{"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/27","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":27,"pages_in_order":249,"rows_per_page":100,"rows":[2601,2700],"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/26","next":"/method/multi-head-attention/papers/28","papers":[{"paper":null,"slug":"spiking-transformer-introducing-accurate-1","title":"Spiking Transformer: Introducing Accurate Addition-Only Spiking Self-Attention for Transformer","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"task-aware-cross-modal-feature-refinement","title":"Task-aware Cross-modal Feature Refinement Transformer with Large Language Models for Visual Grounding","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"texgarment-consistent-garment-uv-texture","title":"TexGarment: Consistent Garment UV Texture Generation via Efficient 3D Structure-Guided Diffusion Transformer","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/volformer-explore-more-comprehensive-cube","slug":"volformer-explore-more-comprehensive-cube","title":"VolFormer: Explore More Comprehensive Cube Interaction for Hyperspectral Image Restoration and Beyond","date":"2025-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/wavelet-and-prototype-augmented-query-based","slug":"wavelet-and-prototype-augmented-query-based","title":"Wavelet and Prototype Augmented Query-based Transformer for Pixel-level Surface Defect Detection","date":"2025-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"yo-chameleon-personalized-vision-and-language","title":"Yo'Chameleon: Personalized Vision and Language Generation","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-shape-guided-transformer-network-for","title":"A Novel Shape Guided Transformer Network for Instance Segmentation in Remote Sensing Images","date":"2024-12-31","arxiv_id":"2501.00360","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-on-context-length-and-efficient","title":"A Study on Context Length and Efficient Transformers for Biomedical Image Analysis","date":"2024-12-31","arxiv_id":"2501.00619","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-lung-nodule-segmentation-and","title":"Advanced Lung Nodule Segmentation and Classification for Early Detection of Lung Cancer using SAM and Transfer Learning","date":"2024-12-31","arxiv_id":"2501.00586","n_code_links":0,"syntology":null},{"paper":"/paper/crrg-clip-automatic-generation-of-chest","slug":"crrg-clip-automatic-generation-of-chest","title":"CRRG-CLIP: Automatic Generation of Chest Radiology Reports and Classification of Chest Radiographs","date":"2024-12-31","arxiv_id":"2501.01989","n_code_links":1,"syntology":null},{"paper":null,"slug":"dementia-detection-using-multi-modal-methods","title":"Dementia Detection using Multi-modal Methods on Audio Data","date":"2024-12-31","arxiv_id":"2501.00465","n_code_links":0,"syntology":null},{"paper":null,"slug":"echoes-in-ai-quantifying-lack-of-plot","title":"Echoes in AI: Quantifying Lack of Plot Diversity in LLM Outputs","date":"2024-12-31","arxiv_id":"2501.00273","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-variability-in-fine-tuned-models","title":"Exploring Variability in Fine-Tuned Models for Text Classification with DistilBERT","date":"2024-12-31","arxiv_id":"2501.00241","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-on-clinic-depression-assessment-an-llm","title":"GPT-4 on Clinic Depression Assessment: An LLM-Based Pilot Study","date":"2024-12-31","arxiv_id":"2501.00199","n_code_links":0,"syntology":null},{"paper":null,"slug":"innovative-silicosis-and-pneumonia","title":"Innovative Silicosis and Pneumonia Classification: Leveraging Graph Transformer Post-hoc Modeling and Ensemble Techniques","date":"2024-12-31","arxiv_id":"2501.00520","n_code_links":0,"syntology":null},{"paper":null,"slug":"main-rag-multi-agent-filtering-retrieval","title":"MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation","date":"2024-12-31","arxiv_id":"2501.00332","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-visual-language-priors-in-vlms","title":"Probing Visual Language Priors in VLMs","date":"2024-12-31","arxiv_id":"2501.00569","n_code_links":0,"syntology":null},{"paper":"/paper/rag-instruct-boosting-llms-with-diverse","slug":"rag-instruct-boosting-llms-with-diverse","title":"RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions","date":"2024-12-31","arxiv_id":"2501.00353","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":0,"n_instrument":6,"unverified":0,"pointer_only":0,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["freedomintelligence/rag-instruct"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"reformer-generating-radio-fakes-for-data","title":"ReFormer: Generating Radio Fakes for Data Augmentation","date":"2024-12-31","arxiv_id":"2501.00282","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-with-graphs","title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","date":"2024-12-31","arxiv_id":"2501.00309","n_code_links":0,"syntology":null},{"paper":"/paper/storm-spatio-temporal-reconstruction-model","slug":"storm-spatio-temporal-reconstruction-model","title":"STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes","date":"2024-12-31","arxiv_id":"2501.00602","n_code_links":1,"syntology":null},{"paper":null,"slug":"why-are-positional-encodings-nonessential-for","title":"Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? Revisiting a Petroglyph","date":"2024-12-31","arxiv_id":"2501.00659","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-unsupervised-anomaly-detection-in","title":"An Unsupervised Anomaly Detection in Electricity Consumption Using Reinforcement Learning and Time Series Forest Based Framework","date":"2024-12-30","arxiv_id":"2501.00107","n_code_links":0,"syntology":null},{"paper":"/paper/averagelinear-enhance-long-term-time-series","slug":"averagelinear-enhance-long-term-time-series","title":"AverageTime: Enhance Long-Term Time Series Forecasting with Simple Averaging","date":"2024-12-30","arxiv_id":"2412.20727","n_code_links":1,"syntology":null},{"paper":null,"slug":"casesumm-a-large-scale-dataset-for-long","title":"CaseSumm: A Large-Scale Dataset for Long-Context Summarization from U.S. Supreme Court Opinions","date":"2024-12-30","arxiv_id":"2501.00097","n_code_links":0,"syntology":null},{"paper":"/paper/facilitating-large-language-model-russian","slug":"facilitating-large-language-model-russian","title":"Facilitating large language model Russian adaptation with Learned Embedding Propagation","date":"2024-12-30","arxiv_id":"2412.21140","n_code_links":1,"syntology":null},{"paper":"/paper/plancraft-an-evaluation-dataset-for-planning","slug":"plancraft-an-evaluation-dataset-for-planning","title":"Plancraft: an evaluation dataset for planning with LLM agents","date":"2024-12-30","arxiv_id":"2412.21033","n_code_links":1,"syntology":null},{"paper":null,"slug":"position-information-emerges-in-causal","title":"Position Information Emerges in Causal Transformers Without Positional Encodings via Similarity of Nearby Embeddings","date":"2024-12-30","arxiv_id":"2501.00073","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-classification-neural-networks-vs","title":"Text Classification: Neural Networks VS Machine Learning Models VS Pre-trained Models","date":"2024-12-30","arxiv_id":"2412.21022","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-performance-of-advanced-nlp","title":"Comparative Performance of Advanced NLP Models and LLMs in Multilingual Geo-Entity Detection","date":"2024-12-29","arxiv_id":"2412.20414","n_code_links":0,"syntology":null},{"paper":"/paper/electra-and-gpt-4o-cost-effective-partners","slug":"electra-and-gpt-4o-cost-effective-partners","title":"ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis","date":"2024-12-29","arxiv_id":"2501.00062","n_code_links":1,"syntology":null},{"paper":"/paper/freqmixformerv2-lightweight-frequency-aware","slug":"freqmixformerv2-lightweight-frequency-aware","title":"FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition","date":"2024-12-29","arxiv_id":"2412.20621","n_code_links":1,"syntology":null},{"paper":null,"slug":"matey-multiscale-adaptive-foundation-models","title":"MATEY: multiscale adaptive foundation models for spatiotemporal physical systems","date":"2024-12-29","arxiv_id":"2412.20601","n_code_links":0,"syntology":null},{"paper":null,"slug":"nlp-based-regulatory-compliance-using-gpt-4-0","title":"NLP-based Regulatory Compliance -- Using GPT 4.0 to Decode Regulatory Documents","date":"2024-12-29","arxiv_id":"2412.20602","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-adversarial-robustness-of-language-models","title":"On Adversarial Robustness of Language Models in Transfer Learning","date":"2024-12-29","arxiv_id":"2501.00066","n_code_links":0,"syntology":null},{"paper":"/paper/open-sora-democratizing-efficient-video","slug":"open-sora-democratizing-efficient-video","title":"Open-Sora: Democratizing Efficient Video Production for All","date":"2024-12-29","arxiv_id":"2412.20404","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":["hpcaitech/open-sora"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/understanding-the-impact-of-confidence-in","slug":"understanding-the-impact-of-confidence-in","title":"Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical Domain","date":"2024-12-29","arxiv_id":"2412.20309","n_code_links":1,"syntology":null},{"paper":"/paper/a-fuzzy-rank-based-ensemble-of-cnn-models-for-1","slug":"a-fuzzy-rank-based-ensemble-of-cnn-models-for-1","title":"A fuzzy rank-based ensemble of CNN models for MRI segmentation","date":"2024-12-28","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-robustness-for-deep-learning","title":"Adversarial Robustness for Deep Learning-based Wildfire Prediction Models","date":"2024-12-28","arxiv_id":"2412.20006","n_code_links":0,"syntology":null},{"paper":null,"slug":"ddd-gendt-dynamic-data-driven-generative","title":"DDD-GenDT: Dynamic Data-driven Generative Digital Twin Framework","date":"2024-12-28","arxiv_id":"2501.00051","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilled-transformers-with-locally-enhanced","title":"Distilled Transformers with Locally Enhanced Global Representations for Face Forgery Detection","date":"2024-12-28","arxiv_id":"2412.20156","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-multi-agent-collaboration-with-tool","title":"Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering","date":"2024-12-28","arxiv_id":"2412.20145","n_code_links":0,"syntology":null},{"paper":null,"slug":"real-time-calibration-model-for-low-cost","title":"Real-time Calibration Model for Low-cost Sensor in Fine-grained Time series","date":"2024-12-28","arxiv_id":"2412.20170","n_code_links":0,"syntology":null},{"paper":"/paper/segkan-high-resolution-medical-image","slug":"segkan-high-resolution-medical-image","title":"SegKAN: High-Resolution Medical Image Segmentation with Long-Distance Dependencies","date":"2024-12-28","arxiv_id":"2412.19990","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-contrastive-meta-learning","title":"Transformer-Based Contrastive Meta-Learning For Low-Resource Generalizable Activity Recognition","date":"2024-12-28","arxiv_id":"2412.20290","n_code_links":0,"syntology":null},{"paper":"/paper/velora-a-low-rank-adaptation-approach-for","slug":"velora-a-low-rank-adaptation-approach-for","title":"VELoRA: A Low-Rank Adaptation Approach for Efficient RGB-Event based Recognition","date":"2024-12-28","arxiv_id":"2412.20064","n_code_links":1,"syntology":null},{"paper":"/paper/vistabnet-adapting-vision-transformers-for","slug":"vistabnet-adapting-vision-transformers-for","title":"VisTabNet: Adapting Vision Transformers for Tabular Data","date":"2024-12-28","arxiv_id":"2501.00057","n_code_links":1,"syntology":null},{"paper":"/paper/yad-leveraging-t5-for-improved-automatic","slug":"yad-leveraging-t5-for-improved-automatic","title":"YAD: Leveraging T5 for Improved Automatic Diacritization of Yorùbá Text","date":"2024-12-28","arxiv_id":"2412.20218","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-text-classification-methods-for","title":"Assessing Text Classification Methods for Cyberbullying Detection on Social Media Platforms","date":"2024-12-27","arxiv_id":"2412.19928","n_code_links":0,"syntology":null},{"paper":"/paper/drivingworld-constructingworld-model-for","slug":"drivingworld-constructingworld-model-for","title":"DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT","date":"2024-12-27","arxiv_id":"2412.19505","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yvanyin/drivingworld"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"feature-alignment-based-knowledge","title":"Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models","date":"2024-12-27","arxiv_id":"2412.19449","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-uncertainty-based-evidential","slug":"generalized-uncertainty-based-evidential","title":"Generalized Uncertainty-Based Evidential Fusion with Hybrid Multi-Head Attention for Weak-Supervised Temporal Action Localization","date":"2024-12-27","arxiv_id":"2412.19418","n_code_links":1,"syntology":null},{"paper":"/paper/generative-pretrained-embedding-and","slug":"generative-pretrained-embedding-and","title":"Generative Pretrained Embedding and Hierarchical Irregular Time Series Representation for Daily Living Activity Recognition","date":"2024-12-27","arxiv_id":"2412.19732","n_code_links":1,"syntology":null},{"paper":"/paper/gradient-weight-normalized-low-rank","slug":"gradient-weight-normalized-low-rank","title":"Gradient Weight-normalized Low-rank Projection for Efficient LLM Training","date":"2024-12-27","arxiv_id":"2412.19616","n_code_links":1,"syntology":null},{"paper":null,"slug":"hidformer-transformer-style-neural-network-in","title":"Hidformer: Transformer-Style Neural Network in Stock Price Forecasting","date":"2024-12-27","arxiv_id":"2412.19932","n_code_links":0,"syntology":null},{"paper":"/paper/long-context-vs-rag-for-llms-an-evaluation","slug":"long-context-vs-rag-for-llms-an-evaluation","title":"Long Context vs. RAG for LLMs: An Evaluation and Revisits","date":"2024-12-27","arxiv_id":"2501.01880","n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-local-global-dependencies-for","slug":"optimizing-local-global-dependencies-for","title":"Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimation","date":"2024-12-27","arxiv_id":"2412.19676","n_code_links":1,"syntology":null},{"paper":"/paper/revisiting-pca-for-time-series-reduction-in","slug":"revisiting-pca-for-time-series-reduction-in","title":"Revisiting PCA for time series reduction in temporal dimension","date":"2024-12-27","arxiv_id":"2412.19423","n_code_links":1,"syntology":null},{"paper":null,"slug":"text2insight-transform-natural-language-text","title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","date":"2024-12-27","arxiv_id":"2412.19718","n_code_links":0,"syntology":null},{"paper":"/paper/toward-adaptive-reasoning-in-large-language-1","slug":"toward-adaptive-reasoning-in-large-language-1","title":"Toward Adaptive Reasoning in Large Language Models with Thought Rollback","date":"2024-12-27","arxiv_id":"2412.19707","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":["iQua/llmpebase"],"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/context-aware-deep-learning-for-multi-modal","slug":"context-aware-deep-learning-for-multi-modal","title":"Context-Aware Deep Learning for Multi Modal Depression Detection","date":"2024-12-26","arxiv_id":"2412.19209","n_code_links":1,"syntology":null},{"paper":"/paper/dapointr-domain-adaptive-point-transformer","slug":"dapointr-domain-adaptive-point-transformer","title":"DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion","date":"2024-12-26","arxiv_id":"2412.19062","n_code_links":1,"syntology":null},{"paper":null,"slug":"dual-channel-multi-attention-in-vit-for","title":"Dual Channel Multi-Attention in ViT for Biometric Authentication using Forehead Subcutaneous Vein Pattern and Periocular Pattern","date":"2024-12-26","arxiv_id":"2412.19160","n_code_links":0,"syntology":null},{"paper":null,"slug":"indonesian-english-code-switching-speech","title":"Indonesian-English Code-Switching Speech Synthesizer Utilizing Multilingual STEN-TTS and Bert LID","date":"2024-12-26","arxiv_id":"2412.19043","n_code_links":0,"syntology":null},{"paper":"/paper/medec-a-benchmark-for-medical-error-detection","slug":"medec-a-benchmark-for-medical-error-detection","title":"MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes","date":"2024-12-26","arxiv_id":"2412.19260","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-matrix-factorization-attention","title":"Multi-matrix Factorization Attention","date":"2024-12-26","arxiv_id":"2412.19255","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-expressiveness-and-length","slug":"on-the-expressiveness-and-length","title":"On the Expressiveness and Length Generalization of Selective State-Space Models on Regular Languages","date":"2024-12-26","arxiv_id":"2412.19350","n_code_links":1,"syntology":null},{"paper":"/paper/rag-with-differential-privacy","slug":"rag-with-differential-privacy","title":"RAG with Differential Privacy","date":"2024-12-26","arxiv_id":"2412.19291","n_code_links":1,"syntology":null},{"paper":"/paper/reversed-in-time-a-novel-temporal-emphasized","slug":"reversed-in-time-a-novel-temporal-emphasized","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","date":"2024-12-26","arxiv_id":"2412.19178","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-trading-with-large-language-models","title":"Sentiment trading with large language models","date":"2024-12-26","arxiv_id":"2412.19245","n_code_links":0,"syntology":null},{"paper":"/paper/spectralkd-understanding-and-optimizing","slug":"spectralkd-understanding-and-optimizing","title":"SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral Analysis","date":"2024-12-26","arxiv_id":"2412.19055","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-based-wireless-capsule-endoscopy","slug":"transformer-based-wireless-capsule-endoscopy","title":"Transformer-Based Wireless Capsule Endoscopy Bleeding Tissue Detection and Classification","date":"2024-12-26","arxiv_id":"2412.19218","n_code_links":1,"syntology":null},{"paper":null,"slug":"adopting-trustworthy-ai-for-sleep-disorder","title":"Adopting Trustworthy AI for Sleep Disorder Prediction: Deep Time Series Analysis with Temporal Attention Mechanism and Counterfactual Explanations","date":"2024-12-25","arxiv_id":"2412.18971","n_code_links":0,"syntology":null},{"paper":"/paper/dcis-efficient-length-extrapolation-of-llms","slug":"dcis-efficient-length-extrapolation-of-llms","title":"DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor Search","date":"2024-12-25","arxiv_id":"2412.18811","n_code_links":1,"syntology":null},{"paper":"/paper/distortion-aware-adversarial-attacks-on","slug":"distortion-aware-adversarial-attacks-on","title":"Distortion-Aware Adversarial Attacks on Bounding Boxes of Object Detectors","date":"2024-12-25","arxiv_id":"2412.18815","n_code_links":1,"syntology":null},{"paper":null,"slug":"ec-diffuser-multi-object-manipulation-via","title":"EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation","date":"2024-12-25","arxiv_id":"2412.18907","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-adversarial-robustness-of-3","title":"Evaluating the Adversarial Robustness of Detection Transformers","date":"2024-12-25","arxiv_id":"2412.18718","n_code_links":0,"syntology":null},{"paper":null,"slug":"hand-hierarchical-attention-network-for-multi","title":"HAND: Hierarchical Attention Network for Multi-Scale Handwritten Document Recognition and Layout Analysis","date":"2024-12-25","arxiv_id":"2412.18981","n_code_links":0,"syntology":null},{"paper":null,"slug":"injecting-bias-into-text-classification","title":"Injecting Bias into Text Classification Models using Backdoor Attacks","date":"2024-12-25","arxiv_id":"2412.18975","n_code_links":0,"syntology":null},{"paper":null,"slug":"ister-inverted-seasonal-trend-decomposition","title":"Ister: Inverted Seasonal-Trend Decomposition Transformer for Explainable Multivariate Time Series Forecasting","date":"2024-12-25","arxiv_id":"2412.18798","n_code_links":0,"syntology":null},{"paper":"/paper/mtcae-dfer-multi-task-cascaded-autoencoder","slug":"mtcae-dfer-multi-task-cascaded-autoencoder","title":"MTCAE-DFER: Multi-Task Cascaded Autoencoder for Dynamic Facial Expression Recognition","date":"2024-12-25","arxiv_id":"2412.18988","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimizing-large-language-models-with-an","title":"Optimizing Large Language Models with an Enhanced LoRA Fine-Tuning Algorithm for Efficiency and Robustness in NLP Tasks","date":"2024-12-25","arxiv_id":"2412.18729","n_code_links":0,"syntology":null},{"paper":null,"slug":"position-aware-graph-transformer-for","title":"Position-aware Graph Transformer for Recommendation","date":"2024-12-25","arxiv_id":"2412.18731","n_code_links":0,"syntology":null},{"paper":null,"slug":"resource-efficient-transformer-architecture","title":"Resource-Efficient Transformer Architecture: Optimizing Memory and Execution Time for Real-Time Applications","date":"2024-12-25","arxiv_id":"2501.00042","n_code_links":0,"syntology":null},{"paper":null,"slug":"saflite-fuzzing-autonomous-systems-via-large","title":"SAFLITE: Fuzzing Autonomous Systems via Large Language Models","date":"2024-12-25","arxiv_id":"2412.18727","n_code_links":0,"syntology":null},{"paper":null,"slug":"unic-adapter-unified-image-instruction","title":"UNIC-Adapter: Unified Image-instruction Adapter with Multi-modal Transformer for Image Generation","date":"2024-12-25","arxiv_id":"2412.18928","n_code_links":0,"syntology":null},{"paper":null,"slug":"unified-local-and-global-attention","title":"Unified Local and Global Attention Interaction Modeling for Vision Transformers","date":"2024-12-25","arxiv_id":"2412.18778","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-for-automated","title":"Using Large Language Models for Automated Grading of Student Writing about Science","date":"2024-12-25","arxiv_id":"2412.18719","n_code_links":0,"syntology":null},{"paper":null,"slug":"whose-morality-do-they-speak-unraveling","title":"Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Models","date":"2024-12-25","arxiv_id":"2412.18863","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-explainability-in-neural-machine","title":"Advancing Explainability in Neural Machine Translation: Analytical Metrics for Attention and Alignment Consistency","date":"2024-12-24","arxiv_id":"2412.18669","n_code_links":0,"syntology":null},{"paper":null,"slug":"autosculpt-a-pattern-based-model-auto-pruning","title":"AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learning","date":"2024-12-24","arxiv_id":"2412.18091","n_code_links":0,"syntology":null},{"paper":"/paper/comprehensive-assessment-of-bert-based","slug":"comprehensive-assessment-of-bert-based","title":"Comprehensive Assessment of BERT-Based Methods for Predicting Antimicrobial Peptides","date":"2024-12-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/decentralized-intelligence-in-gamefi-embodied","slug":"decentralized-intelligence-in-gamefi-embodied","title":"Decentralized Intelligence in GameFi: Embodied AI Agents and the Convergence of DeFi and Virtual Ecosystems","date":"2024-12-24","arxiv_id":"2412.18601","n_code_links":1,"syntology":null},{"paper":"/paper/ditctrl-exploring-attention-control-in-multi","slug":"ditctrl-exploring-attention-control-in-multi","title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation","date":"2024-12-24","arxiv_id":"2412.18597","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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":["tencentarc/ditctrl"],"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","unlocated"]}}},{"paper":null,"slug":"do-language-models-understand-the-cognitive","title":"Do Language Models Understand the Cognitive Tasks Given to Them? Investigations with the N-Back Paradigm","date":"2024-12-24","arxiv_id":"2412.18120","n_code_links":0,"syntology":null},{"paper":"/paper/ervd-an-efficient-and-robust-vit-based","slug":"ervd-an-efficient-and-robust-vit-based","title":"ERVD: An Efficient and Robust ViT-Based Distillation Framework for Remote Sensing Image Retrieval","date":"2024-12-24","arxiv_id":"2412.18136","n_code_links":1,"syntology":null},{"paper":null,"slug":"evopat-a-multi-llm-based-patents","title":"EvoPat: A Multi-LLM-based Patents Summarization and Analysis Agent","date":"2024-12-24","arxiv_id":"2412.18100","n_code_links":0,"syntology":null},{"paper":null,"slug":"gear-graph-enhanced-agent-for-retrieval","title":"GeAR: Graph-enhanced Agent for Retrieval-augmented Generation","date":"2024-12-24","arxiv_id":"2412.18431","n_code_links":0,"syntology":null},{"paper":null,"slug":"htr-jand-handwritten-text-recognition-with","title":"HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge Distillation","date":"2024-12-24","arxiv_id":"2412.18524","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-factuality-with-explicit-working","title":"Improving Factuality with Explicit Working Memory","date":"2024-12-24","arxiv_id":"2412.18069","n_code_links":0,"syntology":null}],"record_sha256":"158fb9d9de362b3f1cc036e18b7a889a4896b701520ab2bd18b70aadc7cb5a7e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}