{"url":"/method/focus","slug":"focus","name":"Focus","full_name":"Focus","full_name_withheld":false,"description_markdown":null,"description_state":"absent","introduced_year":null,"introduced_by":{"title":"Focus Your Attention (with Adaptive IIR Filters)","paper":"/paper/2305-14952","first_author":"Shahar Lutati","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/2305-14952"},"source":{"url":"https://arxiv.org/abs/2305.14952v2","title":"Focus Your Attention (with Adaptive IIR Filters)","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":15340,"archive_num_papers":15341,"papers_newest_first":[{"paper":"/paper/efficient-deployment-of-spiking-neural","title":"Efficient Deployment of Spiking Neural Networks on SpiNNaker2 for DVS Gesture Recognition Using Neuromorphic Intermediate Representation","date":"2025-09-04","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/a-fuzzy-approach-to-project-success-measuring","title":"A Fuzzy Approach to Project Success: Measuring What Matters","date":"2025-07-16","arxiv_id":"2507.12653","n_code_links":1,"syntology":null},{"paper":"/paper/instructflip-exploring-unified-vision","title":"InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofing","date":"2025-07-16","arxiv_id":"2507.12060","n_code_links":1,"syntology":null},{"paper":"/paper/attributes-shape-the-embedding-space-of-face","title":"Attributes Shape the Embedding Space of Face Recognition Models","date":"2025-07-15","arxiv_id":"2507.11372","n_code_links":1,"syntology":null},{"paper":null,"title":"Functional Emotion Modeling in Biomimetic Reinforcement Learning","date":"2025-07-15","arxiv_id":"2507.11027","n_code_links":0,"syntology":null},{"paper":"/paper/implementing-adaptations-for-vision","title":"Implementing Adaptations for Vision AutoRegressive Model","date":"2025-07-15","arxiv_id":"2507.11441","n_code_links":1,"syntology":{"ran":0,"of":8,"unverified":8,"pointer_only":8}},{"paper":null,"title":"Multi-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs","date":"2025-07-15","arxiv_id":"2507.11112","n_code_links":0,"syntology":null},{"paper":"/paper/optimal-sensor-scheduling-and-selection-for","title":"Optimal Sensor Scheduling and Selection for Continuous-Discrete Kalman Filtering with Auxiliary Dynamics","date":"2025-07-15","arxiv_id":"2507.11240","n_code_links":1,"syntology":null},{"paper":null,"title":"Pricing energy spread options with variance gamma-driven Ornstein-Uhlenbeck dynamics","date":"2025-07-15","arxiv_id":"2507.11480","n_code_links":0,"syntology":null},{"paper":"/paper/robust-multi-task-gradient-boosting","title":"Robust-Multi-Task Gradient Boosting","date":"2025-07-15","arxiv_id":"2507.11411","n_code_links":1,"syntology":null},{"paper":null,"title":"Tactical Decision for Multi-UGV Confrontation with a Vision-Language Model-Based Commander","date":"2025-07-15","arxiv_id":"2507.11079","n_code_links":0,"syntology":null},{"paper":null,"title":"The model is the message: Lightweight convolutional autoencoders applied to noisy imaging data for planetary science and astrobiology","date":"2025-07-15","arxiv_id":"2507.11400","n_code_links":0,"syntology":null},{"paper":null,"title":"Turning Sand to Gold: Recycling Data to Bridge On-Policy and Off-Policy Learning via Causal Bound","date":"2025-07-15","arxiv_id":"2507.11269","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-robustness-and-generalization","title":"Bridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix Approach","date":"2025-07-14","arxiv_id":"2507.10330","n_code_links":1,"syntology":null},{"paper":null,"title":"Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning","date":"2025-07-14","arxiv_id":"2507.10348","n_code_links":0,"syntology":null},{"paper":"/paper/graph-world-model","title":"Graph World Model","date":"2025-07-14","arxiv_id":"2507.10539","n_code_links":1,"syntology":null},{"paper":"/paper/reasoning-or-memorization-unreliable-results","title":"Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination","date":"2025-07-14","arxiv_id":"2507.10532","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":1}},{"paper":null,"title":"Unsupervised Methods for Video Quality Improvement: A Survey of Restoration and Enhancement Techniques","date":"2025-07-11","arxiv_id":"2507.08375","n_code_links":0,"syntology":null},{"paper":null,"title":"Bradley-Terry and Multi-Objective Reward Modeling Are Complementary","date":"2025-07-10","arxiv_id":"2507.07375","n_code_links":0,"syntology":null},{"paper":"/paper/learning-collective-variables-from-time","title":"Learning Collective Variables from Time-lagged Generation","date":"2025-07-10","arxiv_id":"2507.07390","n_code_links":1,"syntology":null},{"paper":null,"title":"Quantum Federated Learning for Multimodal Data: A Modality-Agnostic Approach","date":"2025-07-10","arxiv_id":"2507.08217","n_code_links":0,"syntology":null},{"paper":"/paper/boosting-parameter-efficiency-in-llm-based","title":"Boosting Parameter Efficiency in LLM-Based Recommendation through Sophisticated Pruning","date":"2025-07-09","arxiv_id":"2507.07064","n_code_links":1,"syntology":null},{"paper":"/paper/ms-dpps-multi-source-determinantal-point","title":"MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval","date":"2025-07-09","arxiv_id":"2507.06654","n_code_links":1,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":1}},{"paper":null,"title":"Speak2Sign3D: A Multi-modal Pipeline for English Speech to American Sign Language Animation","date":"2025-07-09","arxiv_id":"2507.06530","n_code_links":0,"syntology":null},{"paper":null,"title":"What Demands Attention in Urban Street Scenes? From Scene Understanding towards Road Safety: A Survey of Vision-driven Datasets and Studies","date":"2025-07-09","arxiv_id":"2507.06513","n_code_links":0,"syntology":null},{"paper":null,"title":"DreamArt: Generating Interactable Articulated Objects from a Single Image","date":"2025-07-08","arxiv_id":"2507.05763","n_code_links":0,"syntology":null},{"paper":null,"title":"Feature-Based vs. GAN-Based Learning from Demonstrations: When and Why","date":"2025-07-08","arxiv_id":"2507.05906","n_code_links":0,"syntology":null},{"paper":"/paper/high-resolution-visual-reasoning-via-multi","title":"High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning","date":"2025-07-08","arxiv_id":"2507.05920","n_code_links":1,"syntology":null},{"paper":null,"title":"Identifiability in Causal Abstractions: A Hierarchy of Criteria","date":"2025-07-08","arxiv_id":"2507.06213","n_code_links":0,"syntology":null},{"paper":"/paper/langmamba-a-language-driven-mamba-framework","title":"LangMamba: A Language-driven Mamba Framework for Low-dose CT Denoising with Vision-language Models","date":"2025-07-08","arxiv_id":"2507.06140","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":735},{"task":"/task/language-modeling","name":"Language Modeling","papers":584},{"task":"/task/retrieval","name":"Retrieval","papers":504},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":465},{"task":"/task/decision-making","name":"Decision Making","papers":445},{"task":"/task/question-answering","name":"Question Answering","papers":441},{"task":"/task/large-language-model","name":"Large Language Model","papers":438},{"task":"/task/object-detection","name":"Object Detection","papers":364},{"task":"/task/object-detection-1","name":"object-detection","papers":356},{"task":"/task/representation-learning","name":"Representation Learning","papers":351},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":345},{"task":"/task/segmentation","name":"Segmentation","papers":325},{"task":"/task/object","name":"Object","papers":319},{"task":"/task/benchmarking","name":"Benchmarking","papers":314},{"task":"/task/diversity","name":"Diversity","papers":301},{"task":"/task/fairness","name":"Fairness","papers":299},{"task":"/task/image-generation","name":"Image Generation","papers":288},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":274},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":260},{"task":"/task/denoising","name":"Denoising","papers":258}],"tasks_shown":20,"n_tasks":1935,"usage_by_year":[{"year":"2023","papers":3769},{"year":"2024","papers":7710},{"year":"2025","papers":3861}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/focus"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}