2025-04-08","arxiv_id":"2504.06158","n_code_links":1,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-with-2","slug":"retrieval-augmented-generation-with-2","title":"Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation","date":"2025-04-08","arxiv_id":"2504.05731","n_code_links":1,"syntology":null},{"paper":null,"slug":"ai-for-climate-finance-agentic-retrieval-and","title":"AI for Climate Finance: Agentic Retrieval and Multi-Step Reasoning for Early Warning System Investments","date":"2025-04-07","arxiv_id":"2504.05104","n_code_links":0,"syntology":null},{"paper":null,"slug":"boundary-representation-learning-via","title":"Boundary representation learning via Transformer","date":"2025-04-07","arxiv_id":"2504.07134","n_code_links":0,"syntology":null},{"paper":null,"slug":"ccsk-cognitive-convection-of-self-knowledge","title":"CCSK:Cognitive Convection of Self-Knowledge Based Retrieval Augmentation for Large Language Models","date":"2025-04-07","arxiv_id":"2504.10498","n_code_links":0,"syntology":null},{"paper":"/paper/collab-rag-boosting-retrieval-augmented","slug":"collab-rag-boosting-retrieval-augmented","title":"Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration","date":"2025-04-07","arxiv_id":"2504.04915","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["ritaranx/collab-rag"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/content-aware-transformer-for-all-in-one","slug":"content-aware-transformer-for-all-in-one","title":"Content-Aware Transformer for All-in-one Image Restoration","date":"2025-04-07","arxiv_id":"2504.04869","n_code_links":1,"syntology":null},{"paper":null,"slug":"instructionbench-an-instructional-video","title":"InstructionBench: An Instructional Video Understanding Benchmark","date":"2025-04-07","arxiv_id":"2504.05040","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-llms-for-utility-focused","title":"Leveraging LLMs for Utility-Focused Annotation: Reducing Manual Effort for Retrieval and RAG","date":"2025-04-07","arxiv_id":"2504.05220","n_code_links":0,"syntology":null},{"paper":null,"slug":"lumina-omnilv-a-unified-multimodal-framework","title":"Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision","date":"2025-04-07","arxiv_id":"2504.04903","n_code_links":0,"syntology":null},{"paper":"/paper/omniecon-nexus-global-microeconomic","slug":"omniecon-nexus-global-microeconomic","title":"OmniEcon Nexus: Global Microeconomic Simulation Engine","date":"2025-04-07","arxiv_id":null,"n_code_links":1,"syntology":null}],"record_sha256":"93a0ef1b63e5107cd3f5f0d9475789baeb970cd7554338224ff7bec2f7a9fdd6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}