{"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/attention/papers/148","list_of":"/method/attention","method":"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":148,"pages_in_order":316,"rows_per_page":100,"rows":[14701,14800],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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/attention","prev":"/method/attention/papers/147","next":"/method/attention/papers/149","papers":[{"paper":null,"slug":"contact-aware-human-motion-generation-from","title":"Contact-aware Human Motion Generation from Textual Descriptions","date":"2024-03-23","arxiv_id":"2403.15709","n_code_links":0,"syntology":null},{"paper":null,"slug":"eagle-a-domain-generalization-framework-for","title":"EAGLE: A Domain Generalization Framework for AI-generated Text Detection","date":"2024-03-23","arxiv_id":"2403.15690","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-llm-for-enterprise-practical","title":"Fine Tuning LLM for Enterprise: Practical Guidelines and Recommendations","date":"2024-03-23","arxiv_id":"2404.10779","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-retrieval-for-rag-based-question","title":"Improving Retrieval for RAG based Question Answering Models on Financial Documents","date":"2024-03-23","arxiv_id":"2404.07221","n_code_links":0,"syntology":null},{"paper":"/paper/llambert-large-scale-low-cost-data-annotation","slug":"llambert-large-scale-low-cost-data-annotation","title":"LlamBERT: Large-scale low-cost data annotation in NLP","date":"2024-03-23","arxiv_id":"2403.15938","n_code_links":1,"syntology":null},{"paper":"/paper/once-for-both-single-stage-of-importance-and","slug":"once-for-both-single-stage-of-importance-and","title":"Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression","date":"2024-03-23","arxiv_id":"2403.15835","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["hankye/once-for-both"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"technical-report-masked-skeleton-sequence","title":"Technical Report: Masked Skeleton Sequence Modeling for Learning Larval Zebrafish Behavior Latent Embeddings","date":"2024-03-23","arxiv_id":"2403.15693","n_code_links":0,"syntology":null},{"paper":"/paper/towards-a-textbf-rag-based-summarization","slug":"towards-a-textbf-rag-based-summarization","title":"Towards a RAG-based Summarization Agent for the Electron-Ion Collider","date":"2024-03-23","arxiv_id":"2403.15729","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-emergent-abilities-of-language","title":"Understanding Emergent Abilities of Language Models from the Loss Perspective","date":"2024-03-23","arxiv_id":"2403.15796","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-for-ontoclean","title":"Using Large Language Models for OntoClean-based Ontology Refinement","date":"2024-03-23","arxiv_id":"2403.15864","n_code_links":0,"syntology":null},{"paper":"/paper/when-llm-based-code-generation-meets-the","slug":"when-llm-based-code-generation-meets-the","title":"SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents","date":"2024-03-23","arxiv_id":"2403.15852","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapprox-adaptive-approximation-in-adam","title":"Adapprox: Adaptive Approximation in Adam Optimization via Randomized Low-Rank Matrices","date":"2024-03-22","arxiv_id":"2403.14958","n_code_links":0,"syntology":null},{"paper":"/paper/blended-rag-improving-rag-retriever-augmented","slug":"blended-rag-improving-rag-retriever-augmented","title":"Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers","date":"2024-03-22","arxiv_id":"2404.07220","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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":["ibm-ecosystem-engineering/blended-rag"],"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":"/paper/bsnet-box-supervised-simulation-assisted-mean","slug":"bsnet-box-supervised-simulation-assisted-mean","title":"BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation","date":"2024-03-22","arxiv_id":"2403.15019","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["peoplelu/bsnet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"can-large-language-models-explore-in-context","title":"Can large language models explore in-context?","date":"2024-03-22","arxiv_id":"2403.15371","n_code_links":0,"syntology":null},{"paper":"/paper/comprehensive-evaluation-and-insights-into-1","slug":"comprehensive-evaluation-and-insights-into-1","title":"Comprehensive Evaluation and Insights into the Use of Large Language Models in the Automation of Behavior-Driven Development Acceptance Test Formulation","date":"2024-03-22","arxiv_id":"2403.14965","n_code_links":1,"syntology":null},{"paper":"/paper/construction-of-a-japanese-financial","slug":"construction-of-a-japanese-financial","title":"Construction of a Japanese Financial Benchmark for Large Language Models","date":"2024-03-22","arxiv_id":"2403.15062","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"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":["pfnet-research/japanese-lm-fin-harness"],"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":"esg-classification-by-implicit-rule-learning","title":"ESG Classification by Implicit Rule Learning via GPT-4","date":"2024-03-22","arxiv_id":"2403.15040","n_code_links":0,"syntology":null},{"paper":"/paper/gtc-gnn-transformer-co-contrastive-learning","slug":"gtc-gnn-transformer-co-contrastive-learning","title":"GTC: GNN-Transformer Co-contrastive Learning for Self-supervised Heterogeneous Graph Representation","date":"2024-03-22","arxiv_id":"2403.15520","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":4,"n_instrument":2,"unverified":2,"pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["phd-lanyu/gtc"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hierarchical-information-enhancement-network","title":"Hierarchical Information Enhancement Network for Cascade Prediction in Social Networks","date":"2024-03-22","arxiv_id":"2403.15257","n_code_links":0,"syntology":null},{"paper":"/paper/llava-prumerge-adaptive-token-reduction-for","slug":"llava-prumerge-adaptive-token-reduction-for","title":"LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models","date":"2024-03-22","arxiv_id":"2403.15388","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":null}},{"paper":null,"slug":"masontigers-at-semeval-2024-task-1-an","title":"MasonTigers at SemEval-2024 Task 1: An Ensemble Approach for Semantic Textual Relatedness","date":"2024-03-22","arxiv_id":"2403.14990","n_code_links":0,"syntology":null},{"paper":null,"slug":"measuring-gender-and-racial-biases-in-large","title":"Measuring Gender and Racial Biases in Large Language Models","date":"2024-03-22","arxiv_id":"2403.15281","n_code_links":0,"syntology":null},{"paper":"/paper/neural-plasticity-inspired-foundation-model","slug":"neural-plasticity-inspired-foundation-model","title":"Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation","date":"2024-03-22","arxiv_id":"2403.15356","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhu-xlab/dofa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-zero-shot-counterspeech-generation-by-llms","slug":"on-zero-shot-counterspeech-generation-by-llms","title":"On Zero-Shot Counterspeech Generation by LLMs","date":"2024-03-22","arxiv_id":"2403.14938","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimal-path-for-biomedical-text","title":"Optimal path for Biomedical Text Summarization Using Pointer GPT","date":"2024-03-22","arxiv_id":"2404.08654","n_code_links":0,"syntology":null},{"paper":null,"slug":"parformer-vision-transformer-baseline-with","title":"ParFormer: A Vision Transformer with Parallel Mixer and Sparse Channel Attention Patch Embedding","date":"2024-03-22","arxiv_id":"2403.15004","n_code_links":0,"syntology":null},{"paper":null,"slug":"reasoning-enhanced-object-centric-learning","title":"Reasoning-Enhanced Object-Centric Learning for Videos","date":"2024-03-22","arxiv_id":"2403.15245","n_code_links":0,"syntology":null},{"paper":null,"slug":"selecting-query-bag-as-pseudo-relevance","title":"Selecting Query-bag as Pseudo Relevance Feedback for Information-seeking Conversations","date":"2024-03-22","arxiv_id":"2404.04272","n_code_links":0,"syntology":null},{"paper":null,"slug":"selectively-informative-description-can","title":"Selectively Informative Description can Reduce Undesired Embedding Entanglements in Text-to-Image Personalization","date":"2024-03-22","arxiv_id":"2403.15330","n_code_links":0,"syntology":null},{"paper":null,"slug":"sensoryt5-infusing-sensorimotor-norms-into-t5","title":"SensoryT5: Infusing Sensorimotor Norms into T5 for Enhanced Fine-grained Emotion Classification","date":"2024-03-22","arxiv_id":"2403.15574","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-clustering-with-llm-embeddings","title":"Text Clustering with Large Language Model Embeddings","date":"2024-03-22","arxiv_id":"2403.15112","n_code_links":0,"syntology":null},{"paper":null,"slug":"vehicle-detection-performance-in-nordic","title":"Vehicle Detection Performance in Nordic Region","date":"2024-03-22","arxiv_id":"2403.15017","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-chain-of-thought-prompting-approach-with","title":"A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science","date":"2024-03-21","arxiv_id":"2403.14565","n_code_links":0,"syntology":null},{"paper":"/paper/a-large-scale-network-construction-and","slug":"a-large-scale-network-construction-and","title":"A Large-Scale Network Construction and Lightweighting Method for Point Cloud Semantic Segmentation","date":"2024-03-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"ai-and-memory-wall","title":"AI and Memory Wall","date":"2024-03-21","arxiv_id":"2403.14123","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-utility-of-large-language","title":"Assessing the Utility of Large Language Models for Phenotype-Driven Gene Prioritization in Rare Genetic Disorder Diagnosis","date":"2024-03-21","arxiv_id":"2403.14801","n_code_links":0,"syntology":null},{"paper":"/paper/cobra-extending-mamba-to-multi-modal-large","slug":"cobra-extending-mamba-to-multi-modal-large","title":"Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference","date":"2024-03-21","arxiv_id":"2403.14520","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":["h-zhao1997/cobra"],"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/emergent-world-models-and-latent-variable","slug":"emergent-world-models-and-latent-variable","title":"Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models","date":"2024-03-21","arxiv_id":"2403.15498","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["adamkarvonen/chess_llm_interpretability"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-the-potential-of-large-language-7","title":"Exploring the Potential of Large Language Models in Graph Generation","date":"2024-03-21","arxiv_id":"2403.14358","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-emotion-phrases-from-tweets-using","title":"Extracting Emotion Phrases from Tweets using BART","date":"2024-03-21","arxiv_id":"2403.14050","n_code_links":0,"syntology":null},{"paper":null,"slug":"fit-rag-black-box-rag-with-factual","title":"FIT-RAG: Black-Box RAG with Factual Information and Token Reduction","date":"2024-03-21","arxiv_id":"2403.14374","n_code_links":0,"syntology":null},{"paper":"/paper/k-act2emo-korean-commonsense-knowledge-graph","slug":"k-act2emo-korean-commonsense-knowledge-graph","title":"K-Act2Emo: Korean Commonsense Knowledge Graph for Indirect Emotional Expression","date":"2024-03-21","arxiv_id":"2403.14253","n_code_links":1,"syntology":null},{"paper":null,"slug":"ldtr-transformer-based-lane-detection-with","title":"LDTR: Transformer-based Lane Detection with Anchor-chain Representation","date":"2024-03-21","arxiv_id":"2403.14354","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-with-sasquatch-a-novel-variational","title":"Learning with SASQuaTCh: a Novel Variational Quantum Transformer Architecture with Kernel-Based Self-Attention","date":"2024-03-21","arxiv_id":"2403.14753","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-based-extraction-of-contradictions-from","title":"LLM-based Extraction of Contradictions from Patents","date":"2024-03-21","arxiv_id":"2403.14258","n_code_links":0,"syntology":null},{"paper":"/paper/otseg-multi-prompt-sinkhorn-attention-for","slug":"otseg-multi-prompt-sinkhorn-attention-for","title":"OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation","date":"2024-03-21","arxiv_id":"2403.14183","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":7,"n_instrument":3,"unverified":0,"pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cubeyoung/OTSeg"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/psalm-pixelwise-segmentation-with-large-multi","slug":"psalm-pixelwise-segmentation-with-large-multi","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","date":"2024-03-21","arxiv_id":"2403.14598","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":2,"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) · 4 unverified","official":{"repos":["zamling/psalm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"react-meets-actre-autonomous-annotations-of","title":"ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy","date":"2024-03-21","arxiv_id":"2403.14589","n_code_links":0,"syntology":null},{"paper":"/paper/s2lic-learned-image-compression-with-the","slug":"s2lic-learned-image-compression-with-the","title":"S2LIC: Learned Image Compression with the SwinV2 Block, Adaptive Channel-wise and Global-inter Attention Context","date":"2024-03-21","arxiv_id":"2403.14471","n_code_links":1,"syntology":null},{"paper":null,"slug":"speech-aware-neural-diarization-with-encoder","title":"Speech-Aware Neural Diarization with Encoder-Decoder Attractor Guided by Attention Constraints","date":"2024-03-21","arxiv_id":"2403.14268","n_code_links":0,"syntology":null},{"paper":"/paper/spikegraphormer-a-high-performance-graph","slug":"spikegraphormer-a-high-performance-graph","title":"SpikeGraphormer: A High-Performance Graph Transformer with Spiking Graph Attention","date":"2024-03-21","arxiv_id":"2403.15480","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["phd-lanyu/spikegraphormer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/spikingresformer-bridging-resnet-and-vision","slug":"spikingresformer-bridging-resnet-and-vision","title":"SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks","date":"2024-03-21","arxiv_id":"2403.14302","n_code_links":2,"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, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xyshi2000/spikingresformer"],"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":null,"slug":"token-transformation-matters-towards-faithful","title":"Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer","date":"2024-03-21","arxiv_id":"2403.14552","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-multi-class-anomaly-detection","title":"Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference","date":"2024-03-21","arxiv_id":"2403.14213","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-audio-visual-segmentation-with","title":"Unsupervised Audio-Visual Segmentation with Modality Alignment","date":"2024-03-21","arxiv_id":"2403.14203","n_code_links":0,"syntology":null},{"paper":"/paper/vurf-a-general-purpose-reasoning-and-self","slug":"vurf-a-general-purpose-reasoning-and-self","title":"VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding","date":"2024-03-21","arxiv_id":"2403.14743","n_code_links":1,"syntology":null},{"paper":null,"slug":"amp-autoregressive-motion-prediction","title":"AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving","date":"2024-03-20","arxiv_id":"2403.13331","n_code_links":0,"syntology":null},{"paper":null,"slug":"aud-tgn-advancing-action-unit-detection-with","title":"AUD-TGN: Advancing Action Unit Detection with Temporal Convolution and GPT-2 in Wild Audiovisual Contexts","date":"2024-03-20","arxiv_id":"2403.13678","n_code_links":0,"syntology":null},{"paper":"/paper/ax-to-grind-urdu-benchmark-dataset-for-urdu","slug":"ax-to-grind-urdu-benchmark-dataset-for-urdu","title":"Ax-to-Grind Urdu: Benchmark Dataset for Urdu Fake News Detection","date":"2024-03-20","arxiv_id":"2403.14037","n_code_links":1,"syntology":null},{"paper":null,"slug":"diffimpute-tabular-data-imputation-with","title":"DiffImpute: Tabular Data Imputation With Denoising Diffusion Probabilistic Model","date":"2024-03-20","arxiv_id":"2403.13863","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-argument-classification-with","title":"Efficient argument classification with compact language models and ChatGPT-4 refinements","date":"2024-03-20","arxiv_id":"2403.15473","n_code_links":0,"syntology":null},{"paper":"/paper/facilitating-pornographic-text-detection-for","slug":"facilitating-pornographic-text-detection-for","title":"Facilitating Pornographic Text Detection for Open-Domain Dialogue Systems via Knowledge Distillation of Large Language Models","date":"2024-03-20","arxiv_id":"2403.13250","n_code_links":1,"syntology":null},{"paper":null,"slug":"high-confidence-pseudo-labels-for-domain","title":"High-confidence pseudo-labels for domain adaptation in COVID-19 detection","date":"2024-03-20","arxiv_id":"2403.13509","n_code_links":0,"syntology":null},{"paper":"/paper/incentivizing-news-consumption-on-social","slug":"incentivizing-news-consumption-on-social","title":"Incentivizing News Consumption on Social Media Platforms Using Large Language Models and Realistic Bot Accounts","date":"2024-03-20","arxiv_id":"2403.13362","n_code_links":1,"syntology":null},{"paper":"/paper/motion-generation-from-fine-grained-textual","slug":"motion-generation-from-fine-grained-textual","title":"Motion Generation from Fine-grained Textual Descriptions","date":"2024-03-20","arxiv_id":"2403.13518","n_code_links":1,"syntology":null},{"paper":"/paper/mtp-advancing-remote-sensing-foundation-model","slug":"mtp-advancing-remote-sensing-foundation-model","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","date":"2024-03-20","arxiv_id":"2403.13430","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":2,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vitae-transformer/mtp"],"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":["listed","official"]}}},{"paper":null,"slug":"natural-language-as-polices-reasoning-for","title":"Natural Language as Policies: Reasoning for Coordinate-Level Embodied Control with LLMs","date":"2024-03-20","arxiv_id":"2403.13801","n_code_links":0,"syntology":null},{"paper":null,"slug":"open-access-nao-oan-a-ros2-based-software","title":"Open Access NAO (OAN): a ROS2-based software framework for HRI applications with the NAO robot","date":"2024-03-20","arxiv_id":"2403.13960","n_code_links":0,"syntology":null},{"paper":null,"slug":"paramanu-ayn-an-efficient-novel-generative","title":"PARAMANU-AYN: Pretrain from scratch or Continual Pretraining of LLMs for Legal Domain Adaptation?","date":"2024-03-20","arxiv_id":"2403.13681","n_code_links":0,"syntology":null},{"paper":null,"slug":"portrait4d-v2-pseudo-multi-view-data-creates","title":"Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer","date":"2024-03-20","arxiv_id":"2403.13570","n_code_links":0,"syntology":null},{"paper":"/paper/retina-vision-transformer-retinavit","slug":"retina-vision-transformer-retinavit","title":"Retina Vision Transformer (RetinaViT): Introducing Scaled Patches into Vision Transformers","date":"2024-03-20","arxiv_id":"2403.13677","n_code_links":1,"syntology":null},{"paper":"/paper/rotary-position-embedding-for-vision","slug":"rotary-position-embedding-for-vision","title":"Rotary Position Embedding for Vision Transformer","date":"2024-03-20","arxiv_id":"2403.13298","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["naver-ai/rope-vit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"t-pixel2mesh-combining-global-and-local","title":"T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image","date":"2024-03-20","arxiv_id":"2403.13663","n_code_links":0,"syntology":null},{"paper":null,"slug":"vi-mistral-x-building-a-vietnamese-language","title":"Vi-Mistral-X: Building a Vietnamese Language Model with Advanced Continual Pre-training","date":"2024-03-20","arxiv_id":"2403.15470","n_code_links":0,"syntology":null},{"paper":"/paper/vl-mamba-exploring-state-space-models-for","slug":"vl-mamba-exploring-state-space-models-for","title":"VL-Mamba: Exploring State Space Models for Multimodal Learning","date":"2024-03-20","arxiv_id":"2403.13600","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparison-of-deep-learning-architectures-1","title":"A Comparison of Deep Learning Architectures for Spacecraft Anomaly Detection","date":"2024-03-19","arxiv_id":"2403.12864","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-data-curation-for-robust-language","title":"Automated Data Curation for Robust Language Model Fine-Tuning","date":"2024-03-19","arxiv_id":"2403.12776","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-information-extraction-from","title":"Automatic Information Extraction From Employment Tribunal Judgements Using Large Language Models","date":"2024-03-19","arxiv_id":"2403.12936","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-summarization-of-doctor-patient","title":"Automatic Summarization of Doctor-Patient Encounter Dialogues Using Large Language Model through Prompt Tuning","date":"2024-03-19","arxiv_id":"2403.13089","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-ai-outperform-human-experts-in-creating","title":"Can AI Outperform Human Experts in Creating Social Media Creatives?","date":"2024-03-19","arxiv_id":"2404.00018","n_code_links":0,"syntology":null},{"paper":"/paper/deblurdinat-a-lightweight-and-effective","slug":"deblurdinat-a-lightweight-and-effective","title":"DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains","date":"2024-03-19","arxiv_id":"2403.13163","n_code_links":1,"syntology":null},{"paper":"/paper/diffusion-driven-self-supervised-learning-for","slug":"diffusion-driven-self-supervised-learning-for","title":"Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimation","date":"2024-03-19","arxiv_id":"2403.12728","n_code_links":1,"syntology":null},{"paper":"/paper/emotion-recognition-using-transformers-with","slug":"emotion-recognition-using-transformers-with","title":"Emotion Recognition Using Transformers with Masked Learning","date":"2024-03-19","arxiv_id":"2403.13731","n_code_links":1,"syntology":null},{"paper":"/paper/encode-once-and-decode-in-parallel-efficient","slug":"encode-once-and-decode-in-parallel-efficient","title":"Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks","date":"2024-03-19","arxiv_id":"2403.13112","n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-pre-trained-language-models-to","slug":"fine-tuning-pre-trained-language-models-to","title":"Fine-Tuning Pre-trained Language Models to Detect In-Game Trash Talks","date":"2024-03-19","arxiv_id":"2403.15458","n_code_links":0,"syntology":null},{"paper":"/paper/flowerformer-empowering-neural-architecture","slug":"flowerformer-empowering-neural-architecture","title":"FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer","date":"2024-03-19","arxiv_id":"2403.12821","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["y0ngjaenius/cvpr2024_flowerformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"graphere-jointly-multiple-event-event","title":"GraphERE: Jointly Multiple Event-Event Relation Extraction via Graph-Enhanced Event Embeddings","date":"2024-03-19","arxiv_id":"2403.12523","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-eatformer-a-vision-transformer-for","title":"Improved EATFormer: A Vision Transformer for Medical Image Classification","date":"2024-03-19","arxiv_id":"2403.13167","n_code_links":0,"syntology":null},{"paper":"/paper/insight-end-to-end-neuro-symbolic-visual","slug":"insight-end-to-end-neuro-symbolic-visual","title":"End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations","date":"2024-03-19","arxiv_id":"2403.12451","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["liruiluo/nsrl-vision-pub"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/instructing-large-language-models-to-identify","slug":"instructing-large-language-models-to-identify","title":"Instructing Large Language Models to Identify and Ignore Irrelevant Conditions","date":"2024-03-19","arxiv_id":"2403.12744","n_code_links":1,"syntology":null},{"paper":null,"slug":"lhmke-a-large-scale-holistic-multi-subject","title":"LHMKE: A Large-scale Holistic Multi-subject Knowledge Evaluation Benchmark for Chinese Large Language Models","date":"2024-03-19","arxiv_id":"2403.12601","n_code_links":0,"syntology":null},{"paper":"/paper/llmlingua-2-data-distillation-for-efficient","slug":"llmlingua-2-data-distillation-for-efficient","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","date":"2024-03-19","arxiv_id":"2403.12968","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-fusion-method-with-spatiotemporal","title":"Multimodal Fusion Method with Spatiotemporal Sequences and Relationship Learning for Valence-Arousal Estimation","date":"2024-03-19","arxiv_id":"2403.12425","n_code_links":0,"syntology":null},{"paper":null,"slug":"pipelined-biomedical-event-extraction","title":"Pipelined Biomedical Event Extraction Rivaling Joint Learning","date":"2024-03-19","arxiv_id":"2403.12386","n_code_links":0,"syntology":null},{"paper":"/paper/pragmatic-competence-evaluation-of-large","slug":"pragmatic-competence-evaluation-of-large","title":"Pragmatic Competence Evaluation of Large Language Models for the Korean Language","date":"2024-03-19","arxiv_id":"2403.12675","n_code_links":1,"syntology":null},{"paper":null,"slug":"rankprompt-step-by-step-comparisons-make","title":"RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners","date":"2024-03-19","arxiv_id":"2403.12373","n_code_links":0,"syntology":null},{"paper":"/paper/seven-pruning-transformer-model-by-reserving","slug":"seven-pruning-transformer-model-by-reserving","title":"SEVEN: Pruning Transformer Model by Reserving Sentinels","date":"2024-03-19","arxiv_id":"2403.12688","n_code_links":1,"syntology":null},{"paper":null,"slug":"simple-hack-for-transformers-against-heavy","title":"Simple Hack for Transformers against Heavy Long-Text Classification on a Time- and Memory-Limited GPU Service","date":"2024-03-19","arxiv_id":"2403.12563","n_code_links":0,"syntology":null},{"paper":null,"slug":"trustworthiness-of-pretrained-transformers","title":"Quantifying uncertainty in lung cancer segmentation with foundation models applied to mixed-domain datasets","date":"2024-03-19","arxiv_id":"2403.13113","n_code_links":0,"syntology":null}],"record_sha256":"9bce339d224b4309f814b6905e008172d848009a90b117a4809a23ee5fcd205e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}