{"list":"other","total":56,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"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":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","created":"2024-09-18","cited_by_count":1090},{"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":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2204.08958","title":"MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment","created":"2022-04-19","cited_by_count":522},{"id":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513},{"id":"2312.17090","title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","created":"2023-12-28","cited_by_count":503},{"id":"2312.00849","title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback","created":"2023-12-01","cited_by_count":412},{"id":"1709.05424","title":"NIMA: Neural Image Assessment","created":"2017-09-15","cited_by_count":389},{"id":"1910.06180","title":"KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment","created":"2019-10-14","cited_by_count":355},{"id":"1907.02665","title":"Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network","created":"2019-07-05","cited_by_count":302},{"id":"2503.12937","title":"R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization","created":"2025-03-17","cited_by_count":301},{"id":"2309.14181","title":"Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision","created":"2023-09-25","cited_by_count":249},{"id":"1612.01697","title":"Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment","created":"2016-12-06","cited_by_count":225},{"id":"2311.16839","title":"Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization","created":"2023-11-28","cited_by_count":225},{"id":"2007.12142","title":"PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration","created":"2020-07-23","cited_by_count":178},{"id":"2502.19634","title":"MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning","created":"2025-02-26","cited_by_count":173},{"id":"1806.02067","title":"PieAPP: Perceptual Image-Error Assessment through Pairwise Preference","created":"2018-06-06","cited_by_count":160},{"id":"2311.06783","title":"Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models","created":"2023-11-12","cited_by_count":152},{"id":"1707.08347","title":"RankIQA: Learning from Rankings for No-reference Image Quality Assessment","created":"2017-07-26","cited_by_count":151},{"id":"1612.05890","title":"Learning a No-Reference Quality Metric for Single-Image Super-Resolution","created":"2016-12-18","cited_by_count":144},{"id":"2004.05508","title":"MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment","created":"2020-04-11","cited_by_count":144},{"id":"2306.04717","title":"AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment","created":"2023-06-07","cited_by_count":142},{"id":"2501.11561","title":"Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution","created":"2025-01-20","cited_by_count":141},{"id":"2402.06332","title":"InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning","created":"2024-02-09","cited_by_count":119},{"id":"2312.08962","title":"Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models","created":"2023-12-14","cited_by_count":105},{"id":"2402.16641","title":"Towards Open-ended Visual Quality Comparison","created":"2024-02-26","cited_by_count":85},{"id":"2412.00154","title":"o1-Coder: an o1 Replication for Coding","created":"2024-11-29","cited_by_count":78},{"id":"2405.19298","title":"Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare","created":"2024-05-29","cited_by_count":66},{"id":"2207.13686","title":"Shift-tolerant Perceptual Similarity Metric","created":"2022-07-27","cited_by_count":44},{"id":"2103.07666","title":"GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment","created":"2021-03-13","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":"2108.07948","title":"Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment","created":"2021-08-18","cited_by_count":41},{"id":"2409.20063","title":"Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMs","created":"2024-09-30","cited_by_count":39},{"id":"2405.18842","title":"Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset","created":"2024-05-29","cited_by_count":38},{"id":"2503.11221","title":"Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption","created":"2025-03-14","cited_by_count":35},{"id":"2110.08521","title":"Locally Adaptive Structure and Texture Similarity for Image Quality Assessment","created":"2021-10-16","cited_by_count":32},{"id":"2503.02357","title":"Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content","created":"2025-03-04","cited_by_count":32},{"id":"2407.17035","title":"Q-Ground: Image Quality Grounding with Large Multi-modality Models","created":"2024-07-24","cited_by_count":30},{"id":"1805.08493","title":"Blind Predicting Similar Quality Map for Image Quality Assessment","created":"2018-05-22","cited_by_count":21},{"id":"2503.09197","title":"Q-SiT: Teaching LMMs for Image Quality Scoring and Interpreting","created":"2025-03-12","cited_by_count":13},{"id":"2204.08763","title":"Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment","created":"2022-04-19","cited_by_count":12}],"next_cursor":null}