{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2106.03106","title":"Uformer: A General U-Shaped Transformer for Image Restoration","created":"2021-06-06","cited_by_count":866},{"id":"2102.02808","title":"Multi-Stage Progressive Image Restoration","created":"2021-02-04","cited_by_count":816},{"id":"1711.06077","title":"The Perception-Distortion Tradeoff","created":"2017-11-16","cited_by_count":587},{"id":"2204.08958","title":"MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment","created":"2022-04-19","cited_by_count":522},{"id":"1712.04143","title":"Benchmarking Single Image Dehazing and Beyond","created":"2017-12-12","cited_by_count":447},{"id":"1907.07484","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","created":"2019-07-17","cited_by_count":336},{"id":"2003.06792","title":"Learning Enriched Features for Real Image Restoration and Enhancement","created":"2020-03-15","cited_by_count":312},{"id":"2201.02973","title":"MAXIM: Multi-Axis MLP for Image Processing","created":"2022-01-09","cited_by_count":302},{"id":"2204.03883","title":"Vision Transformers for Single Image Dehazing","created":"2022-04-08","cited_by_count":260},{"id":"2401.16468","title":"InstructIR: High-Quality Image Restoration Following Human Instructions","created":"2024-01-29","cited_by_count":140},{"id":"2310.10123","title":"AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion","created":"2023-10-16","cited_by_count":100},{"id":"2108.13610","title":"Iterative Filter Adaptive Network for Single Image Defocus Deblurring","created":"2021-08-31","cited_by_count":86},{"id":"2402.16641","title":"Towards Open-ended Visual Quality Comparison","created":"2024-02-26","cited_by_count":85},{"id":"2109.14573","title":"Towards Flexible Blind JPEG Artifacts Removal","created":"2021-09-29","cited_by_count":76},{"id":"2304.03994","title":"RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors","created":"2023-04-08","cited_by_count":73},{"id":"2310.11881","title":"A Comparative Study of Image Restoration Networks for General Backbone Network Design","created":"2023-10-18","cited_by_count":57},{"id":"1804.04450","title":"Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning","created":"2018-04-12","cited_by_count":52},{"id":"2401.03379","title":"Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy","created":"2024-01-07","cited_by_count":50},{"id":"2505.18227","title":"Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality","created":"2025-05-23","cited_by_count":50},{"id":"2204.00367","title":"Learning to Deblur using Light Field Generated and Real Defocus Images","created":"2022-04-01","cited_by_count":46},{"id":"2207.14083","title":"Weakly-Supervised Camouflaged Object Detection with Scribble Annotations","created":"2022-07-28","cited_by_count":43},{"id":"2410.17809","title":"An Intelligent Agentic System for Complex Image Restoration Problems","created":"2024-10-23","cited_by_count":43},{"id":"2405.19769","title":"All-In-One Medical Image Restoration via Task-Adaptive Routing","created":"2024-05-30","cited_by_count":30},{"id":"2503.09403","title":"Multi-Agent Image Restoration","created":"2025-03-12","cited_by_count":21},{"id":"2503.10120","title":"Hybrid Agents for Image Restoration","created":"2025-03-13","cited_by_count":17},{"id":"2302.06733","title":"Robust Unsupervised StyleGAN Image Restoration","created":"2023-02-13","cited_by_count":14},{"id":"2504.15176","title":"DSPO: Direct Semantic Preference Optimization for Real-World Image Super-Resolution","created":"2025-04-21","cited_by_count":13},{"id":"2503.16980","title":"VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models","created":"2025-03-21","cited_by_count":12},{"id":"2510.05184","title":"Representation Potentials of Foundation Models for Multimodal Alignment: A Survey","created":"2025-10-05","cited_by_count":11},{"id":"2408.15143","title":"A Preliminary Exploration Towards General Image Restoration","created":"2024-08-27","cited_by_count":6},{"id":"2506.16796","title":"RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought","created":"2025-06-20","cited_by_count":5},{"id":"2510.06243","title":"CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning","created":"2025-10-03","cited_by_count":5},{"id":"2512.16891","title":"LinkedOut: Linking World Knowledge Representation Out of Video LLM for Next-Generation Video Recommendation","created":"2025-12-18","cited_by_count":5},{"id":"2511.00682","title":"Outlier-Aware Post-Training Quantization for Image Super-Resolution","created":"2025-11-01","cited_by_count":4},{"id":"2309.15019","title":"IFT: Image Fusion Transformer for Ghost-free High Dynamic Range Imaging","created":"2023-09-26","cited_by_count":3}],"next_cursor":null}