{"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/56","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":56,"pages_in_order":249,"rows_per_page":100,"rows":[5501,5600],"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/55","next":"/method/multi-head-attention/papers/57","papers":[{"paper":null,"slug":"bctr-bidirectional-conditioning-transformer","title":"BCTR: Bidirectional Conditioning Transformer for Scene Graph Generation","date":"2024-07-26","arxiv_id":"2407.18715","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-companion-learning-enhancing","title":"Deep Companion Learning: Enhancing Generalization Through Historical Consistency","date":"2024-07-26","arxiv_id":"2407.18821","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-deciphering-fedspeak-quantifying-dissent","slug":"gpt-deciphering-fedspeak-quantifying-dissent","title":"GPT Deciphering Fedspeak: Quantifying Dissent Among Hawks and Doves","date":"2024-07-26","arxiv_id":"2407.19110","n_code_links":1,"syntology":null},{"paper":null,"slug":"human-artificial-intelligence-teaming-for","title":"Human-artificial intelligence teaming for scientific information extraction from data-driven additive manufacturing research using large language models","date":"2024-07-26","arxiv_id":"2407.18827","n_code_links":0,"syntology":null},{"paper":"/paper/is-larger-always-better-evaluating-and","slug":"is-larger-always-better-evaluating-and","title":"ClinicRealm: Re-evaluating Large Language Models with Conventional Machine Learning for Non-Generative Clinical Prediction Tasks","date":"2024-07-26","arxiv_id":"2407.18525","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":8,"phrase":"8 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yhzhu99/ehr-llm-benchmark"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mistralbsm-leveraging-mistral-7b-for","title":"MistralBSM: Leveraging Mistral-7B for Vehicular Networks Misbehavior Detection","date":"2024-07-26","arxiv_id":"2407.18462","n_code_links":0,"syntology":null},{"paper":"/paper/mixed-non-linear-quantization-for-vision","slug":"mixed-non-linear-quantization-for-vision","title":"Mixed Non-linear Quantization for Vision Transformers","date":"2024-07-26","arxiv_id":"2407.18437","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-emotion-recognition-using-audio","slug":"multimodal-emotion-recognition-using-audio","title":"Multimodal Emotion Recognition using Audio-Video Transformer Fusion with Cross Attention","date":"2024-07-26","arxiv_id":"2407.18552","n_code_links":1,"syntology":null},{"paper":"/paper/officebench-benchmarking-language-agents","slug":"officebench-benchmarking-language-agents","title":"OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation","date":"2024-07-26","arxiv_id":"2407.19056","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":["zlwang-cs/OfficeBench"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"qt-tdm-planning-with-transformer-dynamics","title":"QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-Learning","date":"2024-07-26","arxiv_id":"2407.18841","n_code_links":0,"syntology":null},{"paper":null,"slug":"reaper-reasoning-based-retrieval-planning-for","title":"REAPER: Reasoning based Retrieval Planning for Complex RAG Systems","date":"2024-07-26","arxiv_id":"2407.18553","n_code_links":0,"syntology":null},{"paper":null,"slug":"shic-shape-image-correspondences-with-no","title":"SHIC: Shape-Image Correspondences with no Keypoint Supervision","date":"2024-07-26","arxiv_id":"2407.18907","n_code_links":0,"syntology":null},{"paper":null,"slug":"skin-cancer-detection-utilizing-deep-learning","title":"Skin Cancer Detection utilizing Deep Learning: Classification of Skin Lesion Images using a Vision Transformer","date":"2024-07-26","arxiv_id":"2407.18554","n_code_links":0,"syntology":null},{"paper":null,"slug":"tagify-llm-powered-tagging-interface-for","title":"TAGIFY: LLM-powered Tagging Interface for Improved Data Findability on OGD portals","date":"2024-07-26","arxiv_id":"2407.18764","n_code_links":0,"syntology":null},{"paper":"/paper/towards-a-transformer-based-pre-trained-model","slug":"towards-a-transformer-based-pre-trained-model","title":"Towards a Transformer-Based Pre-trained Model for IoT Traffic Classification","date":"2024-07-26","arxiv_id":"2407.19051","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-gpt-4-to-guide-causal-machine-learning","title":"Using GPT-4 to guide causal machine learning","date":"2024-07-26","arxiv_id":"2407.18607","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-for-the","title":"Using Large Language Models for the Interpretation of Building Regulations","date":"2024-07-26","arxiv_id":"2407.21060","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-robust-decision-transformer","slug":"adversarial-robust-decision-transformer","title":"Adversarially Robust Decision Transformer","date":"2024-07-25","arxiv_id":"2407.18414","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":["xiaohangt/ardt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"banyan-improved-representation-learning-with","title":"Banyan: Improved Representation Learning with Explicit Structure","date":"2024-07-25","arxiv_id":"2407.17771","n_code_links":0,"syntology":null},{"paper":null,"slug":"closing-the-gap-between-open-source-and","title":"Closing the gap between open-source and commercial large language models for medical evidence summarization","date":"2024-07-25","arxiv_id":"2408.00588","n_code_links":0,"syntology":null},{"paper":"/paper/cost-effective-instruction-learning-for","slug":"cost-effective-instruction-learning-for","title":"Cost-effective Instruction Learning for Pathology Vision and Language Analysis","date":"2024-07-25","arxiv_id":"2407.17734","n_code_links":1,"syntology":null},{"paper":"/paper/cswin-unet-transformer-unet-with-cross-shaped","slug":"cswin-unet-transformer-unet-with-cross-shaped","title":"CSWin-UNet: Transformer UNet with Cross-Shaped Windows for Medical Image Segmentation","date":"2024-07-25","arxiv_id":"2407.18070","n_code_links":1,"syntology":null},{"paper":"/paper/detection-of-manatee-vocalisations-using-the","slug":"detection-of-manatee-vocalisations-using-the","title":"Detection of manatee vocalisations using the Audio Spectrogram Transformer","date":"2024-07-25","arxiv_id":"2407.18083","n_code_links":1,"syntology":null},{"paper":null,"slug":"hg-pipe-vision-transformer-acceleration-with","title":"HG-PIPE: Vision Transformer Acceleration with Hybrid-Grained Pipeline","date":"2024-07-25","arxiv_id":"2407.17879","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-the-digital-forensics-and-incident","title":"Is the Digital Forensics and Incident Response Pipeline Ready for Text-Based Threats in LLM Era?","date":"2024-07-25","arxiv_id":"2407.17870","n_code_links":0,"syntology":null},{"paper":null,"slug":"keep-the-cost-down-a-review-on-methods-to","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","date":"2024-07-25","arxiv_id":"2407.18003","n_code_links":0,"syntology":null},{"paper":"/paper/peft-u-parameter-efficient-fine-tuning-for","slug":"peft-u-parameter-efficient-fine-tuning-for","title":"PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization","date":"2024-07-25","arxiv_id":"2407.18078","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 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) · 2 unverified","official":{"repos":["ChrisIsKing/Parameter-Efficient-Personalization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/personagym-evaluating-persona-agents-and-llms","slug":"personagym-evaluating-persona-agents-and-llms","title":"PersonaGym: Evaluating Persona Agents and LLMs","date":"2024-07-25","arxiv_id":"2407.18416","n_code_links":1,"syntology":null},{"paper":"/paper/positive-text-reframing-under-multi-strategy","slug":"positive-text-reframing-under-multi-strategy","title":"Positive Text Reframing under Multi-strategy Optimization","date":"2024-07-25","arxiv_id":"2407.17940","n_code_links":1,"syntology":null},{"paper":null,"slug":"roberta-resnext-and-bilstm-with-self","title":"RoBERTa, ResNeXt and BiLSTM with self-attention: The ultimate trio for customer sentiment analysis","date":"2024-07-25","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/self-training-with-direct-preference","slug":"self-training-with-direct-preference","title":"Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning","date":"2024-07-25","arxiv_id":"2407.18248","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tianduowang/dpo-st"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-geometry-of-queries-query-based","title":"The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation","date":"2024-07-25","arxiv_id":"2407.18044","n_code_links":0,"syntology":null},{"paper":null,"slug":"trajectory-aligned-space-time-tokens-for-few","title":"Trajectory-aligned Space-time Tokens for Few-shot Action Recognition","date":"2024-07-25","arxiv_id":"2407.18249","n_code_links":0,"syntology":null},{"paper":null,"slug":"trust-or-escalate-llm-judges-with-provable","title":"Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement","date":"2024-07-25","arxiv_id":"2407.18370","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-the-interplay-of-scale-data-and","title":"Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT","date":"2024-07-25","arxiv_id":"2407.21058","n_code_links":0,"syntology":null},{"paper":null,"slug":"2407-21056","title":"What Matters in Explanations: Towards Explainable Fake Review Detection Focusing on Transformers","date":"2024-07-24","arxiv_id":"2407.21056","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-approach-to-misspelling","title":"A Comprehensive Approach to Misspelling Correction with BERT and Levenshtein Distance","date":"2024-07-24","arxiv_id":"2407.17383","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-two-step-fine-tuning-pipeline-for","title":"A Novel Two-Step Fine-Tuning Pipeline for Cold-Start Active Learning in Text Classification Tasks","date":"2024-07-24","arxiv_id":"2407.17284","n_code_links":0,"syntology":null},{"paper":null,"slug":"bailicai-a-domain-optimized-retrieval","title":"Bailicai: A Domain-Optimized Retrieval-Augmented Generation Framework for Medical Applications","date":"2024-07-24","arxiv_id":"2407.21055","n_code_links":0,"syntology":null},{"paper":"/paper/case-enhanced-vision-transformer-improving","slug":"case-enhanced-vision-transformer-improving","title":"Case-Enhanced Vision Transformer: Improving Explanations of Image Similarity with a ViT-based Similarity Metric","date":"2024-07-24","arxiv_id":"2407.16981","n_code_links":1,"syntology":null},{"paper":"/paper/dependency-transformer-grammars-integrating","slug":"dependency-transformer-grammars-integrating","title":"Dependency Transformer Grammars: Integrating Dependency Structures into Transformer Language Models","date":"2024-07-24","arxiv_id":"2407.17406","n_code_links":1,"syntology":null},{"paper":null,"slug":"domain-generalized-recaptured-screen-image","title":"Domain Generalized Recaptured Screen Image Identification Using SWIN Transformer","date":"2024-07-24","arxiv_id":"2407.17170","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-graph-transformer-with-correlated","slug":"dynamic-graph-transformer-with-correlated","title":"Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding","date":"2024-07-24","arxiv_id":"2407.16959","n_code_links":1,"syntology":null},{"paper":"/paper/embedding-free-transformer-with-inference","slug":"embedding-free-transformer-with-inference","title":"Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation","date":"2024-07-24","arxiv_id":"2407.17261","n_code_links":1,"syntology":null},{"paper":"/paper/graph-neural-networks-a-suitable-alternative","slug":"graph-neural-networks-a-suitable-alternative","title":"Graph Neural Networks: A suitable Alternative to MLPs in Latent 3D Medical Image Classification?","date":"2024-07-24","arxiv_id":"2407.17219","n_code_links":1,"syntology":null},{"paper":"/paper/i-could-ve-asked-that-reformulating","slug":"i-could-ve-asked-that-reformulating","title":"I Could've Asked That: Reformulating Unanswerable Questions","date":"2024-07-24","arxiv_id":"2407.17469","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-icd-coding-using-chapter-based","title":"Improving ICD coding using Chapter based Named Entities and Attentional Models","date":"2024-07-24","arxiv_id":"2407.17230","n_code_links":0,"syntology":null},{"paper":"/paper/loformer-local-frequency-transformer-for","slug":"loformer-local-frequency-transformer-for","title":"LoFormer: Local Frequency Transformer for Image Deblurring","date":"2024-07-24","arxiv_id":"2407.16993","n_code_links":2,"syntology":null},{"paper":"/paper/must-multi-scale-transformers-for-surgical","slug":"must-multi-scale-transformers-for-surgical","title":"MuST: Multi-Scale Transformers for Surgical Phase Recognition","date":"2024-07-24","arxiv_id":"2407.17361","n_code_links":1,"syntology":null},{"paper":null,"slug":"reporting-and-analysing-the-environmental","title":"Reporting and Analysing the Environmental Impact of Language Models on the Example of Commonsense Question Answering with External Knowledge","date":"2024-07-24","arxiv_id":"2408.01453","n_code_links":0,"syntology":null},{"paper":null,"slug":"testing-large-language-models-on-driving","title":"Testing Large Language Models on Driving Theory Knowledge and Skills for Connected Autonomous Vehicles","date":"2024-07-24","arxiv_id":"2407.17211","n_code_links":0,"syntology":null},{"paper":"/paper/trans2unet-neural-fusion-for-nuclei-semantic","slug":"trans2unet-neural-fusion-for-nuclei-semantic","title":"Trans2Unet: Neural fusion for Nuclei Semantic Segmentation","date":"2024-07-24","arxiv_id":"2407.17181","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-the-polysemy-evolution-using","title":"Analyzing Polysemy Evolution Using Semantic Cells","date":"2024-07-23","arxiv_id":"2407.16110","n_code_links":0,"syntology":null},{"paper":null,"slug":"artificial-intelligence-in-extracting","title":"Artificial Intelligence in Extracting Diagnostic Data from Dental Records","date":"2024-07-23","arxiv_id":"2407.21050","n_code_links":0,"syntology":null},{"paper":"/paper/channel-partitioned-windowed-attention-and","slug":"channel-partitioned-windowed-attention-and","title":"Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution","date":"2024-07-23","arxiv_id":"2407.16232","n_code_links":0,"syntology":null},{"paper":"/paper/data-mixture-inference-what-do-bpe-tokenizers","slug":"data-mixture-inference-what-do-bpe-tokenizers","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","date":"2024-07-23","arxiv_id":"2407.16607","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":["alisawuffles/tokenizer-attack"],"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":"diffusion-transformer-captures-spatial","title":"Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data","date":"2024-07-23","arxiv_id":"2407.16134","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-llms-know-when-to-not-answer-investigating","title":"Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models","date":"2024-07-23","arxiv_id":"2407.16221","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-llm-s-cognition-via-structurization","slug":"enhancing-llm-s-cognition-via-structurization","title":"Enhancing LLM's Cognition via Structurization","date":"2024-07-23","arxiv_id":"2407.16434","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["alibaba/struxgpt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-the-neural-burden-in-pruned-models","title":"Exploring The Neural Burden In Pruned Models: An Insight Inspired By Neuroscience","date":"2024-07-23","arxiv_id":"2407.16716","n_code_links":0,"syntology":null},{"paper":null,"slug":"hsvlt-hierarchical-scale-aware-vision","title":"HSVLT: Hierarchical Scale-Aware Vision-Language Transformer for Multi-Label Image Classification","date":"2024-07-23","arxiv_id":"2407.16244","n_code_links":0,"syntology":null},{"paper":"/paper/hytas-a-hyperspectral-image-transformer","slug":"hytas-a-hyperspectral-image-transformer","title":"HyTAS: A Hyperspectral Image Transformer Architecture Search Benchmark and Analysis","date":"2024-07-23","arxiv_id":"2407.16269","n_code_links":1,"syntology":null},{"paper":null,"slug":"lawluo-a-chinese-law-firm-co-run-by-llm","title":"LawLuo: A Multi-Agent Collaborative Framework for Multi-Round Chinese Legal Consultation","date":"2024-07-23","arxiv_id":"2407.16252","n_code_links":0,"syntology":null},{"paper":"/paper/lawma-the-power-of-specialization-for-legal","slug":"lawma-the-power-of-specialization-for-legal","title":"Lawma: The Power of Specialization for Legal Tasks","date":"2024-07-23","arxiv_id":"2407.16615","n_code_links":0,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"masked-graph-learning-with-recurrent","title":"Masked Graph Learning with Recurrent Alignment for Multimodal Emotion Recognition in Conversation","date":"2024-07-23","arxiv_id":"2407.16714","n_code_links":0,"syntology":null},{"paper":"/paper/origen-enhancing-rtl-code-generation-with","slug":"origen-enhancing-rtl-code-generation-with","title":"OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflection","date":"2024-07-23","arxiv_id":"2407.16237","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":3,"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":["pku-liang/origen"],"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":"/paper/patched-rtc-evaluating-llms-for-diverse","slug":"patched-rtc-evaluating-llms-for-diverse","title":"Patched RTC: evaluating LLMs for diverse software development tasks","date":"2024-07-23","arxiv_id":"2407.16557","n_code_links":1,"syntology":null},{"paper":null,"slug":"redagent-red-teaming-large-language-models","title":"RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent","date":"2024-07-23","arxiv_id":"2407.16667","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-or-long","title":"Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach","date":"2024-07-23","arxiv_id":"2407.16833","n_code_links":0,"syntology":null},{"paper":"/paper/robust-privacy-amidst-innovation-with-large","slug":"robust-privacy-amidst-innovation-with-large","title":"Robust Privacy Amidst Innovation with Large Language Models Through a Critical Assessment of the Risks","date":"2024-07-23","arxiv_id":"2407.16166","n_code_links":1,"syntology":null},{"paper":null,"slug":"s-e-pipeline-a-vision-transformer-vit-based","title":"S-E Pipeline: A Vision Transformer (ViT) based Resilient Classification Pipeline for Medical Imaging Against Adversarial Attacks","date":"2024-07-23","arxiv_id":"2407.17587","n_code_links":0,"syntology":null},{"paper":"/paper/sinder-repairing-the-singular-defects-of","slug":"sinder-repairing-the-singular-defects-of","title":"SINDER: Repairing the Singular Defects of DINOv2","date":"2024-07-23","arxiv_id":"2407.16826","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":["haoqiwang/sinder"],"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":"synthesizer-sound-matching-using-audio","title":"Synthesizer Sound Matching Using Audio Spectrogram Transformers","date":"2024-07-23","arxiv_id":"2407.16643","n_code_links":0,"syntology":null},{"paper":null,"slug":"tookabert-a-step-forward-for-persian-nlu","title":"TookaBERT: A Step Forward for Persian NLU","date":"2024-07-23","arxiv_id":"2407.16382","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-comparison-of-video-frame","title":"An Empirical Comparison of Video Frame Sampling Methods for Multi-Modal RAG Retrieval","date":"2024-07-22","arxiv_id":"2408.03340","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-gpt-4-learn-to-analyze-moves-in-research","title":"Can GPT-4 learn to analyse moves in research article abstracts?","date":"2024-07-22","arxiv_id":"2407.15612","n_code_links":0,"syntology":null},{"paper":null,"slug":"customized-retrieval-augmented-generation-and","title":"Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QA","date":"2024-07-22","arxiv_id":"2407.15353","n_code_links":0,"syntology":null},{"paper":"/paper/dissecting-multiplication-in-transformers","slug":"dissecting-multiplication-in-transformers","title":"Dissecting Multiplication in Transformers: Insights into LLMs","date":"2024-07-22","arxiv_id":"2407.15360","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-multi-disparity-transformer-for","title":"Efficient Multi-disparity Transformer for Light Field Image Super-resolution","date":"2024-07-22","arxiv_id":"2407.15329","n_code_links":0,"syntology":null},{"paper":"/paper/estimating-probability-densities-with","slug":"estimating-probability-densities-with","title":"Estimating Probability Densities with Transformer and Denoising Diffusion","date":"2024-07-22","arxiv_id":"2407.15703","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["henrysky/stars_foundation_diffusion"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"impacts-of-anthropomorphizing-large-language","title":"Impacts of Anthropomorphizing Large Language Models in Learning Environments","date":"2024-07-22","arxiv_id":"2408.03945","n_code_links":0,"syntology":null},{"paper":null,"slug":"imposter-ai-adversarial-attacks-with-hidden","title":"Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned Large Language Models","date":"2024-07-22","arxiv_id":"2407.15399","n_code_links":0,"syntology":null},{"paper":"/paper/inverted-activations","slug":"inverted-activations","title":"Inverted Activations: Reducing Memory Footprint in Neural Network Training","date":"2024-07-22","arxiv_id":"2407.15545","n_code_links":1,"syntology":null},{"paper":null,"slug":"kwt-tiny-risc-v-accelerated-embedded-keyword","title":"KWT-Tiny: RISC-V Accelerated, Embedded Keyword Spotting Transformer","date":"2024-07-22","arxiv_id":"2407.16026","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-manipulate-anywhere-a-visual","title":"Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning","date":"2024-07-22","arxiv_id":"2407.15815","n_code_links":0,"syntology":null},{"paper":"/paper/llmmap-fingerprinting-for-large-language","slug":"llmmap-fingerprinting-for-large-language","title":"LLMmap: Fingerprinting For Large Language Models","date":"2024-07-22","arxiv_id":"2407.15847","n_code_links":1,"syntology":{"ran":9,"of":16,"n_ran_checked":9,"n_instrument":0,"unverified":7,"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) · 7 unverified","official":{"repos":["pasquini-dario/LLMmap"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/local-all-pair-correspondence-for-point","slug":"local-all-pair-correspondence-for-point","title":"Local All-Pair Correspondence for Point Tracking","date":"2024-07-22","arxiv_id":"2407.15420","n_code_links":2,"syntology":{"ran":8,"of":12,"n_ran_checked":8,"n_instrument":0,"unverified":4,"pointer_only":2,"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) · 4 unverified","official":{"repos":["cvlab-kaist/locotrack"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/mini-sequence-transformer-optimizing","slug":"mini-sequence-transformer-optimizing","title":"Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training","date":"2024-07-22","arxiv_id":"2407.15892","n_code_links":1,"syntology":null},{"paper":"/paper/mminstruct-a-high-quality-multi-modal","slug":"mminstruct-a-high-quality-multi-modal","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","date":"2024-07-22","arxiv_id":"2407.15838","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":["yuecao0119/mminstruct"],"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":null,"slug":"morse-bridging-the-gap-in-cybersecurity","title":"MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generation","date":"2024-07-22","arxiv_id":"2407.15748","n_code_links":0,"syntology":null},{"paper":null,"slug":"nv-retriever-improving-text-embedding-models","title":"NV-Retriever: Improving text embedding models with effective hard-negative mining","date":"2024-07-22","arxiv_id":"2407.15831","n_code_links":0,"syntology":null},{"paper":"/paper/predicting-the-best-of-n-visual-trackers","slug":"predicting-the-best-of-n-visual-trackers","title":"Predicting the Best of N Visual Trackers","date":"2024-07-22","arxiv_id":"2407.15707","n_code_links":1,"syntology":null},{"paper":"/paper/promises-and-pitfalls-of-generative-masked","slug":"promises-and-pitfalls-of-generative-masked","title":"Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines","date":"2024-07-22","arxiv_id":"2407.21046","n_code_links":1,"syntology":null},{"paper":"/paper/radiorag-factual-large-language-models-for","slug":"radiorag-factual-large-language-models-for","title":"RadioRAG: Factual large language models for enhanced diagnostics in radiology using online retrieval augmented generation","date":"2024-07-22","arxiv_id":"2407.15621","n_code_links":1,"syntology":null},{"paper":"/paper/stretching-each-dollar-diffusion-training","slug":"stretching-each-dollar-diffusion-training","title":"Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget","date":"2024-07-22","arxiv_id":"2407.15811","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":["sonyresearch/micro_diffusion"],"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":"unlocking-the-potential-benchmarking-large","title":"Unlocking the Potential: Benchmarking Large Language Models in Water Engineering and Research","date":"2024-07-22","arxiv_id":"2407.21045","n_code_links":0,"syntology":null},{"paper":null,"slug":"zzu-nlp-at-sighan-2024-dimabsa-task-aspect","title":"ZZU-NLP at SIGHAN-2024 dimABSA Task: Aspect-Based Sentiment Analysis with Coarse-to-Fine In-context Learning","date":"2024-07-22","arxiv_id":"2407.15341","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-level-multi-label-text-classification","title":"A multi-level multi-label text classification dataset of 19th century Ottoman and Russian literary and critical texts","date":"2024-07-21","arxiv_id":"2407.15136","n_code_links":0,"syntology":null},{"paper":null,"slug":"arondight-red-teaming-large-vision-language","title":"Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts","date":"2024-07-21","arxiv_id":"2407.15050","n_code_links":0,"syntology":null},{"paper":"/paper/decoding-multilingual-moral-preferences","slug":"decoding-multilingual-moral-preferences","title":"Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment","date":"2024-07-21","arxiv_id":"2407.15184","n_code_links":1,"syntology":null}],"record_sha256":"2515a5528a64e7cae70f0765b27be898e86c5a548ad4b79747024274f190e7fb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}