{"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/63","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":63,"pages_in_order":249,"rows_per_page":100,"rows":[6201,6300],"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/62","next":"/method/multi-head-attention/papers/64","papers":[{"paper":"/paper/soft-masked-mamba-diffusion-model-for-ct-to","slug":"soft-masked-mamba-diffusion-model-for-ct-to","title":"Soft Masked Mamba Diffusion Model for CT to MRI Conversion","date":"2024-06-22","arxiv_id":"2406.15910","n_code_links":1,"syntology":null},{"paper":"/paper/ss-bench-a-benchmark-for-social-story","slug":"ss-bench-a-benchmark-for-social-story","title":"SS-GEN: A Social Story Generation Framework with Large Language Models","date":"2024-06-22","arxiv_id":"2406.15695","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-gpt-based-code-review-system-for","title":"A GPT-based Code Review System for Programming Language Learning","date":"2024-06-21","arxiv_id":"2407.04722","n_code_links":0,"syntology":null},{"paper":"/paper/a-smart-mnemonic-sounds-like-glue-tonic","slug":"a-smart-mnemonic-sounds-like-glue-tonic","title":"A SMART Mnemonic Sounds like \"Glue Tonic\": Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick","date":"2024-06-21","arxiv_id":"2406.15352","n_code_links":1,"syntology":null},{"paper":"/paper/a-tale-of-trust-and-accuracy-base-vs-instruct","slug":"a-tale-of-trust-and-accuracy-base-vs-instruct","title":"A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems","date":"2024-06-21","arxiv_id":"2406.14972","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-self-supervised-consistency-guided","title":"Self-Supervised Adversarial Diffusion Models for Fast MRI Reconstruction","date":"2024-06-21","arxiv_id":"2406.15656","n_code_links":0,"syntology":null},{"paper":null,"slug":"anime-popularity-prediction-before-huge","title":"Anime Popularity Prediction Before Huge Investments: a Multimodal Approach Using Deep Learning","date":"2024-06-21","arxiv_id":"2406.16961","n_code_links":0,"syntology":null},{"paper":"/paper/brain-like-language-processing-via-a-shallow","slug":"brain-like-language-processing-via-a-shallow","title":"Brain-Like Language Processing via a Shallow Untrained Multihead Attention Network","date":"2024-06-21","arxiv_id":"2406.15109","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-efficient-evaluation-of-large-language","title":"Data Efficient Evaluation of Large Language Models and Text-to-Image Models via Adaptive Sampling","date":"2024-06-21","arxiv_id":"2406.15527","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-continual-pre-training-by","title":"Efficient Continual Pre-training by Mitigating the Stability Gap","date":"2024-06-21","arxiv_id":"2406.14833","n_code_links":0,"syntology":null},{"paper":"/paper/esc-eval-evaluating-emotion-support","slug":"esc-eval-evaluating-emotion-support","title":"ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models","date":"2024-06-21","arxiv_id":"2406.14952","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["aiflames/esc-eval","haidequanbu/esc-eval","smartflowai/emollm"],"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":"giusberto-a-legal-language-model-for-personal","title":"GiusBERTo: A Legal Language Model for Personal Data De-identification in Italian Court of Auditors Decisions","date":"2024-06-21","arxiv_id":"2406.15032","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-effective-is-gpt-4-turbo-in-generating","title":"How Effective is GPT-4 Turbo in Generating School-Level Questions from Textbooks Based on Bloom's Revised Taxonomy?","date":"2024-06-21","arxiv_id":"2406.15211","n_code_links":0,"syntology":null},{"paper":null,"slug":"inferring-pluggable-types-with-machine","title":"Inferring Pluggable Types with Machine Learning","date":"2024-06-21","arxiv_id":"2406.15676","n_code_links":0,"syntology":null},{"paper":"/paper/internlm-law-an-open-source-chinese-legal","slug":"internlm-law-an-open-source-chinese-legal","title":"InternLM-Law: An Open Source Chinese Legal Large Language Model","date":"2024-06-21","arxiv_id":"2406.14887","n_code_links":1,"syntology":null},{"paper":null,"slug":"longrag-enhancing-retrieval-augmented","title":"LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs","date":"2024-06-21","arxiv_id":"2406.15319","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimised-grouped-query-attention-mechanism","title":"Optimised Grouped-Query Attention Mechanism for Transformers","date":"2024-06-21","arxiv_id":"2406.14963","n_code_links":0,"syntology":null},{"paper":null,"slug":"pistis-rag-a-scalable-cascading-framework","title":"Pistis-RAG: Enhancing Retrieval-Augmented Generation with Human Feedback","date":"2024-06-21","arxiv_id":"2407.00072","n_code_links":0,"syntology":null},{"paper":null,"slug":"probabilistic-and-differentiable-wireless","title":"Differentiable and Learnable Wireless Simulation with Geometric Transformers","date":"2024-06-21","arxiv_id":"2406.14995","n_code_links":0,"syntology":null},{"paper":null,"slug":"root-cause-analysis-of-anomalies-in-5g-ran","title":"Root Cause Analysis of Anomalies in 5G RAN Using Graph Neural Network and Transformer","date":"2024-06-21","arxiv_id":"2406.15638","n_code_links":0,"syntology":null},{"paper":"/paper/sit-symmetry-invariant-transformers-for","slug":"sit-symmetry-invariant-transformers-for","title":"SiT: Symmetry-Invariant Transformers for Generalisation in Reinforcement Learning","date":"2024-06-21","arxiv_id":"2406.15025","n_code_links":1,"syntology":null},{"paper":null,"slug":"svformer-a-direct-training-spiking","title":"SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognition","date":"2024-06-21","arxiv_id":"2406.15034","n_code_links":0,"syntology":null},{"paper":"/paper/tinystyler-efficient-few-shot-text-style","slug":"tinystyler-efficient-few-shot-text-style","title":"TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings","date":"2024-06-21","arxiv_id":"2406.15586","n_code_links":1,"syntology":null},{"paper":"/paper/v-recs-a-low-cost-llm4vis-recommender-with","slug":"v-recs-a-low-cost-llm4vis-recommender-with","title":"V-RECS, a Low-Cost LLM4VIS Recommender with Explanations, Captioning and Suggestions","date":"2024-06-21","arxiv_id":"2406.15259","n_code_links":1,"syntology":null},{"paper":null,"slug":"2406-15508","title":"What Teaches Robots to Walk, Teaches Them to Trade too -- Regime Adaptive Execution using Informed Data and LLMs","date":"2024-06-20","arxiv_id":"2406.15508","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-large-language-model-outperforms-other","title":"A Large Language Model Outperforms Other Computational Approaches to the High-Throughput Phenotyping of Physician Notes","date":"2024-06-20","arxiv_id":"2406.14757","n_code_links":0,"syntology":null},{"paper":"/paper/augmenting-query-and-passage-for-retrieval","slug":"augmenting-query-and-passage-for-retrieval","title":"QPaug: Question and Passage Augmentation for Open-Domain Question Answering of LLMs","date":"2024-06-20","arxiv_id":"2406.14277","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["kmswin1/qpaug"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/automatic-labels-are-as-effective-as-manual","slug":"automatic-labels-are-as-effective-as-manual","title":"Automatic Labels are as Effective as Manual Labels in Biomedical Images Classification with Deep Learning","date":"2024-06-20","arxiv_id":"2406.14351","n_code_links":1,"syntology":null},{"paper":null,"slug":"chatgpt-as-research-scientist-probing-gpt-s","title":"ChatGPT as Research Scientist: Probing GPT's Capabilities as a Research Librarian, Research Ethicist, Data Generator and Data Predictor","date":"2024-06-20","arxiv_id":"2406.14765","n_code_links":0,"syntology":null},{"paper":null,"slug":"cmtnet-convolutional-meets-transformer","title":"CMTNet: Convolutional Meets Transformer Network for Hyperspectral Images Classification","date":"2024-06-20","arxiv_id":"2406.14080","n_code_links":0,"syntology":null},{"paper":"/paper/coderag-bench-can-retrieval-augment-code","slug":"coderag-bench-can-retrieval-augment-code","title":"CodeRAG-Bench: Can Retrieval Augment Code Generation?","date":"2024-06-20","arxiv_id":"2406.14497","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["code-rag-bench/code-rag-bench"],"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":"complexity-of-symbolic-representation-in","title":"Complexity of Symbolic Representation in Working Memory of Transformer Correlates with the Complexity of a Task","date":"2024-06-20","arxiv_id":"2406.14213","n_code_links":0,"syntology":null},{"paper":null,"slug":"cryptogpt-a-7b-model-rivaling-gpt-4-in-the","title":"CryptoGPT: a 7B model rivaling GPT-4 in the task of analyzing and classifying real-time financial news","date":"2024-06-20","arxiv_id":"2406.14039","n_code_links":0,"syntology":null},{"paper":"/paper/diras-efficient-llm-assisted-annotation-of","slug":"diras-efficient-llm-assisted-annotation-of","title":"DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation","date":"2024-06-20","arxiv_id":"2406.14162","n_code_links":1,"syntology":null},{"paper":"/paper/enhanced-bank-check-security-introducing-a","slug":"enhanced-bank-check-security-introducing-a","title":"Enhanced Bank Check Security: Introducing a Novel Dataset and Transformer-Based Approach for Detection and Verification","date":"2024-06-20","arxiv_id":"2406.14370","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-the-llm-based-robot-manipulation","title":"Enhancing the LLM-Based Robot Manipulation Through Human-Robot Collaboration","date":"2024-06-20","arxiv_id":"2406.14097","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-implicit-bias-in-large-language","slug":"evaluating-implicit-bias-in-large-language","title":"Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective","date":"2024-06-20","arxiv_id":"2406.14023","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-rag-fusion-with-ragelo-an","slug":"evaluating-rag-fusion-with-ragelo-an","title":"Evaluating RAG-Fusion with RAGElo: an Automated Elo-based Framework","date":"2024-06-20","arxiv_id":"2406.14783","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["zetaalphavector/ragelo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"factual-dialogue-summarization-via-learning","title":"Factual Dialogue Summarization via Learning from Large Language Models","date":"2024-06-20","arxiv_id":"2406.14709","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-for-enhancing-active-learning","title":"Generative AI for Enhancing Active Learning in Education: A Comparative Study of GPT-3.5 and GPT-4 in Crafting Customized Test Questions","date":"2024-06-20","arxiv_id":"2406.13903","n_code_links":0,"syntology":null},{"paper":null,"slug":"healing-powers-of-bert-how-task-specific-fine","title":"Healing Powers of BERT: How Task-Specific Fine-Tuning Recovers Corrupted Language Models","date":"2024-06-20","arxiv_id":"2406.14459","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-compute-the-probability-of-a-word","slug":"how-to-compute-the-probability-of-a-word","title":"How to Compute the Probability of a Word","date":"2024-06-20","arxiv_id":"2406.14561","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["tpimentelms/probability-of-a-word"],"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":"identifying-user-goals-from-ui-trajectories","title":"Identifying User Goals from UI Trajectories","date":"2024-06-20","arxiv_id":"2406.14314","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-plan-for-retrieval-augmented","slug":"learning-to-plan-for-retrieval-augmented","title":"Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs","date":"2024-06-20","arxiv_id":"2406.14282","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zjukg/lpkg"],"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":"/paper/llasa-large-multimodal-agent-for-human","slug":"llasa-large-multimodal-agent-for-human","title":"LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone Sensors","date":"2024-06-20","arxiv_id":"2406.14498","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":3,"n_instrument":3,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bashlab/llasa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/mm-gtunets-unified-multi-modal-graph-deep","slug":"mm-gtunets-unified-multi-modal-graph-deep","title":"MM-GTUNets: Unified Multi-Modal Graph Deep Learning for Brain Disorders Prediction","date":"2024-06-20","arxiv_id":"2406.14455","n_code_links":1,"syntology":null},{"paper":"/paper/mmbench-video-a-long-form-multi-shot","slug":"mmbench-video-a-long-form-multi-shot","title":"MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding","date":"2024-06-20","arxiv_id":"2406.14515","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":1,"n_instrument":4,"unverified":1,"pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["open-compass/vlmevalkit"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mr-ben-a-comprehensive-meta-reasoning","title":"MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs","date":"2024-06-20","arxiv_id":"2406.13975","n_code_links":0,"syntology":null},{"paper":"/paper/persuasiveness-of-generated-free-text","slug":"persuasiveness-of-generated-free-text","title":"Persuasiveness of Generated Free-Text Rationales in Subjective Decisions: A Case Study on Pairwise Argument Ranking","date":"2024-06-20","arxiv_id":"2406.13905","n_code_links":1,"syntology":null},{"paper":"/paper/prism-a-framework-for-decoupling-and","slug":"prism-a-framework-for-decoupling-and","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","date":"2024-06-20","arxiv_id":"2406.14544","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["sparksjoe/prism"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"relation-extraction-with-fine-tuned-large","title":"Relation Extraction with Fine-Tuned Large Language Models in Retrieval Augmented Generation Frameworks","date":"2024-06-20","arxiv_id":"2406.14745","n_code_links":0,"syntology":null},{"paper":null,"slug":"rtformer-re-parameter-tsbn-spiking","title":"RTFormer: Re-parameter TSBN Spiking Transformer","date":"2024-06-20","arxiv_id":"2406.14180","n_code_links":0,"syntology":null},{"paper":null,"slug":"scidmt-a-large-scale-corpus-for-detecting","title":"SciDMT: A Large-Scale Corpus for Detecting Scientific Mentions","date":"2024-06-20","arxiv_id":"2406.14756","n_code_links":0,"syntology":null},{"paper":"/paper/seg-lstm-performance-of-xlstm-for-semantic","slug":"seg-lstm-performance-of-xlstm-for-semantic","title":"Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images","date":"2024-06-20","arxiv_id":"2406.14086","n_code_links":1,"syntology":null},{"paper":"/paper/sorry-bench-systematically-evaluating-large","slug":"sorry-bench-systematically-evaluating-large","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors","date":"2024-06-20","arxiv_id":"2406.14598","n_code_links":1,"syntology":null},{"paper":null,"slug":"spl-a-socratic-playground-for-learning","title":"SPL: A Socratic Playground for Learning Powered by Large Language Model","date":"2024-06-20","arxiv_id":"2406.13919","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-use-of-multimodal-large-language-models","title":"The Use of Multimodal Large Language Models to Detect Objects from Thermal Images: Transportation Applications","date":"2024-06-20","arxiv_id":"2406.13898","n_code_links":0,"syntology":null},{"paper":null,"slug":"ttqa-rs-a-break-down-prompting-approach-for","title":"TTQA-RS- A break-down prompting approach for Multi-hop Table-Text Question Answering with Reasoning and Summarization","date":"2024-06-20","arxiv_id":"2406.14732","n_code_links":0,"syntology":null},{"paper":null,"slug":"unmasking-database-vulnerabilities-zero","title":"Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems","date":"2024-06-20","arxiv_id":"2406.14545","n_code_links":0,"syntology":null},{"paper":"/paper/a-pure-transformer-pretraining-framework-on","slug":"a-pure-transformer-pretraining-framework-on","title":"A Pure Transformer Pretraining Framework on Text-attributed Graphs","date":"2024-06-19","arxiv_id":"2406.13873","n_code_links":1,"syntology":null},{"paper":"/paper/alanavlm-a-multimodal-embodied-ai-foundation","slug":"alanavlm-a-multimodal-embodied-ai-foundation","title":"AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding","date":"2024-06-19","arxiv_id":"2406.13807","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["alanaai/evud"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-long-context-language-models-subsume","slug":"can-long-context-language-models-subsume","title":"Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?","date":"2024-06-19","arxiv_id":"2406.13121","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 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-deepmind/loft"],"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":"/paper/do-multimodal-foundation-models-understand","slug":"do-multimodal-foundation-models-understand","title":"WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Tasks","date":"2024-06-19","arxiv_id":"2406.13264","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":11,"n_instrument":0,"unverified":1,"pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hazyresearch/wonderbread"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficient-sharpness-aware-minimization-for-2","slug":"efficient-sharpness-aware-minimization-for-2","title":"Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models","date":"2024-06-19","arxiv_id":"2406.13137","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":{"repos":["YL-wang/GraphSAM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fine-tuning-berts-for-definition-extraction","title":"Fine-Tuning BERTs for Definition Extraction from Mathematical Text","date":"2024-06-19","arxiv_id":"2406.13827","n_code_links":0,"syntology":null},{"paper":null,"slug":"forag-factuality-optimized-retrieval","title":"FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering","date":"2024-06-19","arxiv_id":"2406.13779","n_code_links":0,"syntology":null},{"paper":null,"slug":"guided-context-gating-learning-to-leverage","title":"Guided Context Gating: Learning to leverage salient lesions in retinal fundus images","date":"2024-06-19","arxiv_id":"2406.13126","n_code_links":0,"syntology":null},{"paper":"/paper/instructrag-instructing-retrieval-augmented","slug":"instructrag-instructing-retrieval-augmented","title":"InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales","date":"2024-06-19","arxiv_id":"2406.13629","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"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) · 1 unverified","official":{"repos":["weizhepei/instructrag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"is-gpt-4-conscious","title":"Is GPT-4 conscious?","date":"2024-06-19","arxiv_id":"2407.09517","n_code_links":0,"syntology":null},{"paper":null,"slug":"liveness-detection-in-computer-vision","title":"Liveness Detection in Computer Vision: Transformer-based Self-Supervised Learning for Face Anti-Spoofing","date":"2024-06-19","arxiv_id":"2406.13860","n_code_links":0,"syntology":null},{"paper":null,"slug":"m3t-multi-modal-medical-transformer-to-bridge","title":"M3T: Multi-Modal Medical Transformer to bridge Clinical Context with Visual Insights for Retinal Image Medical Description Generation","date":"2024-06-19","arxiv_id":"2406.13129","n_code_links":0,"syntology":null},{"paper":"/paper/model-internals-based-answer-attribution-for","slug":"model-internals-based-answer-attribution-for","title":"Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation","date":"2024-06-19","arxiv_id":"2406.13663","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 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["betswish/mirage"],"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":"/paper/morehopqa-more-than-multi-hop-reasoning","slug":"morehopqa-more-than-multi-hop-reasoning","title":"MoreHopQA: More Than Multi-hop Reasoning","date":"2024-06-19","arxiv_id":"2406.13397","n_code_links":1,"syntology":null},{"paper":"/paper/multi-meta-rag-improving-rag-for-multi-hop","slug":"multi-meta-rag-improving-rag-for-multi-hop","title":"Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata","date":"2024-06-19","arxiv_id":"2406.13213","n_code_links":1,"syntology":null},{"paper":"/paper/on-ai-inspired-ui-design","slug":"on-ai-inspired-ui-design","title":"On AI-Inspired UI-Design","date":"2024-06-19","arxiv_id":"2406.13631","n_code_links":1,"syntology":null},{"paper":null,"slug":"open-generative-large-language-models-for","title":"Open Generative Large Language Models for Galician","date":"2024-06-19","arxiv_id":"2406.13893","n_code_links":0,"syntology":null},{"paper":"/paper/part-aware-unified-representation-of-language-1","slug":"part-aware-unified-representation-of-language-1","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","date":"2024-06-19","arxiv_id":"2406.13327","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["azzh1/purls"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/patholm-identifying-pathogenicity-from-the","slug":"patholm-identifying-pathogenicity-from-the","title":"PathoLM: Identifying pathogenicity from the DNA sequence through the Genome Foundation Model","date":"2024-06-19","arxiv_id":"2406.13133","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":["Sajib-006/Patho-LM"],"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/r-2ag-incorporating-retrieval-information","slug":"r-2ag-incorporating-retrieval-information","title":"R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation","date":"2024-06-19","arxiv_id":"2406.13249","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"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) · 2 unverified","official":{"repos":["yefd/RRAG"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/sali-short-term-alignment-and-long-term-1","slug":"sali-short-term-alignment-and-long-term-1","title":"SALI: Short-term Alignment and Long-term Interaction Network for Colonoscopy Video Polyp Segmentation","date":"2024-06-19","arxiv_id":"2406.13532","n_code_links":1,"syntology":null},{"paper":null,"slug":"swinstyleformer-is-a-favorable-choice-for","title":"SwinStyleformer is a favorable choice for image inversion","date":"2024-06-19","arxiv_id":"2406.13153","n_code_links":0,"syntology":null},{"paper":null,"slug":"wikicontradict-a-benchmark-for-evaluating","title":"WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia","date":"2024-06-19","arxiv_id":"2406.13805","n_code_links":0,"syntology":null},{"paper":"/paper/an-investigation-of-neuron-activation-as-a","slug":"an-investigation-of-neuron-activation-as-a","title":"An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs","date":"2024-06-18","arxiv_id":"2406.12288","n_code_links":2,"syntology":{"ran":34,"of":36,"n_ran_checked":32,"n_instrument":2,"unverified":2,"pointer_only":12,"phrase":"34 ran (of which 0 constructed an object rather than computing a result; 32 with no instrument failure: 0 honoured, 3 violated, 29 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["dakingrai/neuron-analysis-cot-arithmetic-reasoning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"assessing-ai-vs-human-authored-spear-phishing","title":"Assessing AI vs Human-Authored Spear Phishing SMS Attacks: An Empirical Study","date":"2024-06-18","arxiv_id":"2406.13049","n_code_links":0,"syntology":null},{"paper":"/paper/can-large-language-models-always-solve-easy","slug":"can-large-language-models-always-solve-easy","title":"Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?","date":"2024-06-18","arxiv_id":"2406.12809","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":11,"n_instrument":0,"unverified":3,"pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["QwenLM/ConsisEval"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/chatglm-a-family-of-large-language-models","slug":"chatglm-a-family-of-large-language-models","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","date":"2024-06-18","arxiv_id":"2406.12793","n_code_links":7,"syntology":{"ran":21,"of":29,"n_ran_checked":20,"n_instrument":1,"unverified":8,"pointer_only":1,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["thudm/chatglm-6b"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/cyclic-2-5d-perceptual-loss-for-cross-modal","slug":"cyclic-2-5d-perceptual-loss-for-cross-modal","title":"Cyclic 2.5D Perceptual Loss for Cross-Modal 3D Medical Image Synthesis: T1w MRI to Tau PET","date":"2024-06-18","arxiv_id":"2406.12632","n_code_links":1,"syntology":null},{"paper":"/paper/dart-math-difficulty-aware-rejection-tuning-1","slug":"dart-math-difficulty-aware-rejection-tuning-1","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","date":"2024-06-18","arxiv_id":"2407.13690","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":10,"n_instrument":0,"unverified":2,"pointer_only":0,"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":["hkust-nlp/dart-math"],"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":null,"slug":"from-rags-to-rich-parameters-probing-how","title":"From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries","date":"2024-06-18","arxiv_id":"2406.12824","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-educational-materials-with","title":"Generating Educational Materials with Different Levels of Readability using LLMs","date":"2024-06-18","arxiv_id":"2406.12787","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-artificial-intelligence-guided","title":"Generative Artificial Intelligence-Guided User Studies: An Application for Air Taxi Services","date":"2024-06-18","arxiv_id":"2406.12296","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-associative-memory-parallelized","slug":"hierarchical-associative-memory-parallelized","title":"Hierarchical Associative Memory, Parallelized MLP-Mixer, and Symmetry Breaking","date":"2024-06-18","arxiv_id":"2406.12220","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 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Toshihiro-Ota/paramixer"],"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":"intermediate-distillation-data-efficient","title":"Intermediate Distillation: Data-Efficient Distillation from Black-Box LLMs for Information Retrieval","date":"2024-06-18","arxiv_id":"2406.12169","n_code_links":0,"syntology":null},{"paper":"/paper/interpretable-preferences-via-multi-objective","slug":"interpretable-preferences-via-multi-objective","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","date":"2024-06-18","arxiv_id":"2406.12845","n_code_links":2,"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":{"repos":["RLHFlow/RLHF-Reward-Modeling"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/ipeval-a-bilingual-intellectual-property","slug":"ipeval-a-bilingual-intellectual-property","title":"IPEval: A Bilingual Intellectual Property Agency Consultation Evaluation Benchmark for Large Language Models","date":"2024-06-18","arxiv_id":"2406.12386","n_code_links":1,"syntology":null},{"paper":"/paper/judging-the-judges-evaluating-alignment-and","slug":"judging-the-judges-evaluating-alignment-and","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","date":"2024-06-18","arxiv_id":"2406.12624","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["UMass-Meta-LLM-Eval/llm_eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/measuring-psychological-depth-in-language","slug":"measuring-psychological-depth-in-language","title":"Measuring Psychological Depth in Language Models","date":"2024-06-18","arxiv_id":"2406.12680","n_code_links":1,"syntology":null},{"paper":"/paper/mixing-natural-and-synthetic-images-for","slug":"mixing-natural-and-synthetic-images-for","title":"MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations","date":"2024-06-18","arxiv_id":"2406.12368","n_code_links":1,"syntology":null},{"paper":"/paper/pcie-egohandpose-solution-for-egoexo4d-hand","slug":"pcie-egohandpose-solution-for-egoexo4d-hand","title":"PCIE_EgoHandPose Solution for EgoExo4D Hand Pose Challenge","date":"2024-06-18","arxiv_id":"2406.12219","n_code_links":1,"syntology":null},{"paper":"/paper/planrag-a-plan-then-retrieval-augmented","slug":"planrag-a-plan-then-retrieval-augmented","title":"PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers","date":"2024-06-18","arxiv_id":"2406.12430","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":["myeon9h/planrag"],"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"]}}}],"record_sha256":"089b454c144723d7b643504b75368fa78764783f09eb6cbde1aad6f90730f488","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}