{"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/66","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":66,"pages_in_order":249,"rows_per_page":100,"rows":[6501,6600],"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/65","next":"/method/multi-head-attention/papers/67","papers":[{"paper":"/paper/data-efficient-learning-with-neural-programs","slug":"data-efficient-learning-with-neural-programs","title":"Data-Efficient Learning with Neural Programs","date":"2024-06-10","arxiv_id":"2406.06246","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":["alaiasolkobreslin/ised"],"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":"/paper/diving-into-underwater-segment-anything-model","slug":"diving-into-underwater-segment-anything-model","title":"Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset","date":"2024-06-10","arxiv_id":"2406.06039","n_code_links":1,"syntology":null},{"paper":null,"slug":"emotion-aware-speech-self-supervised","title":"Emotion-Aware Speech Self-Supervised Representation Learning with Intensity Knowledge","date":"2024-06-10","arxiv_id":"2406.06646","n_code_links":0,"syntology":null},{"paper":"/paper/husky-a-unified-open-source-language-agent","slug":"husky-a-unified-open-source-language-agent","title":"Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning","date":"2024-06-10","arxiv_id":"2406.06469","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["agent-husky/husky-v1"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/in-context-learning-and-fine-tuning-gpt-for","slug":"in-context-learning-and-fine-tuning-gpt-for","title":"In-Context Learning and Fine-Tuning GPT for Argument Mining","date":"2024-06-10","arxiv_id":"2406.06699","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-physical-simulation-with-message","title":"Learning Physical Simulation with Message Passing Transformer","date":"2024-06-10","arxiv_id":"2406.06060","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-12","title":"Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing","date":"2024-06-10","arxiv_id":"2406.06723","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-dcache-improving-tool-augmented-llms-with","title":"LLM-dCache: Improving Tool-Augmented LLMs with GPT-Driven Localized Data Caching","date":"2024-06-10","arxiv_id":"2406.06799","n_code_links":0,"syntology":null},{"paper":null,"slug":"pointabm-integrating-bidirectional-state","title":"PointABM:Integrating Bidirectional State Space Model with Multi-Head Self-Attention for Point Cloud Analysis","date":"2024-06-10","arxiv_id":"2406.06069","n_code_links":0,"syntology":null},{"paper":null,"slug":"securenet-a-comparative-study-of-deberta-and","title":"SecureNet: A Comparative Study of DeBERTa and Large Language Models for Phishing Detection","date":"2024-06-10","arxiv_id":"2406.06663","n_code_links":0,"syntology":null},{"paper":"/paper/separate-and-reconstruct-asymmetric-encoder","slug":"separate-and-reconstruct-asymmetric-encoder","title":"Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation","date":"2024-06-10","arxiv_id":"2406.05983","n_code_links":1,"syntology":null},{"paper":null,"slug":"symmetric-dot-product-attention-for-efficient","title":"Symmetric Dot-Product Attention for Efficient Training of BERT Language Models","date":"2024-06-10","arxiv_id":"2406.06366","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-quantization-on-retrieval","title":"The Impact of Quantization on Retrieval-Augmented Generation: An Analysis of Small LLMs","date":"2024-06-10","arxiv_id":"2406.10251","n_code_links":0,"syntology":null},{"paper":"/paper/umbrela-umbrela-is-the-open-source","slug":"umbrela-umbrela-is-the-open-source","title":"UMBRELA: UMbrela is the (Open-Source Reproduction of the) Bing RELevance Assessor","date":"2024-06-10","arxiv_id":"2406.06519","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-knowledge-component-based-methodology-for","title":"A Knowledge-Component-Based Methodology for Evaluating AI Assistants","date":"2024-06-09","arxiv_id":"2406.05603","n_code_links":0,"syntology":null},{"paper":"/paper/are-large-language-models-actually-good-at","slug":"are-large-language-models-actually-good-at","title":"Are Large Language Models Actually Good at Text Style Transfer?","date":"2024-06-09","arxiv_id":"2406.05885","n_code_links":1,"syntology":null},{"paper":"/paper/attention-as-a-hypernetwork","slug":"attention-as-a-hypernetwork","title":"Attention as a Hypernetwork","date":"2024-06-09","arxiv_id":"2406.05816","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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["smonsays/hypernetwork-attention"],"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/convolution-and-attention-free-mamba-based","slug":"convolution-and-attention-free-mamba-based","title":"CAMS: Convolution and Attention-Free Mamba-based Cardiac Image Segmentation","date":"2024-06-09","arxiv_id":"2406.05786","n_code_links":1,"syntology":null},{"paper":"/paper/domainrag-a-chinese-benchmark-for-evaluating","slug":"domainrag-a-chinese-benchmark-for-evaluating","title":"DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05654","n_code_links":2,"syntology":{"ran":12,"of":12,"n_ran_checked":11,"n_instrument":1,"unverified":0,"pointer_only":12,"phrase":"12 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ShootingWong/DomainRAG"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-the-efficacy-of-large-language-1","title":"Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering","date":"2024-06-09","arxiv_id":"2406.06637","n_code_links":0,"syntology":null},{"paper":"/paper/gctx-unet-efficient-network-for-medical-image","slug":"gctx-unet-efficient-network-for-medical-image","title":"GCtx-UNet: Efficient Network for Medical Image Segmentation","date":"2024-06-09","arxiv_id":"2406.05891","n_code_links":1,"syntology":null},{"paper":null,"slug":"hidden-holes-topological-aspects-of-language","title":"Hidden Holes: topological aspects of language models","date":"2024-06-09","arxiv_id":"2406.05798","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-memorize-sensor","title":"Large Language Models Memorize Sensor Datasets! Implications on Human Activity Recognition Research","date":"2024-06-09","arxiv_id":"2406.05900","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-against-the-rag-jamming-retrieval","title":"Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents","date":"2024-06-09","arxiv_id":"2406.05870","n_code_links":0,"syntology":null},{"paper":null,"slug":"medreqal-examining-medical-knowledge-recall","title":"MedREQAL: Examining Medical Knowledge Recall of Large Language Models via Question Answering","date":"2024-06-09","arxiv_id":"2406.05845","n_code_links":0,"syntology":null},{"paper":null,"slug":"od-detr-online-distillation-for-stabilizing","title":"OD-DETR: Online Distillation for Stabilizing Training of Detection Transformer","date":"2024-06-09","arxiv_id":"2406.05791","n_code_links":0,"syntology":null},{"paper":"/paper/re-rag-improving-open-domain-qa-performance","slug":"re-rag-improving-open-domain-qa-performance","title":"RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05794","n_code_links":1,"syntology":null},{"paper":"/paper/sinklora-enhanced-efficiency-and-chat","slug":"sinklora-enhanced-efficiency-and-chat","title":"SinkLoRA: Enhanced Efficiency and Chat Capabilities for Long-Context Large Language Models","date":"2024-06-09","arxiv_id":"2406.05678","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":["dexter-gt-86/sinklora"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/smiles2dock-an-open-large-scale-multi-task","slug":"smiles2dock-an-open-large-scale-multi-task","title":"Smiles2Dock: an open large-scale multi-task dataset for ML-based molecular docking","date":"2024-06-09","arxiv_id":"2406.05738","n_code_links":1,"syntology":null},{"paper":null,"slug":"text2vp-generative-ai-for-visual-programming","title":"Text2VP: Generative AI for Visual Programming and Parametric Modeling","date":"2024-06-09","arxiv_id":"2407.07732","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-mamba-cutting-edge-classification-of","title":"Vision Mamba: Cutting-Edge Classification of Alzheimer's Disease with 3D MRI Scans","date":"2024-06-09","arxiv_id":"2406.05757","n_code_links":0,"syntology":null},{"paper":null,"slug":"1st-place-winner-of-the-2024-pixel-level","title":"1st Place Winner of the 2024 Pixel-level Video Understanding in the Wild (CVPR'24 PVUW) Challenge in Video Panoptic Segmentation and Best Long Video Consistency of Video Semantic Segmentation","date":"2024-06-08","arxiv_id":"2406.05352","n_code_links":0,"syntology":null},{"paper":"/paper/a-fine-tuning-dataset-and-benchmark-for-large","slug":"a-fine-tuning-dataset-and-benchmark-for-large","title":"A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding","date":"2024-06-08","arxiv_id":"2406.05540","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":["tsynbio/proteinlmdataset"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/advancing-semantic-textual-similarity","slug":"advancing-semantic-textual-similarity","title":"Advancing Semantic Textual Similarity Modeling: A Regression Framework with Translated ReLU and Smooth K2 Loss","date":"2024-06-08","arxiv_id":"2406.05326","n_code_links":2,"syntology":null},{"paper":"/paper/automata-extraction-from-transformers","slug":"automata-extraction-from-transformers","title":"Automata Extraction from Transformers","date":"2024-06-08","arxiv_id":"2406.05564","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmarking-neural-decoding-backbones","title":"Benchmarking Neural Decoding Backbones towards Enhanced On-edge iBCI Applications","date":"2024-06-08","arxiv_id":"2406.06626","n_code_links":0,"syntology":null},{"paper":null,"slug":"concept-formation-and-alignment-in-language","title":"Concept Formation and Alignment in Language Models: Bridging Statistical Patterns in Latent Space to Concept Taxonomy","date":"2024-06-08","arxiv_id":"2406.05315","n_code_links":0,"syntology":null},{"paper":null,"slug":"critical-phase-transition-in-a-large-language","title":"Critical Phase Transition in Large Language Models","date":"2024-06-08","arxiv_id":"2406.05335","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-llms-recognize-me-when-i-is-not-me","title":"Do LLMs Recognize me, When I is not me: Assessment of LLMs Understanding of Turkish Indexical Pronouns in Indexical Shift Contexts","date":"2024-06-08","arxiv_id":"2406.05569","n_code_links":0,"syntology":null},{"paper":null,"slug":"g-transformer-counterfactual-outcome","title":"G-Transformer: Counterfactual Outcome Prediction under Dynamic and Time-varying Treatment Regimes","date":"2024-06-08","arxiv_id":"2406.05504","n_code_links":0,"syntology":null},{"paper":null,"slug":"matablegpt-gpt-based-table-data-extractor","title":"MaTableGPT: GPT-based Table Data Extractor from Materials Science Literature","date":"2024-06-08","arxiv_id":"2406.05431","n_code_links":0,"syntology":null},{"paper":null,"slug":"selfdefend-llms-can-defend-themselves-against","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","date":"2024-06-08","arxiv_id":"2406.05498","n_code_links":0,"syntology":null},{"paper":null,"slug":"teaching-assistant-in-the-loop-improving","title":"Teaching-Assistant-in-the-Loop: Improving Knowledge Distillation from Imperfect Teacher Models in Low-Budget Scenarios","date":"2024-06-08","arxiv_id":"2406.05322","n_code_links":0,"syntology":null},{"paper":"/paper/toward-reliable-ad-hoc-scientific-information","slug":"toward-reliable-ad-hoc-scientific-information","title":"Toward Reliable Ad-hoc Scientific Information Extraction: A Case Study on Two Materials Datasets","date":"2024-06-08","arxiv_id":"2406.05348","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-conformal-prediction-for-time","slug":"transformer-conformal-prediction-for-time","title":"Transformer Conformal Prediction for Time Series","date":"2024-06-08","arxiv_id":"2406.05332","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Jayaos/TCPTS"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/u-net-ensemble-for-enhanced-semantic","slug":"u-net-ensemble-for-enhanced-semantic","title":"U-Net Ensemble for Enhanced Semantic Segmentation in Remote Sensing Imagery","date":"2024-06-08","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"vp-llm-text-driven-3d-volume-completion-with","title":"VP-LLM: Text-Driven 3D Volume Completion with Large Language Models through Patchification","date":"2024-06-08","arxiv_id":"2406.05543","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-more-empathetic","title":"Are Large Language Models More Empathetic than Humans?","date":"2024-06-07","arxiv_id":"2406.05063","n_code_links":0,"syntology":null},{"paper":"/paper/bamo-at-semeval-2024-task-9-brainteaser-a","slug":"bamo-at-semeval-2024-task-9-brainteaser-a","title":"BAMO at SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common Sense","date":"2024-06-07","arxiv_id":"2406.04947","n_code_links":1,"syntology":null},{"paper":"/paper/berts-are-generative-in-context-learners","slug":"berts-are-generative-in-context-learners","title":"BERTs are Generative In-Context Learners","date":"2024-06-07","arxiv_id":"2406.04823","n_code_links":1,"syntology":{"ran":13,"of":26,"n_ran_checked":12,"n_instrument":1,"unverified":13,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 13 unverified","official":{"repos":["ltgoslo/bert-in-context"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":13,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cdefuse-continuous-decomposition-for-infrared","title":"Conti-Fuse: A Novel Continuous Decomposition-based Fusion Framework for Infrared and Visible Images","date":"2024-06-07","arxiv_id":"2406.04689","n_code_links":0,"syntology":null},{"paper":"/paper/corpus-poisoning-via-approximate-greedy","slug":"corpus-poisoning-via-approximate-greedy","title":"Corpus Poisoning via Approximate Greedy Gradient Descent","date":"2024-06-07","arxiv_id":"2406.05087","n_code_links":1,"syntology":null},{"paper":"/paper/crag-comprehensive-rag-benchmark","slug":"crag-comprehensive-rag-benchmark","title":"CRAG -- Comprehensive RAG Benchmark","date":"2024-06-07","arxiv_id":"2406.04744","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/crag"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ctsyn-a-foundational-model-for-cross-tabular","title":"CTSyn: A Foundational Model for Cross Tabular Data Generation","date":"2024-06-07","arxiv_id":"2406.04619","n_code_links":0,"syntology":null},{"paper":"/paper/diner-a-large-realistic-dataset-for","slug":"diner-a-large-realistic-dataset-for","title":"DiNeR: a Large Realistic Dataset for Evaluating Compositional Generalization","date":"2024-06-07","arxiv_id":"2406.04669","n_code_links":1,"syntology":null},{"paper":"/paper/diving-deep-into-the-motion-representation-of","slug":"diving-deep-into-the-motion-representation-of","title":"Diving Deep into the Motion Representation of Video-Text Models","date":"2024-06-07","arxiv_id":"2406.05075","n_code_links":1,"syntology":null},{"paper":"/paper/gamebench-evaluating-strategic-reasoning","slug":"gamebench-evaluating-strategic-reasoning","title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents","date":"2024-06-07","arxiv_id":"2406.06613","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["Joshuaclymer/GameBench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hints-in-browser-benchmarking-language-models","title":"Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation","date":"2024-06-07","arxiv_id":"2406.05053","n_code_links":0,"syntology":null},{"paper":"/paper/improving-logits-based-detector-without","slug":"improving-logits-based-detector-without","title":"DALD: Improving Logits-based Detector without Logits from Black-box LLMs","date":"2024-06-07","arxiv_id":"2406.05232","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-generative-graph-models","title":"Large Generative Graph Models","date":"2024-06-07","arxiv_id":"2406.05109","n_code_links":0,"syntology":null},{"paper":"/paper/llavaguard-vlm-based-safeguards-for-vision","slug":"llavaguard-vlm-based-safeguards-for-vision","title":"LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models","date":"2024-06-07","arxiv_id":"2406.05113","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":["ml-research/llavaguard"],"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/llms-are-not-intelligent-thinkers-introducing","slug":"llms-are-not-intelligent-thinkers-introducing","title":"LLMs Are Not Intelligent Thinkers: Introducing Mathematical Topic Tree Benchmark for Comprehensive Evaluation of LLMs","date":"2024-06-07","arxiv_id":"2406.05194","n_code_links":1,"syntology":null},{"paper":null,"slug":"logic-synthesis-with-generative-deep-neural","title":"Logic Synthesis with Generative Deep Neural Networks","date":"2024-06-07","arxiv_id":"2406.04699","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-resource-cross-lingual-summarization","title":"Low-Resource Cross-Lingual Summarization through Few-Shot Learning with Large Language Models","date":"2024-06-07","arxiv_id":"2406.04630","n_code_links":0,"syntology":null},{"paper":"/paper/mixture-of-agents-enhances-large-language","slug":"mixture-of-agents-enhances-large-language","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","date":"2024-06-07","arxiv_id":"2406.04692","n_code_links":3,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/multi-head-rag-solving-multi-aspect-problems","slug":"multi-head-rag-solving-multi-aspect-problems","title":"Multi-Head RAG: Solving Multi-Aspect Problems with LLMs","date":"2024-06-07","arxiv_id":"2406.05085","n_code_links":2,"syntology":null},{"paper":null,"slug":"multiplane-prior-guided-few-shot-aerial-scene","title":"Multiplane Prior Guided Few-Shot Aerial Scene Rendering","date":"2024-06-07","arxiv_id":"2406.04961","n_code_links":0,"syntology":null},{"paper":"/paper/on-subjective-uncertainty-quantification-and","slug":"on-subjective-uncertainty-quantification-and","title":"On Subjective Uncertainty Quantification and Calibration in Natural Language Generation","date":"2024-06-07","arxiv_id":"2406.05213","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":12,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["meta-inf/suq-nlg"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pretraining-decision-transformers-with-reward","title":"Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning","date":"2024-06-07","arxiv_id":"2406.05064","n_code_links":0,"syntology":null},{"paper":null,"slug":"rep-resource-efficient-prompting-for-on","title":"REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning","date":"2024-06-07","arxiv_id":"2406.04772","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-interpretable-deep-local-learning","title":"Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation","date":"2024-06-07","arxiv_id":"2406.05222","n_code_links":0,"syntology":null},{"paper":null,"slug":"unitst-effectively-modeling-inter-series-and","title":"UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting","date":"2024-06-07","arxiv_id":"2406.04975","n_code_links":0,"syntology":null},{"paper":null,"slug":"vtrans-accelerating-transformer-compression","title":"VTrans: Accelerating Transformer Compression with Variational Information Bottleneck based Pruning","date":"2024-06-07","arxiv_id":"2406.05276","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-medical-large-language-models","title":"A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions","date":"2024-06-06","arxiv_id":"2406.03712","n_code_links":0,"syntology":null},{"paper":"/paper/abex-data-augmentation-for-low-resource-nlu","slug":"abex-data-augmentation-for-low-resource-nlu","title":"ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions","date":"2024-06-06","arxiv_id":"2406.04286","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":["sreyan88/abex"],"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":"/paper/are-graphs-and-gcns-necessary-for-short-term","slug":"are-graphs-and-gcns-necessary-for-short-term","title":"Are Graphs and GCNs necessary for short-term metro ridership forecasting?","date":"2024-06-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmark-data-contamination-of-large","title":"Benchmark Data Contamination of Large Language Models: A Survey","date":"2024-06-06","arxiv_id":"2406.04244","n_code_links":0,"syntology":null},{"paper":"/paper/characterizing-similarities-and-divergences","slug":"characterizing-similarities-and-divergences","title":"Characterizing Similarities and Divergences in Conversational Tones in Humans and LLMs by Sampling with People","date":"2024-06-06","arxiv_id":"2406.04278","n_code_links":1,"syntology":null},{"paper":null,"slug":"credit-card-fraud-detection-using-advanced","title":"Credit Card Fraud Detection Using Advanced Transformer Model","date":"2024-06-06","arxiv_id":"2406.03733","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-variable-linear-integrated-enhanced","title":"Cross-variable Linear Integrated ENhanced Transformer for Photovoltaic power forecasting","date":"2024-06-06","arxiv_id":"2406.03808","n_code_links":0,"syntology":null},{"paper":"/paper/decoder-only-streaming-transformer-for","slug":"decoder-only-streaming-transformer-for","title":"Decoder-only Streaming Transformer for Simultaneous Translation","date":"2024-06-06","arxiv_id":"2406.03878","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["ictnlp/DST"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/deepstack-deeply-stacking-visual-tokens-is","slug":"deepstack-deeply-stacking-visual-tokens-is","title":"DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs","date":"2024-06-06","arxiv_id":"2406.04334","n_code_links":0,"syntology":null},{"paper":"/paper/do-language-models-understand-morality","slug":"do-language-models-understand-morality","title":"Do Language Models Understand Morality? Towards a Robust Detection of Moral Content","date":"2024-06-06","arxiv_id":"2406.04143","n_code_links":1,"syntology":null},{"paper":null,"slug":"empirical-guidelines-for-deploying-llms-onto","title":"Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices","date":"2024-06-06","arxiv_id":"2406.03777","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-in-context-learning-performance","slug":"enhancing-in-context-learning-performance","title":"Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective","date":"2024-06-06","arxiv_id":"2406.03768","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["chen123ctrls/enhancingicl_svdpruning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-the-latest-llms-for-leaderboard","title":"Exploring the Latest LLMs for Leaderboard Extraction","date":"2024-06-06","arxiv_id":"2406.04383","n_code_links":0,"syntology":null},{"paper":"/paper/generalization-enhanced-code-vulnerability","slug":"generalization-enhanced-code-vulnerability","title":"Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning","date":"2024-06-06","arxiv_id":"2406.03718","n_code_links":1,"syntology":null},{"paper":null,"slug":"glint-ru-gated-lightweight-intelligent","title":"GLINT-RU: Gated Lightweight Intelligent Recurrent Units for Sequential Recommender Systems","date":"2024-06-06","arxiv_id":"2406.10244","n_code_links":0,"syntology":null},{"paper":"/paper/horae-a-domain-agnostic-modeling-language-for","slug":"horae-a-domain-agnostic-modeling-language-for","title":"HORAE: A Domain-Agnostic Language for Automated Service Regulation","date":"2024-06-06","arxiv_id":"2406.06600","n_code_links":1,"syntology":null},{"paper":"/paper/llmembed-rethinking-lightweight-llm-s-genuine","slug":"llmembed-rethinking-lightweight-llm-s-genuine","title":"LLMEmbed: Rethinking Lightweight LLM's Genuine Function in Text Classification","date":"2024-06-06","arxiv_id":"2406.03725","n_code_links":1,"syntology":null},{"paper":null,"slug":"natural-plan-benchmarking-llms-on-natural","title":"NATURAL PLAN: Benchmarking LLMs on Natural Language Planning","date":"2024-06-06","arxiv_id":"2406.04520","n_code_links":0,"syntology":null},{"paper":null,"slug":"proactive-detection-of-physical-inter-rule","title":"Proactive Detection of Physical Inter-rule Vulnerabilities in IoT Services Using a Deep Learning Approach","date":"2024-06-06","arxiv_id":"2406.03836","n_code_links":0,"syntology":null},{"paper":null,"slug":"redistill-residual-encoded-distillation-for","title":"ReDistill: Residual Encoded Distillation for Peak Memory Reduction","date":"2024-06-06","arxiv_id":"2406.03744","n_code_links":0,"syntology":null},{"paper":null,"slug":"robocoder-robotic-learning-from-basic-skills","title":"RoboCoder: Robotic Learning from Basic Skills to General Tasks with Large Language Models","date":"2024-06-06","arxiv_id":"2406.03757","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-and-evaluating-sparse-autoencoders","slug":"scaling-and-evaluating-sparse-autoencoders","title":"Scaling and evaluating sparse autoencoders","date":"2024-06-06","arxiv_id":"2406.04093","n_code_links":5,"syntology":{"ran":7,"of":10,"n_ran_checked":5,"n_instrument":2,"unverified":3,"pointer_only":4,"phrase":"7 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["openai/sparse_autoencoder"],"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":["listed","official"]}}},{"paper":"/paper/simplified-and-generalized-masked-diffusion","slug":"simplified-and-generalized-masked-diffusion","title":"Simplified and Generalized Masked Diffusion for Discrete Data","date":"2024-06-06","arxiv_id":"2406.04329","n_code_links":1,"syntology":{"ran":6,"of":21,"n_ran_checked":2,"n_instrument":4,"unverified":15,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 15 unverified","official":{"repos":["google-deepmind/md4"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":15,"ran_from_kinds":["official"]}}},{"paper":"/paper/tool-planner-dynamic-solution-tree-planning","slug":"tool-planner-dynamic-solution-tree-planning","title":"Tool-Planner: Task Planning with Clusters across Multiple Tools","date":"2024-06-06","arxiv_id":"2406.03807","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":1,"n_instrument":6,"unverified":2,"pointer_only":9,"phrase":"7 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; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["OceannTwT/Tool-Planner"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/tox-bart-leveraging-toxicity-attributes-for","slug":"tox-bart-leveraging-toxicity-attributes-for","title":"Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech","date":"2024-06-06","arxiv_id":"2406.03953","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformers-need-glasses-information-over","title":"Transformers need glasses! Information over-squashing in language tasks","date":"2024-06-06","arxiv_id":"2406.04267","n_code_links":0,"syntology":null},{"paper":null,"slug":"twins-revisiting-non-stationarity-in","title":"TwinS: Revisiting Non-Stationarity in Multivariate Time Series Forecasting","date":"2024-06-06","arxiv_id":"2406.03710","n_code_links":0,"syntology":null}],"record_sha256":"fa2202b73299d7f31ce39fafa0b8e90173ea4e277001dbfc68b529104f51eda2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}