{"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/37","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":37,"pages_in_order":249,"rows_per_page":100,"rows":[3601,3700],"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/36","next":"/method/multi-head-attention/papers/38","papers":[{"paper":null,"slug":"data-extraction-attacks-in-retrieval","title":"Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors","date":"2024-11-03","arxiv_id":"2411.01705","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-glucose-level-prediction-of-icu","slug":"enhancing-glucose-level-prediction-of-icu","title":"Enhancing Glucose Level Prediction of ICU Patients through Hierarchical Modeling of Irregular Time-Series","date":"2024-11-03","arxiv_id":"2411.01418","n_code_links":1,"syntology":null},{"paper":null,"slug":"enriching-tabular-data-with-contextual-llm","title":"Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifiers","date":"2024-11-03","arxiv_id":"2411.01645","n_code_links":0,"syntology":null},{"paper":null,"slug":"facet-aware-multi-head-mixture-of-experts","title":"Facet-Aware Multi-Head Mixture-of-Experts Model for Sequential Recommendation","date":"2024-11-03","arxiv_id":"2411.01457","n_code_links":0,"syntology":null},{"paper":null,"slug":"gitsr-graph-interaction-transformer-based","title":"GITSR: Graph Interaction Transformer-based Scene Representation for Multi Vehicle Collaborative Decision-making","date":"2024-11-03","arxiv_id":"2411.01608","n_code_links":0,"syntology":null},{"paper":"/paper/graphxform-graph-transformer-for-computer","slug":"graphxform-graph-transformer-for-computer","title":"GraphXForm: Graph transformer for computer-aided molecular design","date":"2024-11-03","arxiv_id":"2411.01667","n_code_links":1,"syntology":null},{"paper":null,"slug":"high-performance-automated-abstract-screening","title":"High-performance automated abstract screening with large language model ensembles","date":"2024-11-03","arxiv_id":"2411.02451","n_code_links":0,"syntology":null},{"paper":null,"slug":"himemformer-hierarchical-memory-aware","title":"HiMemFormer: Hierarchical Memory-Aware Transformer for Multi-Agent Action Anticipation","date":"2024-11-03","arxiv_id":"2411.01455","n_code_links":0,"syntology":null},{"paper":null,"slug":"integration-of-large-vision-language-models","title":"Integration of Large Vision Language Models for Efficient Post-disaster Damage Assessment and Reporting","date":"2024-11-03","arxiv_id":"2411.01511","n_code_links":0,"syntology":null},{"paper":"/paper/linrec-linear-attention-mechanism-for-long","slug":"linrec-linear-attention-mechanism-for-long","title":"LinRec: Linear Attention Mechanism for Long-term Sequential Recommender Systems","date":"2024-11-03","arxiv_id":"2411.01537","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Applied-Machine-Learning-Lab/LinRec"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"uniguard-towards-universal-safety-guardrails","title":"UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models","date":"2024-11-03","arxiv_id":"2411.01703","n_code_links":0,"syntology":null},{"paper":"/paper/an-innovative-cgl-mha-model-for-sarcasm","slug":"an-innovative-cgl-mha-model-for-sarcasm","title":"An Innovative CGL-MHA Model for Sarcasm Sentiment Recognition Using the MindSpore Framework","date":"2024-11-02","arxiv_id":"2411.01264","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-large-language-model-predict-employee","title":"Can Large Language Model Predict Employee Attrition?","date":"2024-11-02","arxiv_id":"2411.01353","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-neural-network-interpretability-1","slug":"enhancing-neural-network-interpretability-1","title":"Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders","date":"2024-11-02","arxiv_id":"2411.01220","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":["luke-marks0/mutual-feature-regularization"],"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":"/paper/few-class-arena-a-benchmark-for-efficient","slug":"few-class-arena-a-benchmark-for-efficient","title":"Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurement","date":"2024-11-02","arxiv_id":"2411.01099","n_code_links":1,"syntology":null},{"paper":null,"slug":"reasoning-limitations-of-multimodal-large","title":"Reasoning Limitations of Multimodal Large Language Models. A case study of Bongard Problems","date":"2024-11-02","arxiv_id":"2411.01173","n_code_links":0,"syntology":null},{"paper":"/paper/task-aware-harmony-multi-task-decision","slug":"task-aware-harmony-multi-task-decision","title":"Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning","date":"2024-11-02","arxiv_id":"2411.01146","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["charleshsc/HarmoDT"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-lorentz-equivariant-transformer-for-all-of","slug":"a-lorentz-equivariant-transformer-for-all-of","title":"A Lorentz-Equivariant Transformer for All of the LHC","date":"2024-11-01","arxiv_id":"2411.00446","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":["heidelberg-hepml/lorentz-gatr"],"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":"attackqa-development-and-adoption-of-a","title":"AttackQA: Development and Adoption of a Dataset for Assisting Cybersecurity Operations using Fine-tuned and Open-Source LLMs","date":"2024-11-01","arxiv_id":"2411.01073","n_code_links":0,"syntology":null},{"paper":null,"slug":"corag-a-cost-constrained-retrieval","title":"CORAG: A Cost-Constrained Retrieval Optimization System for Retrieval-Augmented Generation","date":"2024-11-01","arxiv_id":"2411.00744","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-fundus-transformer-for-multi-modal","title":"Cross-Fundus Transformer for Multi-modal Diabetic Retinopathy Grading with Cataract","date":"2024-11-01","arxiv_id":"2411.00726","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-impact-of-lab-test-results-on","title":"Evaluating the Impact of Lab Test Results on Large Language Models Generated Differential Diagnoses from Clinical Case Vignettes","date":"2024-11-01","arxiv_id":"2411.02523","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-ref-enhancing-reference-handling-in","title":"LLM-Ref: Enhancing Reference Handling in Technical Writing with Large Language Models","date":"2024-11-01","arxiv_id":"2411.00294","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-a-game-changer-for-software-engineers","title":"LLMs: A Game-Changer for Software Engineers?","date":"2024-11-01","arxiv_id":"2411.00932","n_code_links":0,"syntology":null},{"paper":null,"slug":"provenance-a-light-weight-fact-checker-for","title":"Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output","date":"2024-11-01","arxiv_id":"2411.01022","n_code_links":0,"syntology":null},{"paper":"/paper/rationale-guided-retrieval-augmented","slug":"rationale-guided-retrieval-augmented","title":"Rationale-Guided Retrieval Augmented Generation for Medical Question Answering","date":"2024-11-01","arxiv_id":"2411.00300","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["dmis-lab/rag2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-evolved-reward-learning-for-llms","slug":"self-evolved-reward-learning-for-llms","title":"Self-Evolved Reward Learning for LLMs","date":"2024-11-01","arxiv_id":"2411.00418","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":null}},{"paper":"/paper/staa-spatio-temporal-attention-attribution","slug":"staa-spatio-temporal-attention-attribution","title":"STAA: Spatio-Temporal Attention Attribution for Real-Time Interpreting Transformer-based Video Models","date":"2024-11-01","arxiv_id":"2411.00630","n_code_links":1,"syntology":null},{"paper":"/paper/target-guided-adversarial-point-cloud","slug":"target-guided-adversarial-point-cloud","title":"Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptions","date":"2024-11-01","arxiv_id":"2411.00462","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":["roywangj/apct"],"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":"towards-high-fidelity-head-blending-with","title":"Towards High-fidelity Head Blending with Chroma Keying for Industrial Applications","date":"2024-11-01","arxiv_id":"2411.00652","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-multi-source-retrieval-augmented","title":"Towards Multi-Source Retrieval-Augmented Generation via Synergizing Reasoning and Preference-Driven Retrieval","date":"2024-11-01","arxiv_id":"2411.00689","n_code_links":0,"syntology":null},{"paper":"/paper/ada-mshyper-adaptive-multi-scale-hypergraph","slug":"ada-mshyper-adaptive-multi-scale-hypergraph","title":"Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting","date":"2024-10-31","arxiv_id":"2410.23992","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["shangzongjiang/Ada-MSHyper"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"aerial-flood-scene-classification-using-fine","title":"Aerial Flood Scene Classification Using Fine-Tuned Attention-based Architecture for Flood-Prone Countries in South Asia","date":"2024-10-31","arxiv_id":"2411.00169","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-reducing-the-need-for-learning-rate","title":"Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training","date":"2024-10-31","arxiv_id":"2410.23922","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-is-all-you-need-to-optimize-wind","title":"Attention is All You Need to Optimize Wind Farm Operations and Maintenance","date":"2024-10-31","arxiv_id":"2410.24052","n_code_links":0,"syntology":null},{"paper":null,"slug":"automating-quantum-software-maintenance","title":"Automating Quantum Software Maintenance: Flakiness Detection and Root Cause Analysis","date":"2024-10-31","arxiv_id":"2410.23578","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-in-long-short-stock-portfolio","title":"Deep Learning in Long-Short Stock Portfolio Allocation: An Empirical Study","date":"2024-10-31","arxiv_id":"2411.13555","n_code_links":0,"syntology":null},{"paper":null,"slug":"desert-camels-and-oil-sheikhs-arab-centric","title":"Desert Camels and Oil Sheikhs: Arab-Centric Red Teaming of Frontier LLMs","date":"2024-10-31","arxiv_id":"2410.24049","n_code_links":0,"syntology":null},{"paper":"/paper/edt-an-efficient-diffusion-transformer","slug":"edt-an-efficient-diffusion-transformer","title":"EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching","date":"2024-10-31","arxiv_id":"2410.23788","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":9,"n_instrument":3,"unverified":3,"pointer_only":2,"phrase":"12 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["xinwangchen/edt"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":7,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"enhancing-brain-tumor-classification-using","title":"Enhancing Brain Tumor Classification Using TrAdaBoost and Multi-Classifier Deep Learning Approaches","date":"2024-10-31","arxiv_id":"2411.00875","n_code_links":0,"syntology":null},{"paper":null,"slug":"handwriting-recognition-in-historical","title":"Handwriting Recognition in Historical Documents with Multimodal LLM","date":"2024-10-31","arxiv_id":"2410.24034","n_code_links":0,"syntology":null},{"paper":null,"slug":"io-transformer-evaluating-swinv2-based-reward","title":"IO Transformer: Evaluating SwinV2-Based Reward Models for Computer Vision","date":"2024-10-31","arxiv_id":"2411.00252","n_code_links":0,"syntology":null},{"paper":null,"slug":"jema-a-joint-embedding-framework-for-scalable","title":"JEMA: A Joint Embedding Framework for Scalable Co-Learning with Multimodal Alignment","date":"2024-10-31","arxiv_id":"2410.23988","n_code_links":0,"syntology":null},{"paper":null,"slug":"judgerank-leveraging-large-language-models","title":"JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking","date":"2024-10-31","arxiv_id":"2411.00142","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-patient-comments","title":"Large Language Models for Patient Comments Multi-Label Classification","date":"2024-10-31","arxiv_id":"2410.23528","n_code_links":0,"syntology":null},{"paper":null,"slug":"leaf-learning-and-evaluation-augmented-by","title":"LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models","date":"2024-10-31","arxiv_id":"2410.23526","n_code_links":0,"syntology":null},{"paper":null,"slug":"lseattention-is-all-you-need-for-time-series","title":"LSEAttention is All You Need for Time Series Forecasting","date":"2024-10-31","arxiv_id":"2410.23749","n_code_links":0,"syntology":null},{"paper":"/paper/reinforcement-learning-gradients-as-vitamin","slug":"reinforcement-learning-gradients-as-vitamin","title":"Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers","date":"2024-10-31","arxiv_id":"2410.24108","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["kaiyan289/rl_as_vitamin_for_online_decision_transformers"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"responsible-retrieval-augmented-generation","title":"Responsible Retrieval Augmented Generation for Climate Decision Making from Documents","date":"2024-10-31","arxiv_id":"2410.23902","n_code_links":0,"syntology":null},{"paper":"/paper/rsl-sql-robust-schema-linking-in-text-to-sql","slug":"rsl-sql-robust-schema-linking-in-text-to-sql","title":"RSL-SQL: Robust Schema Linking in Text-to-SQL Generation","date":"2024-10-31","arxiv_id":"2411.00073","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":["laqcce-cao/rsl-sql"],"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":"/paper/selfcodealign-self-alignment-for-code","slug":"selfcodealign-self-alignment-for-code","title":"SelfCodeAlign: Self-Alignment for Code Generation","date":"2024-10-31","arxiv_id":"2410.24198","n_code_links":2,"syntology":{"ran":30,"of":37,"n_ran_checked":22,"n_instrument":8,"unverified":7,"pointer_only":0,"phrase":"30 ran (of which 3 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified","official":{"repos":["bigcode-project/selfcodealign"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["community","listed","official"]}}},{"paper":null,"slug":"vit-lca-a-neuromorphic-approach-for-vision","title":"ViT-LCA: A Neuromorphic Approach for Vision Transformers","date":"2024-10-31","arxiv_id":"2411.00140","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-study-on-quantization","title":"A Comprehensive Study on Quantization Techniques for Large Language Models","date":"2024-10-30","arxiv_id":"2411.02530","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-neural-transformer-framework-for","title":"A Transformer Model for Segmentation, Classification, and Caller Identification of Marmoset Vocalization","date":"2024-10-30","arxiv_id":"2410.23279","n_code_links":0,"syntology":null},{"paper":"/paper/coral-benchmarking-multi-turn-conversational","slug":"coral-benchmarking-multi-turn-conversational","title":"CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation","date":"2024-10-30","arxiv_id":"2410.23090","n_code_links":1,"syntology":null},{"paper":null,"slug":"danoliteracy-of-generative-large-language","title":"Danoliteracy of Generative, Large Language Models","date":"2024-10-30","arxiv_id":"2410.22839","n_code_links":0,"syntology":null},{"paper":null,"slug":"eliciting-critical-reasoning-in-retrieval","title":"Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations","date":"2024-10-30","arxiv_id":"2410.22874","n_code_links":0,"syntology":null},{"paper":"/paper/emergence-of-human-like-attention-in-self","slug":"emergence-of-human-like-attention-in-self","title":"Emergence of Human-Like Attention in Self-Supervised Vision Transformers: an eye-tracking study","date":"2024-10-30","arxiv_id":"2410.22768","n_code_links":1,"syntology":null},{"paper":null,"slug":"emergence-of-meta-stable-clustering-in-mean","title":"Emergence of meta-stable clustering in mean-field transformer models","date":"2024-10-30","arxiv_id":"2410.23228","n_code_links":0,"syntology":null},{"paper":"/paper/emotional-rag-enhancing-role-playing-agents","slug":"emotional-rag-enhancing-role-playing-agents","title":"Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrieval","date":"2024-10-30","arxiv_id":"2410.23041","n_code_links":1,"syntology":null},{"paper":null,"slug":"epipolar-free-3d-gaussian-splatting-for","title":"Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis","date":"2024-10-30","arxiv_id":"2410.22817","n_code_links":0,"syntology":null},{"paper":"/paper/evocodebench-an-evolving-code-generation-1","slug":"evocodebench-an-evolving-code-generation-1","title":"EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations","date":"2024-10-30","arxiv_id":"2410.22821","n_code_links":0,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/high-fidelity-document-stain-removal-via-a","slug":"high-fidelity-document-stain-removal-via-a","title":"High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer","date":"2024-10-30","arxiv_id":"2410.22922","n_code_links":1,"syntology":null},{"paper":null,"slug":"higher-order-cross-structural-embedding-model","title":"Higher-order Cross-structural Embedding Model for Time Series Analysis","date":"2024-10-30","arxiv_id":"2410.22984","n_code_links":0,"syntology":null},{"paper":null,"slug":"hijackrag-hijacking-attacks-against-retrieval","title":"HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models","date":"2024-10-30","arxiv_id":"2410.22832","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-achieve-goals-with-belief-state","title":"Learning to Achieve Goals with Belief State Transformers","date":"2024-10-30","arxiv_id":"2410.23506","n_code_links":0,"syntology":null},{"paper":null,"slug":"loflat-local-feature-matching-using-focused","title":"LoFLAT: Local Feature Matching using Focused Linear Attention Transformer","date":"2024-10-30","arxiv_id":"2410.22710","n_code_links":0,"syntology":null},{"paper":"/paper/nmformer-a-transformer-for-noisy-modulation","slug":"nmformer-a-transformer-for-noisy-modulation","title":"NMformer: A Transformer for Noisy Modulation Classification in Wireless Communication","date":"2024-10-30","arxiv_id":"2411.02428","n_code_links":1,"syntology":null},{"paper":"/paper/protransformer-robustify-transformers-via","slug":"protransformer-robustify-transformers-via","title":"ProTransformer: Robustify Transformers via Plug-and-Play Paradigm","date":"2024-10-30","arxiv_id":"2410.23182","n_code_links":1,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-with","title":"Retrieval-Augmented Generation with Estimation of Source Reliability","date":"2024-10-30","arxiv_id":"2410.22954","n_code_links":0,"syntology":null},{"paper":null,"slug":"return-augmented-decision-transformer-for-off","title":"Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning","date":"2024-10-30","arxiv_id":"2410.23450","n_code_links":0,"syntology":null},{"paper":null,"slug":"s3pt-scene-semantics-and-structure-guided","title":"S3PT: Scene Semantics and Structure Guided Clustering to Boost Self-Supervised Pre-Training for Autonomous Driving","date":"2024-10-30","arxiv_id":"2410.23085","n_code_links":0,"syntology":null},{"paper":"/paper/scipip-an-llm-based-scientific-paper-idea","slug":"scipip-an-llm-based-scientific-paper-idea","title":"SciPIP: An LLM-based Scientific Paper Idea Proposer","date":"2024-10-30","arxiv_id":"2410.23166","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cheerss/scipip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/semantic-enrichment-of-the-quantum-cascade","slug":"semantic-enrichment-of-the-quantum-cascade","title":"Semantic Enrichment of the Quantum Cascade Laser Properties in Text- A Knowledge Graph Generation Approach","date":"2024-10-30","arxiv_id":"2410.22996","n_code_links":1,"syntology":null},{"paper":null,"slug":"st-dtpm-spatial-temporal-guided-diffusion","title":"st-DTPM: Spatial-Temporal Guided Diffusion Transformer Probabilistic Model for Delayed Scan PET Image Prediction","date":"2024-10-30","arxiv_id":"2410.22732","n_code_links":0,"syntology":null},{"paper":null,"slug":"textsc-long-2-rag-evaluating-long-context","title":"Long$^2$RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall","date":"2024-10-30","arxiv_id":"2410.23000","n_code_links":0,"syntology":null},{"paper":"/paper/very-fast-bayesian-additive-regression-trees","slug":"very-fast-bayesian-additive-regression-trees","title":"Very fast Bayesian Additive Regression Trees on GPU","date":"2024-10-30","arxiv_id":"2410.23244","n_code_links":1,"syntology":null},{"paper":"/paper/a-large-recurrent-action-model-xlstm-enables","slug":"a-large-recurrent-action-model-xlstm-enables","title":"A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks","date":"2024-10-29","arxiv_id":"2410.22391","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ml-jku/lram"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/abrupt-learning-in-transformers-a-case-study","slug":"abrupt-learning-in-transformers-a-case-study","title":"Abrupt Learning in Transformers: A Case Study on Matrix Completion","date":"2024-10-29","arxiv_id":"2410.22244","n_code_links":0,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/amplegcg-plus-a-strong-generative-model-of","slug":"amplegcg-plus-a-strong-generative-model-of","title":"AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts","date":"2024-10-29","arxiv_id":"2410.22143","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":7,"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) · 0 unverified","official":null}},{"paper":"/paper/beyond-text-optimizing-rag-with-multimodal","slug":"beyond-text-optimizing-rag-with-multimodal","title":"Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications","date":"2024-10-29","arxiv_id":"2410.21943","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["riedlerm/multimodal_rag_for_industry"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cfsafety-comprehensive-fine-grained-safety","title":"CFSafety: Comprehensive Fine-grained Safety Assessment for LLMs","date":"2024-10-29","arxiv_id":"2410.21695","n_code_links":0,"syntology":null},{"paper":null,"slug":"coupling-quantum-like-cognition-with-the","title":"Coupling quantum-like cognition with the neuronal networks within generalized probability theory","date":"2024-10-29","arxiv_id":"2411.00036","n_code_links":0,"syntology":null},{"paper":null,"slug":"dineuro-distilling-knowledge-from-2d-natural","title":"DINeuro: Distilling Knowledge from 2D Natural Images via Deformable Tubular Transferring Strategy for 3D Neuron Reconstruction","date":"2024-10-29","arxiv_id":"2410.22078","n_code_links":0,"syntology":null},{"paper":null,"slug":"dual-conditional-diffusion-models-for","title":"Dual Conditional Diffusion Models for Sequential Recommendation","date":"2024-10-29","arxiv_id":"2410.21967","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-machine-translation-with-a-bilstm","slug":"efficient-machine-translation-with-a-bilstm","title":"Efficient Machine Translation with a BiLSTM-Attention Approach","date":"2024-10-29","arxiv_id":"2410.22335","n_code_links":2,"syntology":null},{"paper":null,"slug":"emotion-guided-image-to-music-generation","title":"Emotion-Guided Image to Music Generation","date":"2024-10-29","arxiv_id":"2410.22299","n_code_links":0,"syntology":null},{"paper":"/paper/et-flow-equivariant-flow-matching-for","slug":"et-flow-equivariant-flow-matching-for","title":"ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generation","date":"2024-10-29","arxiv_id":"2410.22388","n_code_links":1,"syntology":{"ran":12,"of":12,"n_ran_checked":12,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shenoynikhil/etflow"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluating-k-fold-cross-validation-for","title":"Evaluating K-Fold Cross Validation for Transformer Based Symbolic Regression Models","date":"2024-10-29","arxiv_id":"2410.21896","n_code_links":0,"syntology":null},{"paper":null,"slug":"factbench-a-dynamic-benchmark-for-in-the-wild","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","date":"2024-10-29","arxiv_id":"2410.22257","n_code_links":0,"syntology":null},{"paper":null,"slug":"fourier-head-helping-large-language-models","title":"Fourier Head: Helping Large Language Models Learn Complex Probability Distributions","date":"2024-10-29","arxiv_id":"2410.22269","n_code_links":0,"syntology":null},{"paper":null,"slug":"hrpvt-high-resolution-pyramid-vision","title":"HRPVT: High-Resolution Pyramid Vision Transformer for medium and small-scale human pose estimation","date":"2024-10-29","arxiv_id":"2410.22079","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-user-history-with-transformers-for","slug":"leveraging-user-history-with-transformers-for","title":"Leveraging User History with Transformers for News Clicking: The DArgk Approach","date":"2024-10-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/long-context-protein-language-model","slug":"long-context-protein-language-model","title":"Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers","date":"2024-10-29","arxiv_id":"2411.08909","n_code_links":1,"syntology":null},{"paper":null,"slug":"meta-learning-adaptable-foundation-models","title":"Meta-Learning Adaptable Foundation Models","date":"2024-10-29","arxiv_id":"2410.22264","n_code_links":0,"syntology":null},{"paper":"/paper/multi-step-feature-fusion-for-natural","slug":"multi-step-feature-fusion-for-natural","title":"Multi-step feature fusion for natural disaster damage assessment on satellite images","date":"2024-10-29","arxiv_id":"2410.21901","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-role-of-depth-and-looping-for-in","title":"On the Role of Depth and Looping for In-Context Learning with Task Diversity","date":"2024-10-29","arxiv_id":"2410.21698","n_code_links":0,"syntology":null},{"paper":"/paper/sam-swin-sam-driven-dual-swin-transformers","slug":"sam-swin-sam-driven-dual-swin-transformers","title":"SAM-Swin: SAM-Driven Dual-Swin Transformers with Adaptive Lesion Enhancement for Laryngo-Pharyngeal Tumor Detection","date":"2024-10-29","arxiv_id":"2410.21813","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-preference-bias-in-llm-as-a-judge","title":"Self-Preference Bias in LLM-as-a-Judge","date":"2024-10-29","arxiv_id":"2410.21819","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequential-choice-in-ordered-bundles","title":"Sequential choice in ordered bundles","date":"2024-10-29","arxiv_id":"2410.21670","n_code_links":0,"syntology":null}],"record_sha256":"6ea843e7dfdfae1acd86e29d5777387d8e7f5d5f9aafc36a74baae79beb03500","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}