{"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/42","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":42,"pages_in_order":249,"rows_per_page":100,"rows":[4101,4200],"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/41","next":"/method/multi-head-attention/papers/43","papers":[{"paper":null,"slug":"automatic-speech-recognition-with-bert-and","title":"Automatic Speech Recognition with BERT and CTC Transformers: A Review","date":"2024-10-12","arxiv_id":"2410.09456","n_code_links":0,"syntology":null},{"paper":null,"slug":"diabetic-retinopathy-image-classification","title":"Diabetic retinopathy image classification method based on GreenBen data augmentation","date":"2024-10-12","arxiv_id":"2410.09444","n_code_links":0,"syntology":null},{"paper":null,"slug":"eg-spikeformer-eye-gaze-guided-transformer-on","title":"EG-SpikeFormer: Eye-Gaze Guided Transformer on Spiking Neural Networks for Medical Image Analysis","date":"2024-10-12","arxiv_id":"2410.09674","n_code_links":0,"syntology":null},{"paper":null,"slug":"extended-japanese-commonsense-morality","title":"Extended Japanese Commonsense Morality Dataset with Masked Token and Label Enhancement","date":"2024-10-12","arxiv_id":"2410.09564","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpton-generative-pre-trained-transformers","title":"GPTON: Generative Pre-trained Transformers enhanced with Ontology Narration for accurate annotation of biological data","date":"2024-10-12","arxiv_id":"2410.10899","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-3d-finger-traits-recognition-via","title":"Improving 3D Finger Traits Recognition via Generalizable Neural Rendering","date":"2024-10-12","arxiv_id":"2410.09582","n_code_links":0,"syntology":null},{"paper":null,"slug":"llinstruct-an-instruction-tuned-model-for","title":"\\llinstruct: An Instruction-tuned model for English Language Proficiency Assessments","date":"2024-10-12","arxiv_id":"2410.09314","n_code_links":0,"syntology":null},{"paper":null,"slug":"looped-relu-mlps-may-be-all-you-need-as","title":"Looped ReLU MLPs May Be All You Need as Practical Programmable Computers","date":"2024-10-12","arxiv_id":"2410.09375","n_code_links":0,"syntology":null},{"paper":null,"slug":"token-pruning-using-a-lightweight-background","title":"Token Pruning using a Lightweight Background Aware Vision Transformer","date":"2024-10-12","arxiv_id":"2410.09324","n_code_links":0,"syntology":null},{"paper":"/paper/toward-general-instruction-following","slug":"toward-general-instruction-following","title":"Toward General Instruction-Following Alignment for Retrieval-Augmented Generation","date":"2024-10-12","arxiv_id":"2410.09584","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":9,"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) · 2 unverified","official":{"repos":["dongguanting/FollowRAG"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-methodology-for-evaluating-rag-systems-a","slug":"a-methodology-for-evaluating-rag-systems-a","title":"A Methodology for Evaluating RAG Systems: A Case Study On Configuration Dependency Validation","date":"2024-10-11","arxiv_id":"2410.08801","n_code_links":1,"syntology":null},{"paper":"/paper/adaptive-constraint-integration-for","slug":"adaptive-constraint-integration-for","title":"Rethinking Gradient-Based Methods: Multi-Property Materials Design Beyond Differentiable Targets","date":"2024-10-11","arxiv_id":"2410.08562","n_code_links":1,"syntology":null},{"paper":"/paper/attngcg-enhancing-jailbreaking-attacks-on","slug":"attngcg-enhancing-jailbreaking-attacks-on","title":"AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation","date":"2024-10-11","arxiv_id":"2410.09040","n_code_links":1,"syntology":null},{"paper":null,"slug":"cotconet-an-optimized-coupled-transformer","title":"CoTCoNet: An Optimized Coupled Transformer-Convolutional Network with an Adaptive Graph Reconstruction for Leukemia Detection","date":"2024-10-11","arxiv_id":"2410.08797","n_code_links":0,"syntology":null},{"paper":"/paper/dat-dialogue-aware-transformer-with-modality","slug":"dat-dialogue-aware-transformer-with-modality","title":"DAT: Dialogue-Aware Transformer with Modality-Group Fusion for Human Engagement Estimation","date":"2024-10-11","arxiv_id":"2410.08470","n_code_links":1,"syntology":null},{"paper":"/paper/debiformer-vision-transformer-with-deformable","slug":"debiformer-vision-transformer-with-deformable","title":"DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention","date":"2024-10-11","arxiv_id":"2410.08582","n_code_links":1,"syntology":null},{"paper":"/paper/developing-a-pragmatic-benchmark-for","slug":"developing-a-pragmatic-benchmark-for","title":"Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models","date":"2024-10-11","arxiv_id":"2410.08731","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficiently-scanning-and-resampling-spatio","title":"Efficiently Scanning and Resampling Spatio-Temporal Tasks with Irregular Observations","date":"2024-10-11","arxiv_id":"2410.08681","n_code_links":0,"syntology":null},{"paper":null,"slug":"encoding-agent-trajectories-as","title":"Encoding Agent Trajectories as Representations with Sequence Transformers","date":"2024-10-11","arxiv_id":"2410.09204","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-long-context-performance-in-llms","title":"Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism","date":"2024-10-11","arxiv_id":"2410.12859","n_code_links":0,"syntology":null},{"paper":null,"slug":"extra-global-attention-designation-using","title":"Extra Global Attention Designation Using Keyword Detection in Sparse Transformer Architectures","date":"2024-10-11","arxiv_id":"2410.08971","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-in-house-large-language-models-to","title":"Fine-Tuning In-House Large Language Models to Infer Differential Diagnosis from Radiology Reports","date":"2024-10-11","arxiv_id":"2410.09234","n_code_links":0,"syntology":null},{"paper":null,"slug":"horgait-advancing-gait-recognition-with","title":"HorGait: A Hybrid Model for Accurate Gait Recognition in LiDAR Point Cloud Planar Projections","date":"2024-10-11","arxiv_id":"2410.08454","n_code_links":0,"syntology":null},{"paper":null,"slug":"humanity-in-ai-detecting-the-personality-of","title":"Humanity in AI: Detecting the Personality of Large Language Models","date":"2024-10-11","arxiv_id":"2410.08545","n_code_links":0,"syntology":null},{"paper":null,"slug":"hypothesis-only-biases-in-large-language","title":"Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference","date":"2024-10-11","arxiv_id":"2410.08996","n_code_links":0,"syntology":null},{"paper":"/paper/jailjudge-a-comprehensive-jailbreak-judge","slug":"jailjudge-a-comprehensive-jailbreak-judge","title":"JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework","date":"2024-10-11","arxiv_id":"2410.12855","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/l3cube-mahasum-a-comprehensive-dataset-and","slug":"l3cube-mahasum-a-comprehensive-dataset-and","title":"L3Cube-MahaSum: A Comprehensive Dataset and BART Models for Abstractive Text Summarization in Marathi","date":"2024-10-11","arxiv_id":"2410.09184","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-for-medical-osce","title":"Large Language Models for Medical OSCE Assessment: A Novel Approach to Transcript Analysis","date":"2024-10-11","arxiv_id":"2410.12858","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-range-named-entity-recognition-for","title":"Long Range Named Entity Recognition for Marathi Documents","date":"2024-10-11","arxiv_id":"2410.09192","n_code_links":0,"syntology":null},{"paper":null,"slug":"observing-the-southern-us-culture-of-honor","title":"Observing the Southern US Culture of Honor Using Large-Scale Social Media Analysis","date":"2024-10-11","arxiv_id":"2410.13887","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimized-biomedical-question-answering","title":"Optimized Biomedical Question-Answering Services with LLM and Multi-BERT Integration","date":"2024-10-11","arxiv_id":"2410.12856","n_code_links":0,"syntology":null},{"paper":null,"slug":"oretrieval-augmented-generation-for-10-large","title":"oRetrieval Augmented Generation for 10 Large Language Models and its Generalizability in Assessing Medical Fitness","date":"2024-10-11","arxiv_id":"2410.08431","n_code_links":0,"syntology":null},{"paper":"/paper/plddt-predictor-high-speed-protein-screening","slug":"plddt-predictor-high-speed-protein-screening","title":"pLDDT-Predictor: High-speed Protein Screening Using Transformer and ESM2","date":"2024-10-11","arxiv_id":"2410.21283","n_code_links":1,"syntology":null},{"paper":"/paper/retriever-and-memory-towards-adaptive-note","slug":"retriever-and-memory-towards-adaptive-note","title":"Retriever-and-Memory: Towards Adaptive Note-Enhanced Retrieval-Augmented Generation","date":"2024-10-11","arxiv_id":"2410.08821","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"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":["thunlp/adaptive-note"],"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":null,"slug":"scaling-gaussian-processes-for-learning-curve","title":"Scaling Gaussian Processes for Learning Curve Prediction via Latent Kronecker Structure","date":"2024-10-11","arxiv_id":"2410.09239","n_code_links":0,"syntology":null},{"paper":"/paper/socialgaze-improving-the-integration-of-human","slug":"socialgaze-improving-the-integration-of-human","title":"SocialGaze: Improving the Integration of Human Social Norms in Large Language Models","date":"2024-10-11","arxiv_id":"2410.08698","n_code_links":1,"syntology":null},{"paper":"/paper/structrag-boosting-knowledge-intensive","slug":"structrag-boosting-knowledge-intensive","title":"StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization","date":"2024-10-11","arxiv_id":"2410.08815","n_code_links":1,"syntology":null},{"paper":"/paper/supercorrect-supervising-and-correcting","slug":"supercorrect-supervising-and-correcting","title":"SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights","date":"2024-10-11","arxiv_id":"2410.09008","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["yangling0818/supercorrect-llm"],"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/synth-sonar-sonar-image-synthesis-with","slug":"synth-sonar-sonar-image-synthesis-with","title":"Synth-SONAR: Sonar Image Synthesis with Enhanced Diversity and Realism via Dual Diffusion Models and GPT Prompting","date":"2024-10-11","arxiv_id":"2410.08612","n_code_links":1,"syntology":null},{"paper":null,"slug":"vit3d-alignment-of-llama3-3d-medical-image","title":"ViT3D Alignment of LLaMA3: 3D Medical Image Report Generation","date":"2024-10-11","arxiv_id":"2410.08588","n_code_links":0,"syntology":null},{"paper":"/paper/adam-exploits-ell-infty-geometry-of-loss","slug":"adam-exploits-ell-infty-geometry-of-loss","title":"Adam Exploits $\\ell_\\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity","date":"2024-10-10","arxiv_id":"2410.08198","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":6,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"7 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["mohamad-amin/adam-coordinate-adaptivity"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/benchmarking-agentic-workflow-generation","slug":"benchmarking-agentic-workflow-generation","title":"Benchmarking Agentic Workflow Generation","date":"2024-10-10","arxiv_id":"2410.07869","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zjunlp/worfbench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"can-looped-transformers-learn-to-implement","title":"Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?","date":"2024-10-10","arxiv_id":"2410.08292","n_code_links":0,"syntology":null},{"paper":null,"slug":"dice-discrete-inversion-enabling-controllable","title":"DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models","date":"2024-10-10","arxiv_id":"2410.08207","n_code_links":0,"syntology":null},{"paper":null,"slug":"diversity-of-thought-elicits-stronger","title":"Diversity of Thought Elicits Stronger Reasoning Capabilities in Multi-Agent Debate Frameworks","date":"2024-10-10","arxiv_id":"2410.12853","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-you-know-what-you-are-talking-about","title":"Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation","date":"2024-10-10","arxiv_id":"2410.08320","n_code_links":0,"syntology":null},{"paper":"/paper/explainability-of-deep-neural-networks-for","slug":"explainability-of-deep-neural-networks-for","title":"Explainability of Deep Neural Networks for Brain Tumor Detection","date":"2024-10-10","arxiv_id":"2410.07613","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-language-models-for-ethical","title":"Fine-Tuning Language Models for Ethical Ambiguity: A Comparative Study of Alignment with Human Responses","date":"2024-10-10","arxiv_id":"2410.07826","n_code_links":0,"syntology":null},{"paper":null,"slug":"flier-few-shot-language-image-models-embedded","title":"FLIER: Few-shot Language Image Models Embedded with Latent Representations","date":"2024-10-10","arxiv_id":"2410.07648","n_code_links":0,"syntology":null},{"paper":null,"slug":"icediff-high-resolution-and-high-quality-sea","title":"IceDiff: High Resolution and High-Quality Sea Ice Forecasting with Generative Diffusion Prior","date":"2024-10-10","arxiv_id":"2410.09111","n_code_links":0,"syntology":null},{"paper":null,"slug":"news-reporter-a-multi-lingual-llm-framework","title":"News Reporter: A Multi-lingual LLM Framework for Broadcast T.V News","date":"2024-10-10","arxiv_id":"2410.07520","n_code_links":0,"syntology":null},{"paper":null,"slug":"no-free-lunch-retrieval-augmented-generation","title":"No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users","date":"2024-10-10","arxiv_id":"2410.07589","n_code_links":0,"syntology":null},{"paper":null,"slug":"offline-inverse-constrained-reinforcement","title":"Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare","date":"2024-10-10","arxiv_id":"2410.07525","n_code_links":0,"syntology":null},{"paper":null,"slug":"plamo-100b-a-ground-up-language-model","title":"PLaMo-100B: A Ground-Up Language Model Designed for Japanese Proficiency","date":"2024-10-10","arxiv_id":"2410.07563","n_code_links":0,"syntology":null},{"paper":"/paper/pretraining-graph-transformers-with-atom-in-a","slug":"pretraining-graph-transformers-with-atom-in-a","title":"Pretraining Graph Transformers with Atom-in-a-Molecule Quantum Properties for Improved ADMET Modeling","date":"2024-10-10","arxiv_id":"2410.08024","n_code_links":1,"syntology":null},{"paper":"/paper/privately-learning-from-graphs-with","slug":"privately-learning-from-graphs-with","title":"Privately Learning from Graphs with Applications in Fine-tuning Large Language Models","date":"2024-10-10","arxiv_id":"2410.08299","n_code_links":1,"syntology":null},{"paper":null,"slug":"prompt-engineering-a-schizophrenia-chatbot","title":"Prompt Engineering a Schizophrenia Chatbot: Utilizing a Multi-Agent Approach for Enhanced Compliance with Prompt Instructions","date":"2024-10-10","arxiv_id":"2410.12848","n_code_links":0,"syntology":null},{"paper":"/paper/rdt-1b-a-diffusion-foundation-model-for","slug":"rdt-1b-a-diffusion-foundation-model-for","title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","date":"2024-10-10","arxiv_id":"2410.07864","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["thu-ml/RoboticsDiffusionTransformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"reducing-the-cost-of-dropout-in-flash","title":"Reducing the Cost of Dropout in Flash-Attention by Hiding RNG with GEMM","date":"2024-10-10","arxiv_id":"2410.07531","n_code_links":0,"syntology":null},{"paper":null,"slug":"rescriber-smaller-llm-powered-user-led-data","title":"Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbots","date":"2024-10-10","arxiv_id":"2410.11876","n_code_links":0,"syntology":null},{"paper":"/paper/robust-ai-generated-text-detection-by","slug":"robust-ai-generated-text-detection-by","title":"Robust AI-Generated Text Detection by Restricted Embeddings","date":"2024-10-10","arxiv_id":"2410.08113","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["silversolver/robustatd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"semv-3d-towards-semantic-and-mutil-view","title":"SeMv-3D: Towards Concurrency of Semantic and Multi-view Consistency in General Text-to-3D Generation","date":"2024-10-10","arxiv_id":"2410.07658","n_code_links":0,"syntology":null},{"paper":"/paper/snn-par-energy-efficient-pedestrian-attribute","slug":"snn-par-energy-efficient-pedestrian-attribute","title":"SNN-PAR: Energy Efficient Pedestrian Attribute Recognition via Spiking Neural Networks","date":"2024-10-10","arxiv_id":"2410.07857","n_code_links":1,"syntology":null},{"paper":"/paper/spa-3d-spatial-awareness-enables-effective","slug":"spa-3d-spatial-awareness-enables-effective","title":"SPA: 3D Spatial-Awareness Enables Effective Embodied Representation","date":"2024-10-10","arxiv_id":"2410.08208","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["haoyizhu/realrobot"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/teaching-inspired-integrated-prompting","slug":"teaching-inspired-integrated-prompting","title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","date":"2024-10-10","arxiv_id":"2410.08068","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sallytan13/teaching-inspired-prompting"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-rise-of-ai-generated-content-in-wikipedia","slug":"the-rise-of-ai-generated-content-in-wikipedia","title":"The Rise of AI-Generated Content in Wikipedia","date":"2024-10-10","arxiv_id":"2410.08044","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["brooksca3/wiki_collection"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"theoretical-limits-of-descending-ell-0-sparse","title":"Theoretical limits of descending $\\ell_0$ sparse-regression ML algorithms","date":"2024-10-10","arxiv_id":"2410.07651","n_code_links":0,"syntology":null},{"paper":null,"slug":"think-beyond-size-dynamic-prompting-for-more","title":"Think Beyond Size: Adaptive Prompting for More Effective Reasoning","date":"2024-10-10","arxiv_id":"2410.08130","n_code_links":0,"syntology":null},{"paper":"/paper/thought2text-text-generation-from-eeg-signal","slug":"thought2text-text-generation-from-eeg-signal","title":"Thought2Text: Text Generation from EEG Signal using Large Language Models (LLMs)","date":"2024-10-10","arxiv_id":"2410.07507","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":["abhijitmishra/Thought2Text"],"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/turborag-accelerating-retrieval-augmented","slug":"turborag-accelerating-retrieval-augmented","title":"TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text","date":"2024-10-10","arxiv_id":"2410.07590","n_code_links":1,"syntology":null},{"paper":"/paper/vibecheck-discover-and-quantify-qualitative","slug":"vibecheck-discover-and-quantify-qualitative","title":"VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models","date":"2024-10-10","arxiv_id":"2410.12851","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":10,"n_instrument":0,"unverified":2,"pointer_only":12,"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) · 2 unverified","official":{"repos":["lisadunlap/vibecheck"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-two-model-approach-for-humour-style","slug":"a-two-model-approach-for-humour-style","title":"A Two-Model Approach for Humour Style Recognition","date":"2024-10-09","arxiv_id":"2410.12842","n_code_links":1,"syntology":null},{"paper":"/paper/adaptive-high-frequency-transformer-for","slug":"adaptive-high-frequency-transformer-for","title":"Adaptive High-Frequency Transformer for Diverse Wildlife Re-Identification","date":"2024-10-09","arxiv_id":"2410.06977","n_code_links":1,"syntology":null},{"paper":null,"slug":"astute-rag-overcoming-imperfect-retrieval","title":"Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models","date":"2024-10-09","arxiv_id":"2410.07176","n_code_links":0,"syntology":null},{"paper":null,"slug":"autofeedback-an-llm-based-framework-for","title":"AutoFeedback: An LLM-based Framework for Efficient and Accurate API Request Generation","date":"2024-10-09","arxiv_id":"2410.06943","n_code_links":0,"syntology":null},{"paper":"/paper/bridge-the-points-graph-based-few-shot","slug":"bridge-the-points-graph-based-few-shot","title":"Bridge the Points: Graph-based Few-shot Segment Anything Semantically","date":"2024-10-09","arxiv_id":"2410.06964","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ANDYZAQ/GF-SAM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"can-transformers-reason-logically-a-study-in","title":"Can Transformers Reason Logically? A Study in SAT Solving","date":"2024-10-09","arxiv_id":"2410.07432","n_code_links":0,"syntology":null},{"paper":null,"slug":"capturing-bias-diversity-in-llms","title":"Capturing Bias Diversity in LLMs","date":"2024-10-09","arxiv_id":"2410.12839","n_code_links":0,"syntology":null},{"paper":"/paper/cluster-wise-graph-transformer-with-dual","slug":"cluster-wise-graph-transformer-with-dual","title":"Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention","date":"2024-10-09","arxiv_id":"2410.06746","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":10,"n_instrument":3,"unverified":1,"pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["lumia-group/cluster-wise-graph-transformer"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"detecting-bias-and-enhancing-diagnostic","title":"Detecting Bias and Enhancing Diagnostic Accuracy in Large Language Models for Healthcare","date":"2024-10-09","arxiv_id":"2410.06566","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-great-minds-think-alike-investigating","title":"Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA","date":"2024-10-09","arxiv_id":"2410.06524","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-training-strategies-for-natural","title":"Efficient training strategies for natural sounding speech synthesis and speaker adaptation based on FastPitch","date":"2024-10-09","arxiv_id":"2410.06787","n_code_links":0,"syntology":null},{"paper":"/paper/eta-evaluating-then-aligning-safety-of-vision","slug":"eta-evaluating-then-aligning-safety-of-vision","title":"ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time","date":"2024-10-09","arxiv_id":"2410.06625","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":6,"n_instrument":3,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["dripnowhy/eta"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/f5-tts-a-fairytaler-that-fakes-fluent-and","slug":"f5-tts-a-fairytaler-that-fakes-fluent-and","title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","date":"2024-10-09","arxiv_id":"2410.06885","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["SWivid/F5-TTS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generative-model-for-less-resourced-language","title":"Generative Model for Less-Resourced Language with 1 billion parameters","date":"2024-10-09","arxiv_id":"2410.06898","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-data-efficiency-via-curating-llm","title":"Improving Data Efficiency via Curating LLM-Driven Rating Systems","date":"2024-10-09","arxiv_id":"2410.10877","n_code_links":0,"syntology":null},{"paper":null,"slug":"instructional-segment-embedding-improving-llm","title":"Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy","date":"2024-10-09","arxiv_id":"2410.09102","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-cost-efficiency-of-llm","title":"Investigating Cost-Efficiency of LLM-Generated Training Data for Conversational Semantic Frame Analysis","date":"2024-10-09","arxiv_id":"2410.06550","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-code-executors-an","title":"Large Language Models as Code Executors: An Exploratory Study","date":"2024-10-09","arxiv_id":"2410.06667","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-self-correction-with-decrim-decompose","title":"LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints","date":"2024-10-09","arxiv_id":"2410.06458","n_code_links":0,"syntology":null},{"paper":null,"slug":"mad-scientist-ai-based-scientist-solving","title":"MaD-Scientist: AI-based Scientist solving Convection-Diffusion-Reaction Equations Using Massive PINN-Based Prior Data","date":"2024-10-09","arxiv_id":"2410.06442","n_code_links":0,"syntology":null},{"paper":"/paper/matmamba-a-matryoshka-state-space-model","slug":"matmamba-a-matryoshka-state-space-model","title":"MatMamba: A Matryoshka State Space Model","date":"2024-10-09","arxiv_id":"2410.06718","n_code_links":1,"syntology":null},{"paper":null,"slug":"mental-disorders-detection-in-the-era-of","title":"Mental Disorders Detection in the Era of Large Language Models","date":"2024-10-09","arxiv_id":"2410.07129","n_code_links":0,"syntology":null},{"paper":"/paper/mentalarena-self-play-training-of-language","slug":"mentalarena-self-play-training-of-language","title":"MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders","date":"2024-10-09","arxiv_id":"2410.06845","n_code_links":1,"syntology":null},{"paper":null,"slug":"netdiff-deep-graph-denoising-diffusion-for-ad","title":"NetDiff: Deep Graph Denoising Diffusion for Ad Hoc Network Topology Generation","date":"2024-10-09","arxiv_id":"2410.08238","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-transformer-based-on-high","title":"Optimizing Transformer based on high-performance optimizer for predicting employment sentiment in American social media content","date":"2024-10-09","arxiv_id":"2410.10874","n_code_links":0,"syntology":null},{"paper":"/paper/pair-vpr-place-aware-pre-training-and","slug":"pair-vpr-place-aware-pre-training-and","title":"Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers","date":"2024-10-09","arxiv_id":"2410.06614","n_code_links":1,"syntology":null},{"paper":"/paper/quadmamba-learning-quadtree-based-selective","slug":"quadmamba-learning-quadtree-based-selective","title":"QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model","date":"2024-10-09","arxiv_id":"2410.06806","n_code_links":1,"syntology":null},{"paper":"/paper/retrieval-augmented-decision-transformer","slug":"retrieval-augmented-decision-transformer","title":"Retrieval-Augmented Decision Transformer: External Memory for In-context RL","date":"2024-10-09","arxiv_id":"2410.07071","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/RA-DT"],"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":null,"slug":"sage-scalable-ground-truth-evaluations-for","title":"SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders","date":"2024-10-09","arxiv_id":"2410.07456","n_code_links":0,"syntology":null}],"record_sha256":"538d2dfa7248b22871b40d4b15c093419b812b0e973ed6f0cb759fced5ac502e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}