{"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/29","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":29,"pages_in_order":249,"rows_per_page":100,"rows":[2801,2900],"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/28","next":"/method/multi-head-attention/papers/30","papers":[{"paper":"/paper/resofilter-rine-grained-synthetic-data","slug":"resofilter-rine-grained-synthetic-data","title":"ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis","date":"2024-12-19","arxiv_id":"2412.14809","n_code_links":1,"syntology":null},{"paper":null,"slug":"review-then-refine-a-dynamic-framework-for","title":"Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability","date":"2024-12-19","arxiv_id":"2412.15101","n_code_links":0,"syntology":null},{"paper":null,"slug":"sketch-structured-knowledge-enhanced-text","title":"SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval","date":"2024-12-19","arxiv_id":"2412.15443","n_code_links":0,"syntology":null},{"paper":null,"slug":"systematic-evaluation-of-long-context-llms-on","title":"Systematic Evaluation of Long-Context LLMs on Financial Concepts","date":"2024-12-19","arxiv_id":"2412.15386","n_code_links":0,"syntology":null},{"paper":"/paper/till-the-layers-collapse-compressing-a-deep","slug":"till-the-layers-collapse-compressing-a-deep","title":"Till the Layers Collapse: Compressing a Deep Neural Network through the Lenses of Batch Normalization Layers","date":"2024-12-19","arxiv_id":"2412.15077","n_code_links":1,"syntology":null},{"paper":"/paper/tokenphormer-structure-aware-multi-token","slug":"tokenphormer-structure-aware-multi-token","title":"Tokenphormer: Structure-aware Multi-token Graph Transformer for Node Classification","date":"2024-12-19","arxiv_id":"2412.15302","n_code_links":1,"syntology":null},{"paper":"/paper/tomg-bench-evaluating-llms-on-text-based-open","slug":"tomg-bench-evaluating-llms-on-text-based-open","title":"TOMG-Bench: Evaluating LLMs on Text-based Open Molecule Generation","date":"2024-12-19","arxiv_id":"2412.14642","n_code_links":1,"syntology":null},{"paper":null,"slug":"visa-retrieval-augmented-generation-with","title":"VISA: Retrieval Augmented Generation with Visual Source Attribution","date":"2024-12-19","arxiv_id":"2412.14457","n_code_links":0,"syntology":null},{"paper":"/paper/autonomous-microscopy-experiments-through","slug":"autonomous-microscopy-experiments-through","title":"Autonomous Microscopy Experiments through Large Language Model Agents","date":"2024-12-18","arxiv_id":"2501.10385","n_code_links":1,"syntology":null},{"paper":null,"slug":"combining-aggregated-attention-and","title":"Combining Aggregated Attention and Transformer Architecture for Accurate and Efficient Performance of Spiking Neural Networks","date":"2024-12-18","arxiv_id":"2412.13553","n_code_links":0,"syntology":null},{"paper":null,"slug":"cracking-the-code-of-hallucination-in-lvlms","title":"Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence","date":"2024-12-18","arxiv_id":"2412.13949","n_code_links":0,"syntology":null},{"paper":"/paper/distilled-pooling-transformer-encoder-for","slug":"distilled-pooling-transformer-encoder-for","title":"Distilled Pooling Transformer Encoder for Efficient Realistic Image Dehazing","date":"2024-12-18","arxiv_id":"2412.14220","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-rhetorical-figure-annotation-an","slug":"enhancing-rhetorical-figure-annotation-an","title":"Enhancing Rhetorical Figure Annotation: An Ontology-Based Web Application with RAG Integration","date":"2024-12-18","arxiv_id":"2412.13799","n_code_links":1,"syntology":null},{"paper":null,"slug":"evowiki-evaluating-llms-on-evolving-knowledge","title":"EvoWiki: Evaluating LLMs on Evolving Knowledge","date":"2024-12-18","arxiv_id":"2412.13582","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-transformer-augmented-lstm-for","title":"Exploring Transformer-Augmented LSTM for Temporal and Spatial Feature Learning in Trajectory Prediction","date":"2024-12-18","arxiv_id":"2412.13419","n_code_links":0,"syntology":null},{"paper":"/paper/fake-news-detection-comparative-evaluation-of","slug":"fake-news-detection-comparative-evaluation-of","title":"Fake News Detection: Comparative Evaluation of BERT-like Models and Large Language Models with Generative AI-Annotated Data","date":"2024-12-18","arxiv_id":"2412.14276","n_code_links":1,"syntology":null},{"paper":"/paper/farexstance-explainable-stance-detection-for","slug":"farexstance-explainable-stance-detection-for","title":"FarExStance: Explainable Stance Detection for Farsi","date":"2024-12-18","arxiv_id":"2412.14008","n_code_links":2,"syntology":null},{"paper":null,"slug":"federated-learning-and-rag-integration-a","title":"Federated Learning and RAG Integration: A Scalable Approach for Medical Large Language Models","date":"2024-12-18","arxiv_id":"2412.13720","n_code_links":0,"syntology":null},{"paper":"/paper/gnn-transformer-cooperative-architecture-for","slug":"gnn-transformer-cooperative-architecture-for","title":"GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning","date":"2024-12-18","arxiv_id":"2412.16218","n_code_links":1,"syntology":null},{"paper":"/paper/jovale-detecting-human-actions-in-video-using","slug":"jovale-detecting-human-actions-in-video-using","title":"JoVALE: Detecting Human Actions in Video Using Audiovisual and Language Contexts","date":"2024-12-18","arxiv_id":"2412.13708","n_code_links":1,"syntology":null},{"paper":null,"slug":"mcmat-multiview-consistent-and-physically","title":"MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation","date":"2024-12-18","arxiv_id":"2412.14148","n_code_links":0,"syntology":null},{"paper":"/paper/memorizing-sam-3d-medical-segment-anything","slug":"memorizing-sam-3d-medical-segment-anything","title":"Memorizing SAM: 3D Medical Segment Anything Model with Memorizing Transformer","date":"2024-12-18","arxiv_id":"2412.13908","n_code_links":1,"syntology":null},{"paper":"/paper/mix-ln-unleashing-the-power-of-deeper-layers","slug":"mix-ln-unleashing-the-power-of-deeper-layers","title":"Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN","date":"2024-12-18","arxiv_id":"2412.13795","n_code_links":1,"syntology":null},{"paper":"/paper/mmhmr-generative-masked-modeling-for-hand","slug":"mmhmr-generative-masked-modeling-for-hand","title":"MMHMR: Generative Masked Modeling for Hand Mesh Recovery","date":"2024-12-18","arxiv_id":"2412.13393","n_code_links":0,"syntology":null},{"paper":"/paper/modality-independent-graph-neural-networks","slug":"modality-independent-graph-neural-networks","title":"Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation","date":"2024-12-18","arxiv_id":"2412.13994","n_code_links":1,"syntology":null},{"paper":"/paper/model-decides-how-to-tokenize-adaptive-dna","slug":"model-decides-how-to-tokenize-adaptive-dna","title":"Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA","date":"2024-12-18","arxiv_id":"2412.13716","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["qiaoqiaolf/mxdna"],"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":["found_in_text","official"]}}},{"paper":null,"slug":"policy-decorator-model-agnostic-online","title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model","date":"2024-12-18","arxiv_id":"2412.13630","n_code_links":0,"syntology":null},{"paper":"/paper/psydt-using-llms-to-construct-the-digital","slug":"psydt-using-llms-to-construct-the-digital","title":"PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological Counseling","date":"2024-12-18","arxiv_id":"2412.13660","n_code_links":1,"syntology":null},{"paper":"/paper/rag-rewardbench-benchmarking-reward-models-in","slug":"rag-rewardbench-benchmarking-reward-models-in","title":"RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment","date":"2024-12-18","arxiv_id":"2412.13746","n_code_links":1,"syntology":null},{"paper":null,"slug":"reinforcement-learning-from-automatic-1","title":"Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation","date":"2024-12-18","arxiv_id":"2412.14308","n_code_links":0,"syntology":null},{"paper":"/paper/self-attentive-transformer-for-fast-and","slug":"self-attentive-transformer-for-fast-and","title":"Self-attentive Transformer for Fast and Accurate Postprocessing of Temperature and Wind Speed Forecasts","date":"2024-12-18","arxiv_id":"2412.13957","n_code_links":1,"syntology":null},{"paper":"/paper/smarter-better-faster-longer-a-modern","slug":"smarter-better-faster-longer-a-modern","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","date":"2024-12-18","arxiv_id":"2412.13663","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["answerdotai/modernbert"],"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":"a-mapreduce-approach-to-effectively-utilize","title":"A MapReduce Approach to Effectively Utilize Long Context Information in Retrieval Augmented Language Models","date":"2024-12-17","arxiv_id":"2412.15271","n_code_links":0,"syntology":null},{"paper":"/paper/adaptations-of-ai-models-for-querying-the","slug":"adaptations-of-ai-models-for-querying-the","title":"Adaptations of AI models for querying the LandMatrix database in natural language","date":"2024-12-17","arxiv_id":"2412.12961","n_code_links":1,"syntology":null},{"paper":null,"slug":"c-fedrag-a-confidential-federated-retrieval","title":"C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System","date":"2024-12-17","arxiv_id":"2412.13163","n_code_links":0,"syntology":null},{"paper":null,"slug":"chinese-safetyqa-a-safety-short-form","title":"Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models","date":"2024-12-17","arxiv_id":"2412.15265","n_code_links":0,"syntology":null},{"paper":null,"slug":"covnet-covariance-information-assisted-csi","title":"CovNet: Covariance Information-Assisted CSI Feedback for FDD Massive MIMO Systems","date":"2024-12-17","arxiv_id":"2412.12875","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-document-level-paraphrased-machine","title":"Detecting Document-level Paraphrased Machine Generated Content: Mimicking Human Writing Style and Involving Discourse Features","date":"2024-12-17","arxiv_id":"2412.12679","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-diffusion-transformer-policies-with","slug":"efficient-diffusion-transformer-policies-with","title":"Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning","date":"2024-12-17","arxiv_id":"2412.12953","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":7,"n_instrument":3,"unverified":1,"pointer_only":3,"phrase":"10 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; 3 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"enhanced-momentum-with-momentum-transformers","title":"Enhanced Momentum with Momentum Transformers","date":"2024-12-17","arxiv_id":"2412.12516","n_code_links":0,"syntology":null},{"paper":"/paper/exit-context-aware-extractive-compression-for","slug":"exit-context-aware-extractive-compression-for","title":"EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation","date":"2024-12-17","arxiv_id":"2412.12559","n_code_links":1,"syntology":null},{"paper":null,"slug":"falcon-faster-and-parallel-inference-of-large","title":"Falcon: Faster and Parallel Inference of Large Language Models through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree","date":"2024-12-17","arxiv_id":"2412.12639","n_code_links":0,"syntology":null},{"paper":"/paper/gausstr-foundation-model-aligned-gaussian","slug":"gausstr-foundation-model-aligned-gaussian","title":"GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding","date":"2024-12-17","arxiv_id":"2412.13193","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":["hustvl/gausstr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/harnessing-event-sensory-data-for-error","slug":"harnessing-event-sensory-data-for-error","title":"Harnessing Event Sensory Data for Error Pattern Prediction in Vehicles: A Language Model Approach","date":"2024-12-17","arxiv_id":"2412.13041","n_code_links":1,"syntology":null},{"paper":"/paper/judgeblender-ensembling-judgments-for","slug":"judgeblender-ensembling-judgments-for","title":"JudgeBlender: Ensembling Judgments for Automatic Relevance Assessment","date":"2024-12-17","arxiv_id":"2412.13268","n_code_links":1,"syntology":null},{"paper":null,"slug":"llm-based-discriminative-reasoning-for","title":"LLM-based Discriminative Reasoning for Knowledge Graph Question Answering","date":"2024-12-17","arxiv_id":"2412.12643","n_code_links":0,"syntology":null},{"paper":null,"slug":"llmcl-gec-advancing-grammatical-error","title":"LLMCL-GEC: Advancing Grammatical Error Correction with LLM-Driven Curriculum Learning","date":"2024-12-17","arxiv_id":"2412.12541","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-are-also-effective-embedding-models-an","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","date":"2024-12-17","arxiv_id":"2412.12591","n_code_links":0,"syntology":null},{"paper":"/paper/omnieval-an-omnidirectional-and-automatic-rag","slug":"omnieval-an-omnidirectional-and-automatic-rag","title":"OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain","date":"2024-12-17","arxiv_id":"2412.13018","n_code_links":1,"syntology":null},{"paper":null,"slug":"perc-plan-as-query-example-retrieval-for","title":"PERC: Plan-As-Query Example Retrieval for Underrepresented Code Generation","date":"2024-12-17","arxiv_id":"2412.12447","n_code_links":0,"syntology":null},{"paper":null,"slug":"pt-a-plain-transformer-is-good-hospital","title":"PT: A Plain Transformer is Good Hospital Readmission Predictor","date":"2024-12-17","arxiv_id":"2412.12909","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-star-enhancing-deliberative-reasoning","title":"RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement","date":"2024-12-17","arxiv_id":"2412.12881","n_code_links":0,"syntology":null},{"paper":"/paper/rctrans-radar-camera-transformer-via-radar","slug":"rctrans-radar-camera-transformer-via-radar","title":"RCTrans: Radar-Camera Transformer via Radar Densifier and Sequential Decoder for 3D Object Detection","date":"2024-12-17","arxiv_id":"2412.12799","n_code_links":1,"syntology":null},{"paper":null,"slug":"remoterag-a-privacy-preserving-llm-cloud-rag","title":"RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service","date":"2024-12-17","arxiv_id":"2412.12775","n_code_links":0,"syntology":null},{"paper":"/paper/simgrag-leveraging-similar-subgraphs-for","slug":"simgrag-leveraging-similar-subgraphs-for","title":"SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation","date":"2024-12-17","arxiv_id":"2412.15272","n_code_links":1,"syntology":null},{"paper":"/paper/timecheat-a-channel-harmony-strategy-for","slug":"timecheat-a-channel-harmony-strategy-for","title":"TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series Analysis","date":"2024-12-17","arxiv_id":"2412.12886","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["Alrash/TimeCHEAT"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"what-external-knowledge-is-preferred-by-llms","title":"What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context","date":"2024-12-17","arxiv_id":"2412.12632","n_code_links":0,"syntology":null},{"paper":"/paper/a-benchmark-and-robustness-study-of-in","slug":"a-benchmark-and-robustness-study-of-in","title":"A Benchmark and Robustness Study of In-Context-Learning with Large Language Models in Music Entity Detection","date":"2024-12-16","arxiv_id":"2412.11851","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-lora-is-worth-a-thousand-pictures","title":"A LoRA is Worth a Thousand Pictures","date":"2024-12-16","arxiv_id":"2412.12048","n_code_links":0,"syntology":null},{"paper":"/paper/biobridge-unified-bio-embedding-with-bridging","slug":"biobridge-unified-bio-embedding-with-bridging","title":"BioBridge: Unified Bio-Embedding with Bridging Modality in Code-Switched EMR","date":"2024-12-16","arxiv_id":"2412.11671","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-language-models-rival-mathematics","title":"Can Language Models Rival Mathematics Students? Evaluating Mathematical Reasoning through Textual Manipulation and Human Experiments","date":"2024-12-16","arxiv_id":"2412.11908","n_code_links":0,"syntology":null},{"paper":"/paper/causal-diffusion-transformers-for-generative","slug":"causal-diffusion-transformers-for-generative","title":"Causal Diffusion Transformers for Generative Modeling","date":"2024-12-16","arxiv_id":"2412.12095","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["causalfusion/causalfusion"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/edformer-embedded-decomposition-transformer","slug":"edformer-embedded-decomposition-transformer","title":"EDformer: Embedded Decomposition Transformer for Interpretable Multivariate Time Series Predictions","date":"2024-12-16","arxiv_id":"2412.12227","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":["sanjaylopa22/EDformer-Feature-Importance"],"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/geox-geometric-problem-solving-through","slug":"geox-geometric-problem-solving-through","title":"GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training","date":"2024-12-16","arxiv_id":"2412.11863","n_code_links":2,"syntology":{"ran":7,"of":7,"n_ran_checked":5,"n_instrument":2,"unverified":0,"pointer_only":7,"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) · 0 unverified","official":{"repos":["alpha-innovator/geox","unimodal4reasoning/geox"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/glimpse-enabling-white-box-methods-to-use","slug":"glimpse-enabling-white-box-methods-to-use","title":"Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection","date":"2024-12-16","arxiv_id":"2412.11506","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["baoguangsheng/glimpse"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"graph-guided-textual-explanation-generation","title":"Graph-Guided Textual Explanation Generation Framework","date":"2024-12-16","arxiv_id":"2412.12318","n_code_links":0,"syntology":null},{"paper":null,"slug":"hresformer-hybrid-residual-transformer-for","title":"HResFormer: Hybrid Residual Transformer for Volumetric Medical Image Segmentation","date":"2024-12-16","arxiv_id":"2412.11458","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-mixture-of-experts-in-dense","title":"Investigating Mixture of Experts in Dense Retrieval","date":"2024-12-16","arxiv_id":"2412.11864","n_code_links":0,"syntology":null},{"paper":"/paper/look-ahead-text-understanding-and-llm","slug":"look-ahead-text-understanding-and-llm","title":"Look Ahead Text Understanding and LLM Stitching","date":"2024-12-16","arxiv_id":"2412.17836","n_code_links":1,"syntology":null},{"paper":null,"slug":"magnetic-field-data-calibration-with","title":"Magnetic Field Data Calibration with Transformer Model Using Physical Constraints: A Scalable Method for Satellite Missions, Illustrated by Tianwen-1","date":"2024-12-16","arxiv_id":"2501.00020","n_code_links":0,"syntology":null},{"paper":"/paper/no-more-adam-learning-rate-scaling-at","slug":"no-more-adam-learning-rate-scaling-at","title":"No More Adam: Learning Rate Scaling at Initialization is All You Need","date":"2024-12-16","arxiv_id":"2412.11768","n_code_links":1,"syntology":null},{"paper":null,"slug":"openreviewer-a-specialized-large-language","title":"OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews","date":"2024-12-16","arxiv_id":"2412.11948","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimized-quran-passage-retrieval-using-an","title":"Optimized Quran Passage Retrieval Using an Expanded QA Dataset and Fine-Tuned Language Models","date":"2024-12-16","arxiv_id":"2412.11431","n_code_links":0,"syntology":null},{"paper":null,"slug":"priority-aware-model-distributed-inference-at","title":"Priority-Aware Model-Distributed Inference at Edge Networks","date":"2024-12-16","arxiv_id":"2412.12371","n_code_links":0,"syntology":null},{"paper":null,"slug":"radarsat-constellation-mission-compact","title":"RADARSAT Constellation Mission Compact Polarisation SAR Data for Burned Area Mapping with Deep Learning","date":"2024-12-16","arxiv_id":"2412.11561","n_code_links":0,"syntology":null},{"paper":"/paper/rag-playground-a-framework-for-systematic","slug":"rag-playground-a-framework-for-systematic","title":"RAG Playground: A Framework for Systematic Evaluation of Retrieval Strategies and Prompt Engineering in RAG Systems","date":"2024-12-16","arxiv_id":"2412.12322","n_code_links":1,"syntology":null},{"paper":null,"slug":"second-language-arabic-acquisition-of-llms","title":"Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion","date":"2024-12-16","arxiv_id":"2412.12310","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-ai-assistance-on-radiology","title":"The Impact of AI Assistance on Radiology Reporting: A Pilot Study Using Simulated AI Draft Reports","date":"2024-12-16","arxiv_id":"2412.12042","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-open-source-advantage-in-large-language","title":"The Open Source Advantage in Large Language Models (LLMs)","date":"2024-12-16","arxiv_id":"2412.12004","n_code_links":0,"syntology":null},{"paper":null,"slug":"unanswerability-evaluation-for-retreival","title":"Unanswerability Evaluation for Retrieval Augmented Generation","date":"2024-12-16","arxiv_id":"2412.12300","n_code_links":0,"syntology":null},{"paper":null,"slug":"unma-capsumt-unified-and-multi-head-attention","title":"UnMA-CapSumT: Unified and Multi-Head Attention-driven Caption Summarization Transformer","date":"2024-12-16","arxiv_id":"2412.11836","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-contextualized-bert-model-for-knowledge","title":"A Contextualized BERT model for Knowledge Graph Completion","date":"2024-12-15","arxiv_id":"2412.11016","n_code_links":0,"syntology":null},{"paper":"/paper/more-class-patch-attention-needs","slug":"more-class-patch-attention-needs","title":"MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation","date":"2024-12-15","arxiv_id":"2412.11076","n_code_links":1,"syntology":null},{"paper":"/paper/multi-graph-co-training-for-capturing-user","slug":"multi-graph-co-training-for-capturing-user","title":"Multi-Graph Co-Training for Capturing User Intent in Session-based Recommendation","date":"2024-12-15","arxiv_id":"2412.11105","n_code_links":1,"syntology":null},{"paper":null,"slug":"one-shot-multilingual-font-generation-via-vit","title":"One-Shot Multilingual Font Generation Via ViT","date":"2024-12-15","arxiv_id":"2412.11342","n_code_links":0,"syntology":null},{"paper":"/paper/rolargesum-a-large-dialect-aware-romanian","slug":"rolargesum-a-large-dialect-aware-romanian","title":"RoLargeSum: A Large Dialect-Aware Romanian News Dataset for Summary, Headline, and Keyword Generation","date":"2024-12-15","arxiv_id":"2412.11317","n_code_links":1,"syntology":null},{"paper":"/paper/smaller-language-models-are-better","slug":"smaller-language-models-are-better","title":"Smaller Language Models Are Better Instruction Evolvers","date":"2024-12-15","arxiv_id":"2412.11231","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-context-aware-convolutional-network","title":"Towards Context-aware Convolutional Network for Image Restoration","date":"2024-12-15","arxiv_id":"2412.11008","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-bearing-fault-detection","title":"Transformer-Based Bearing Fault Detection using Temporal Decomposition Attention Mechanism","date":"2024-12-15","arxiv_id":"2412.11245","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-retrieval-augmented-generation","title":"Accelerating Retrieval-Augmented Generation","date":"2024-12-14","arxiv_id":"2412.15246","n_code_links":0,"syntology":null},{"paper":null,"slug":"centaur-bridging-the-impossible-trinity-of","title":"CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference","date":"2024-12-14","arxiv_id":"2412.10652","n_code_links":0,"syntology":null},{"paper":"/paper/do-large-language-vision-models-understand-3d","slug":"do-large-language-vision-models-understand-3d","title":"Do large language vision models understand 3D shapes?","date":"2024-12-14","arxiv_id":"2412.10908","n_code_links":1,"syntology":null},{"paper":"/paper/fairgp-a-scalable-and-fair-graph-transformer","slug":"fairgp-a-scalable-and-fair-graph-transformer","title":"FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning","date":"2024-12-14","arxiv_id":"2412.10669","n_code_links":1,"syntology":null},{"paper":"/paper/heterogeneous-graph-transformer-for-multiple","slug":"heterogeneous-graph-transformer-for-multiple","title":"Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos","date":"2024-12-14","arxiv_id":"2412.10861","n_code_links":1,"syntology":null},{"paper":null,"slug":"inference-scaling-for-bridging-retrieval-and","title":"Inference Scaling for Bridging Retrieval and Augmented Generation","date":"2024-12-14","arxiv_id":"2412.10684","n_code_links":0,"syntology":null},{"paper":"/paper/medg-krp-medical-graph-knowledge","slug":"medg-krp-medical-graph-knowledge","title":"MedG-KRP: Medical Graph Knowledge Representation Probing","date":"2024-12-14","arxiv_id":"2412.10982","n_code_links":1,"syntology":null},{"paper":null,"slug":"rat-adversarial-attacks-on-deep-reinforcement","title":"RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors","date":"2024-12-14","arxiv_id":"2412.10713","n_code_links":0,"syntology":null},{"paper":null,"slug":"styledit-a-unified-framework-for-diverse","title":"StyleDiT: A Unified Framework for Diverse Child and Partner Faces Synthesis with Style Latent Diffusion Transformer","date":"2024-12-14","arxiv_id":"2412.10785","n_code_links":0,"syntology":null},{"paper":"/paper/susgen-gpt-a-data-centric-llm-for-financial","slug":"susgen-gpt-a-data-centric-llm-for-financial","title":"SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report Generation","date":"2024-12-14","arxiv_id":"2412.10906","n_code_links":1,"syntology":null},{"paper":null,"slug":"tokens-the-oft-overlooked-appetizer-large","title":"Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning","date":"2024-12-14","arxiv_id":"2412.10924","n_code_links":0,"syntology":null}],"record_sha256":"fa00ac4de883e571326203ffd498b028e3899d5effda0cb25f293c09074f37c6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}