{"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/70","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":70,"pages_in_order":316,"rows_per_page":100,"rows":[6901,7000],"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/69","next":"/method/attention/papers/71","papers":[{"paper":null,"slug":"look-every-frame-all-at-once-video-ma-2-mba","title":"Look Every Frame All at Once: Video-Ma$^2$mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing","date":"2024-11-29","arxiv_id":"2411.19460","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-cnn-behavioral-embedding-model-for","title":"Multi-task CNN Behavioral Embedding Model For Transaction Fraud Detection","date":"2024-11-29","arxiv_id":"2411.19457","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-domain-specific-post-training-for","title":"On Domain-Specific Post-Training for Multimodal Large Language Models","date":"2024-11-29","arxiv_id":"2411.19930","n_code_links":0,"syntology":null},{"paper":null,"slug":"ragdiffusion-faithful-cloth-generation-via","title":"RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation","date":"2024-11-29","arxiv_id":"2411.19528","n_code_links":0,"syntology":null},{"paper":null,"slug":"rl-milp-solver-a-reinforcement-learning","title":"RL-MILP Solver: A Reinforcement Learning Approach for Solving Mixed-Integer Linear Programs with Graph Neural Networks","date":"2024-11-29","arxiv_id":"2411.19517","n_code_links":0,"syntology":null},{"paper":null,"slug":"sat-hmr-real-time-multi-person-3d-mesh","title":"SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens","date":"2024-11-29","arxiv_id":"2411.19824","n_code_links":0,"syntology":null},{"paper":"/paper/sdr-gnn-spectral-domain-reconstruction-graph","slug":"sdr-gnn-spectral-domain-reconstruction-graph","title":"SDR-GNN: Spectral Domain Reconstruction Graph Neural Network for Incomplete Multimodal Learning in Conversational Emotion Recognition","date":"2024-11-29","arxiv_id":"2411.19822","n_code_links":1,"syntology":null},{"paper":null,"slug":"sims-simulating-human-scene-interactions-with","title":"SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation","date":"2024-11-29","arxiv_id":"2411.19921","n_code_links":0,"syntology":null},{"paper":"/paper/t2vid-translating-long-text-into-multi-image","slug":"t2vid-translating-long-text-into-multi-image","title":"T2Vid: Translating Long Text into Multi-Image is the Catalyst for Video-LLMs","date":"2024-11-29","arxiv_id":"2411.19951","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-santali-linguistic-inclusion-building","title":"Towards Santali Linguistic Inclusion: Building the First Santali-to-English Translation Model using mT5 Transformer and Data Augmentation","date":"2024-11-29","arxiv_id":"2411.19726","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-understanding-retrieval-accuracy-and","title":"Towards Understanding Retrieval Accuracy and Prompt Quality in RAG Systems","date":"2024-11-29","arxiv_id":"2411.19463","n_code_links":0,"syntology":null},{"paper":null,"slug":"train-once-for-all-a-transitional-approach","title":"Train Once for All: A Transitional Approach for Efficient Aspect Sentiment Triplet Extraction","date":"2024-11-29","arxiv_id":"2412.00208","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-agents-with-weakly-supervised","title":"Training Agents with Weakly Supervised Feedback from Large Language Models","date":"2024-11-29","arxiv_id":"2411.19547","n_code_links":0,"syntology":null},{"paper":"/paper/uniform-attention-maps-boosting-image","slug":"uniform-attention-maps-boosting-image","title":"Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing","date":"2024-11-29","arxiv_id":"2411.19652","n_code_links":1,"syntology":null},{"paper":"/paper/v2sflow-video-to-speech-generation-with","slug":"v2sflow-video-to-speech-generation-with","title":"V2SFlow: Video-to-Speech Generation with Speech Decomposition and Rectified Flow","date":"2024-11-29","arxiv_id":"2411.19486","n_code_links":1,"syntology":null},{"paper":null,"slug":"3d-wag-hierarchical-wavelet-guided","title":"3D-WAG: Hierarchical Wavelet-Guided Autoregressive Generation for High-Fidelity 3D Shapes","date":"2024-11-28","arxiv_id":"2411.19037","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-lean-dataset-for-international-math","title":"A Lean Dataset for International Math Olympiad: Small Steps towards Writing Math Proofs for Hard Problems","date":"2024-11-28","arxiv_id":"2411.18872","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-automatic-online-hate-speech","title":"A Survey on Automatic Online Hate Speech Detection in Low-Resource Languages","date":"2024-11-28","arxiv_id":"2411.19017","n_code_links":0,"syntology":null},{"paper":"/paper/amo-sampler-enhancing-text-rendering-with","slug":"amo-sampler-enhancing-text-rendering-with","title":"AMO Sampler: Enhancing Text Rendering with Overshooting","date":"2024-11-28","arxiv_id":"2411.19415","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-extensive-evaluation-of-factual","title":"An Extensive Evaluation of Factual Consistency in Large Language Models for Data-to-Text Generation","date":"2024-11-28","arxiv_id":"2411.19203","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-prompt-generation-and-grounding","title":"Automatic Prompt Generation and Grounding Object Detection for Zero-Shot Image Anomaly Detection","date":"2024-11-28","arxiv_id":"2411.19220","n_code_links":0,"syntology":null},{"paper":null,"slug":"beautimeter-harnessing-gpt-for-assessing","title":"Beautimeter: Harnessing GPT for Assessing Architectural and Urban Beauty based on the 15 Properties of Living Structure","date":"2024-11-28","arxiv_id":"2411.19094","n_code_links":0,"syntology":null},{"paper":"/paper/clip-meets-dino-for-tuning-zero-shot","slug":"clip-meets-dino-for-tuning-zero-shot","title":"CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections","date":"2024-11-28","arxiv_id":"2411.19346","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-spectral-attention-for-unsupervised-rgb","title":"Cross-Spectral Attention for Unsupervised RGB-IR Face Verification and Person Re-identification","date":"2024-11-28","arxiv_id":"2411.19215","n_code_links":0,"syntology":null},{"paper":"/paper/deniahl-in-context-features-influence-llm","slug":"deniahl-in-context-features-influence-llm","title":"DENIAHL: In-Context Features Influence LLM Needle-In-A-Haystack Abilities","date":"2024-11-28","arxiv_id":"2411.19360","n_code_links":1,"syntology":null},{"paper":null,"slug":"dreamblend-advancing-personalized-fine-tuning","title":"DreamBlend: Advancing Personalized Fine-tuning of Text-to-Image Diffusion Models","date":"2024-11-28","arxiv_id":"2411.19390","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-attention-and-bi-directional-fusion","title":"Dynamic Attention and Bi-directional Fusion for Safety Helmet Wearing Detection","date":"2024-11-28","arxiv_id":"2411.19071","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-learning-content-retrieval-with","title":"Efficient Learning Content Retrieval with Knowledge Injection","date":"2024-11-28","arxiv_id":"2412.00125","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-track-anything","slug":"efficient-track-anything","title":"Efficient Track Anything","date":"2024-11-28","arxiv_id":"2411.18933","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":null}},{"paper":"/paper/enhancing-parameter-efficient-fine-tuning-of","slug":"enhancing-parameter-efficient-fine-tuning-of","title":"Enhancing Parameter-Efficient Fine-Tuning of Vision Transformers through Frequency-Based Adaptation","date":"2024-11-28","arxiv_id":"2411.19297","n_code_links":1,"syntology":null},{"paper":"/paper/gru-pfg-extract-inter-stock-correlation-from","slug":"gru-pfg-extract-inter-stock-correlation-from","title":"GRU-PFG: Extract Inter-Stock Correlation from Stock Factors with Graph Neural Network","date":"2024-11-28","arxiv_id":"2411.18997","n_code_links":1,"syntology":null},{"paper":null,"slug":"habit-coach-customising-rag-based-chatbots-to","title":"Habit Coach: Customising RAG-based chatbots to support behavior change","date":"2024-11-28","arxiv_id":"2411.19229","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-multi-subject-consistency-in-open","title":"Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention","date":"2024-11-28","arxiv_id":"2411.19261","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-database-or-poison-base-detecting","title":"RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis","date":"2024-11-28","arxiv_id":"2411.18948","n_code_links":0,"syntology":null},{"paper":"/paper/large-width-penalization-for-neural-network","slug":"large-width-penalization-for-neural-network","title":"Large width penalization for neural network-based prediction interval estimation","date":"2024-11-28","arxiv_id":"2411.19181","n_code_links":1,"syntology":null},{"paper":null,"slug":"locally-focused-face-representation-for","title":"Locally-Focused Face Representation for Sketch-to-Image Generation Using Noise-Induced Refinement","date":"2024-11-28","arxiv_id":"2411.19005","n_code_links":0,"syntology":null},{"paper":null,"slug":"mag-v-a-multi-agent-framework-for-synthetic","title":"MAG-V: A Multi-Agent Framework for Synthetic Data Generation and Verification","date":"2024-11-28","arxiv_id":"2412.04494","n_code_links":0,"syntology":null},{"paper":null,"slug":"marconi-prefix-caching-for-the-era-of-hybrid","title":"Marconi: Prefix Caching for the Era of Hybrid LLMs","date":"2024-11-28","arxiv_id":"2411.19379","n_code_links":0,"syntology":null},{"paper":"/paper/maskris-semantic-distortion-aware-data","slug":"maskris-semantic-distortion-aware-data","title":"MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation","date":"2024-11-28","arxiv_id":"2411.19067","n_code_links":1,"syntology":null},{"paper":null,"slug":"matata-a-weak-supervised-mathematical-tool","title":"MATATA: Weakly Supervised End-to-End MAthematical Tool-Augmented Reasoning for Tabular Applications","date":"2024-11-28","arxiv_id":"2411.18915","n_code_links":0,"syntology":null},{"paper":null,"slug":"pilot-contamination-aware-transformer-for","title":"Pilot Contamination Aware Transformer for Downlink Power Control in Cell-Free Massive MIMO Networks","date":"2024-11-28","arxiv_id":"2411.19020","n_code_links":0,"syntology":null},{"paper":"/paper/random-sampling-for-diffusion-based","slug":"random-sampling-for-diffusion-based","title":"Random Sampling for Diffusion-based Adversarial Purification","date":"2024-11-28","arxiv_id":"2411.18956","n_code_links":1,"syntology":null},{"paper":null,"slug":"smartllmsentry-a-comprehensive-llm-based","title":"SmartLLMSentry: A Comprehensive LLM Based Smart Contract Vulnerability Detection Framework","date":"2024-11-28","arxiv_id":"2411.19234","n_code_links":0,"syntology":null},{"paper":null,"slug":"sowing-information-cultivating-contextual","title":"SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation","date":"2024-11-28","arxiv_id":"2411.19182","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-attention-vectors-generative","title":"Sparse Attention Vectors: Generative Multimodal Model Features Are Discriminative Vision-Language Classifiers","date":"2024-11-28","arxiv_id":"2412.00142","n_code_links":0,"syntology":null},{"paper":null,"slug":"t2sg-traffic-topology-scene-graph-for","title":"T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving","date":"2024-11-28","arxiv_id":"2411.18894","n_code_links":0,"syntology":null},{"paper":"/paper/talking-to-dino-bridging-self-supervised","slug":"talking-to-dino-bridging-self-supervised","title":"Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation","date":"2024-11-28","arxiv_id":"2411.19331","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["lorebianchi98/Talk2DINO"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-impact-of-example-selection-in-few-shot","title":"The Impact of Example Selection in Few-Shot Prompting on Automated Essay Scoring Using GPT Models","date":"2024-11-28","arxiv_id":"2411.18924","n_code_links":0,"syntology":null},{"paper":null,"slug":"tracking-progress-towards-sustainable","title":"Tracking Progress Towards Sustainable Development Goal 6 Using Satellite Imagery","date":"2024-11-28","arxiv_id":"2411.19093","n_code_links":0,"syntology":null},{"paper":null,"slug":"trajectory-attention-for-fine-grained-video","title":"Trajectory Attention for Fine-grained Video Motion Control","date":"2024-11-28","arxiv_id":"2411.19324","n_code_links":0,"syntology":null},{"paper":null,"slug":"unleashing-the-power-of-data-synthesis-in","title":"Unleashing the Power of Data Synthesis in Visual Localization","date":"2024-11-28","arxiv_id":"2412.00138","n_code_links":0,"syntology":null},{"paper":null,"slug":"waterfall-transformer-for-multi-person-pose","title":"Waterfall Transformer for Multi-person Pose Estimation","date":"2024-11-28","arxiv_id":"2411.18944","n_code_links":0,"syntology":null},{"paper":null,"slug":"3d-scene-graph-guided-vision-language-pre","title":"3D Scene Graph Guided Vision-Language Pre-training","date":"2024-11-27","arxiv_id":"2411.18666","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-pipeline-of-neural-symbolic-integration-to","title":"Dspy-based Neural-Symbolic Pipeline to Enhance Spatial Reasoning in LLMs","date":"2024-11-27","arxiv_id":"2411.18564","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-cutting-edge-relation-extraction","title":"A survey on cutting-edge relation extraction techniques based on language models","date":"2024-11-27","arxiv_id":"2411.18157","n_code_links":0,"syntology":null},{"paper":null,"slug":"addressing-bias-in-recommender-systems-a-case","title":"Addressing bias in Recommender Systems: A Case Study on Data Debiasing Techniques in Mobile Games","date":"2024-11-27","arxiv_id":"2411.18716","n_code_links":0,"syntology":null},{"paper":null,"slug":"aegis-an-agent-based-framework-for-general","title":"AEGIS: An Agent-based Framework for General Bug Reproduction from Issue Descriptions","date":"2024-11-27","arxiv_id":"2411.18015","n_code_links":0,"syntology":null},{"paper":"/paper/aligning-knowledge-concepts-to-whole-slide","slug":"aligning-knowledge-concepts-to-whole-slide","title":"Aligning Knowledge Concepts to Whole Slide Images for Precise Histopathology Image Analysis","date":"2024-11-27","arxiv_id":"2411.18101","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-literature-review-using-nlp","title":"Automated Literature Review Using NLP Techniques and LLM-Based Retrieval-Augmented Generation","date":"2024-11-27","arxiv_id":"2411.18583","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-bidirectional-encoder-become-the-ultimate","title":"Can bidirectional encoder become the ultimate winner for downstream applications of foundation models?","date":"2024-11-27","arxiv_id":"2411.18021","n_code_links":0,"syntology":null},{"paper":"/paper/causal-and-local-correlations-based-network","slug":"causal-and-local-correlations-based-network","title":"Causal and Local Correlations Based Network for Multivariate Time Series Classification","date":"2024-11-27","arxiv_id":"2411.18008","n_code_links":1,"syntology":null},{"paper":null,"slug":"chatgpt-as-speechwriter-for-the-french","title":"ChatGPT as speechwriter for the French presidents","date":"2024-11-27","arxiv_id":"2411.18382","n_code_links":0,"syntology":null},{"paper":"/paper/deep-fourier-embedded-network-for-bi-modal","slug":"deep-fourier-embedded-network-for-bi-modal","title":"Deep Fourier-embedded Network for Bi-modal Salient Object Detection","date":"2024-11-27","arxiv_id":"2411.18409","n_code_links":1,"syntology":null},{"paper":null,"slug":"dhcp-detecting-hallucinations-by-cross-modal","title":"DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models","date":"2024-11-27","arxiv_id":"2411.18659","n_code_links":0,"syntology":null},{"paper":null,"slug":"distinctad-distinctive-audio-description","title":"DistinctAD: Distinctive Audio Description Generation in Contexts","date":"2024-11-27","arxiv_id":"2411.18180","n_code_links":0,"syntology":null},{"paper":"/paper/drs-deep-question-reformulation-with","slug":"drs-deep-question-reformulation-with","title":"DRS: Deep Question Reformulation With Structured Output","date":"2024-11-27","arxiv_id":"2411.17993","n_code_links":1,"syntology":null},{"paper":null,"slug":"dualcast-disentangling-aperiodic-events-from","title":"DualCast: Disentangling Aperiodic Events from Traffic Series with a Dual-Branch Model","date":"2024-11-27","arxiv_id":"2411.18286","n_code_links":0,"syntology":null},{"paper":null,"slug":"electrovizqa-how-well-do-multi-modal-llms","title":"ElectroVizQA: How well do Multi-modal LLMs perform in Electronics Visual Question Answering?","date":"2024-11-27","arxiv_id":"2412.00102","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-mmdit-based-text-to-image-models","slug":"enhancing-mmdit-based-text-to-image-models","title":"Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation","date":"2024-11-27","arxiv_id":"2411.18301","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-and-improving-the-robustness-of-1","slug":"evaluating-and-improving-the-robustness-of-1","title":"Evaluating and Improving the Robustness of Security Attack Detectors Generated by LLMs","date":"2024-11-27","arxiv_id":"2411.18216","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-depth-information-for-detecting","title":"Exploring Depth Information for Detecting Manipulated Face Videos","date":"2024-11-27","arxiv_id":"2411.18572","n_code_links":0,"syntology":null},{"paper":null,"slug":"fam-diffusion-frequency-and-attention","title":"FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion","date":"2024-11-27","arxiv_id":"2411.18552","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-large-language-models-for-5","title":"Fine-Tuning Large Language Models for Scientific Text Classification: A Comparative Study","date":"2024-11-27","arxiv_id":"2412.00098","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-small-embeddings-for-elevated","title":"Fine-Tuning Small Embeddings for Elevated Performance","date":"2024-11-27","arxiv_id":"2411.18099","n_code_links":0,"syntology":null},{"paper":null,"slug":"foundation-models-in-radiology-what-how-when","title":"Foundation Models in Radiology: What, How, When, Why and Why Not","date":"2024-11-27","arxiv_id":"2411.18730","n_code_links":0,"syntology":null},{"paper":"/paper/grid-augumented-vision-a-simple-yet-effective","slug":"grid-augumented-vision-a-simple-yet-effective","title":"Grid-augmented vision: A simple yet effective approach for enhanced spatial understanding in multi-modal agents","date":"2024-11-27","arxiv_id":"2411.18270","n_code_links":1,"syntology":null},{"paper":null,"slug":"haat-hybrid-attention-aggregation-transformer","title":"HAAT: Hybrid Attention Aggregation Transformer for Image Super-Resolution","date":"2024-11-27","arxiv_id":"2411.18003","n_code_links":0,"syntology":null},{"paper":null,"slug":"hdi-former-hybrid-dynamic-interaction-ann-snn","title":"HDI-Former: Hybrid Dynamic Interaction ANN-SNN Transformer for Object Detection Using Frames and Events","date":"2024-11-27","arxiv_id":"2411.18658","n_code_links":0,"syntology":null},{"paper":null,"slug":"heterogeneous-relationships-of-subjects-and","title":"Heterogeneous Relationships of Subjects and Shapelets for Semi-supervised Multivariate Series Classification","date":"2024-11-27","arxiv_id":"2411.18043","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightweight-gaze-estimation-model-via-fusion","title":"Lightweight Gaze Estimation Model Via Fusion Global Information","date":"2024-11-27","arxiv_id":"2411.18064","n_code_links":0,"syntology":null},{"paper":"/paper/locate-gat-modeling-multi-scale-local-context","slug":"locate-gat-modeling-multi-scale-local-context","title":"LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition","date":"2024-11-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"mixture-of-cache-conditional-experts-for","title":"Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference","date":"2024-11-27","arxiv_id":"2412.00099","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-gaze-estimation-via-unidirectional","title":"Multi-task Gaze Estimation Via Unidirectional Convolution","date":"2024-11-27","arxiv_id":"2411.18061","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-model-merging-via-adaptive-weight","title":"Multi-Task Model Merging via Adaptive Weight Disentanglement","date":"2024-11-27","arxiv_id":"2411.18729","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-integration-of-longitudinal","slug":"multimodal-integration-of-longitudinal","title":"Multimodal Integration of Longitudinal Noninvasive Diagnostics for Survival Prediction in Immunotherapy Using Deep Learning","date":"2024-11-27","arxiv_id":"2411.18253","n_code_links":1,"syntology":null},{"paper":null,"slug":"mvketr-chest-ct-report-generation-with-multi","title":"MvKeTR: Chest CT Report Generation with Multi-View Perception and Knowledge Enhancement","date":"2024-11-27","arxiv_id":"2411.18309","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-importance-of-code-mixed-embeddings-for","title":"On Importance of Code-Mixed Embeddings for Hate Speech Identification","date":"2024-11-27","arxiv_id":"2411.18577","n_code_links":0,"syntology":null},{"paper":"/paper/paths-a-hierarchical-transformer-for","slug":"paths-a-hierarchical-transformer-for","title":"PATHS: A Hierarchical Transformer for Efficient Whole Slide Image Analysis","date":"2024-11-27","arxiv_id":"2411.18225","n_code_links":1,"syntology":null},{"paper":null,"slug":"perturbation-ontology-based-graph-attention","title":"Perturbation Ontology based Graph Attention Networks","date":"2024-11-27","arxiv_id":"2411.18520","n_code_links":0,"syntology":null},{"paper":null,"slug":"residual-attention-single-head-vision","title":"Residual Attention Single-Head Vision Transformer Network for Rolling Bearing Fault Diagnosis in Noisy Environments","date":"2024-11-27","arxiv_id":"2412.00085","n_code_links":0,"syntology":null},{"paper":null,"slug":"roictrl-boosting-instance-control-for-visual","title":"ROICtrl: Boosting Instance Control for Visual Generation","date":"2024-11-27","arxiv_id":"2411.17949","n_code_links":0,"syntology":null},{"paper":null,"slug":"rpee-heads-a-novel-benchmark-for-pedestrian","title":"RPEE-HEADS: A Novel Benchmark for Pedestrian Head Detection in Crowd Videos","date":"2024-11-27","arxiv_id":"2411.18164","n_code_links":0,"syntology":null},{"paper":"/paper/spectral-spatial-transformer-with-active","slug":"spectral-spatial-transformer-with-active","title":"Spectral-Spatial Transformer with Active Transfer Learning for Hyperspectral Image Classification","date":"2024-11-27","arxiv_id":"2411.18115","n_code_links":1,"syntology":null},{"paper":"/paper/streamlining-prediction-in-bayesian-deep","slug":"streamlining-prediction-in-bayesian-deep","title":"Streamlining Prediction in Bayesian Deep Learning","date":"2024-11-27","arxiv_id":"2411.18425","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["aaltoml/suq"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"taptrv3-spatial-and-temporal-context-foster","title":"TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video","date":"2024-11-27","arxiv_id":"2411.18671","n_code_links":0,"syntology":null},{"paper":"/paper/the-importance-of-visual-modelling-languages","slug":"the-importance-of-visual-modelling-languages","title":"The importance of visual modelling languages in generative software engineering","date":"2024-11-27","arxiv_id":"2411.17976","n_code_links":1,"syntology":null},{"paper":"/paper/training-and-evaluating-language-models-with","slug":"training-and-evaluating-language-models-with","title":"Training and Evaluating Language Models with Template-based Data Generation","date":"2024-11-27","arxiv_id":"2411.18104","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["iiis-ai/templatemath"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/training-noise-token-pruning","slug":"training-noise-token-pruning","title":"Training Noise Token Pruning","date":"2024-11-27","arxiv_id":"2411.18092","n_code_links":1,"syntology":null},{"paper":"/paper/ts3-codec-transformer-based-simple-streaming","slug":"ts3-codec-transformer-based-simple-streaming","title":"TS3-Codec: Transformer-Based Simple Streaming Single Codec","date":"2024-11-27","arxiv_id":"2411.18803","n_code_links":1,"syntology":null},{"paper":null,"slug":"unpacking-the-individual-components-of","title":"Unpacking the Individual Components of Diffusion Policy","date":"2024-11-27","arxiv_id":"2412.00084","n_code_links":0,"syntology":null}],"record_sha256":"ab9f3b682f45378c77dedb3a9c9e5edc21f237c25f383ff7c9c0f8c471db2140","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}