{"list":"other","total":61,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"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":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2305.01569","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","created":"2023-05-02","cited_by_count":977},{"id":"2306.09341","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","created":"2023-06-15","cited_by_count":890},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2311.12908","title":"Diffusion Model Alignment Using Direct Preference Optimization","created":"2023-11-21","cited_by_count":790},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2309.17400","title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards","created":"2023-09-29","cited_by_count":448},{"id":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340},{"id":"2303.09833","title":"FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model","created":"2023-03-17","cited_by_count":294},{"id":"2310.03739","title":"Aligning Text-to-Image Diffusion Models with Reward Backpropagation","created":"2023-10-05","cited_by_count":288},{"id":"2303.14420","title":"Human Preference Score: Better Aligning Text-to-Image Models with Human Preference","created":"2023-03-25","cited_by_count":287},{"id":"2311.13231","title":"Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model","created":"2023-11-22","cited_by_count":252},{"id":"2303.09556","title":"Efficient Diffusion Training via Min-SNR Weighting Strategy","created":"2023-03-16","cited_by_count":246},{"id":"2406.08673","title":"HelpSteer2: Open-source dataset for training top-performing reward models","created":"2024-06-12","cited_by_count":236},{"id":"2409.08861","title":"Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control","created":"2024-09-13","cited_by_count":233},{"id":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217},{"id":"2405.01483","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","created":"2024-05-02","cited_by_count":216},{"id":"2406.15252","title":"VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation","created":"2024-06-21","cited_by_count":197},{"id":"2310.05470","title":"Generative Judge for Evaluating Alignment","created":"2023-10-09","cited_by_count":169},{"id":"2412.21059","title":"VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation","created":"2024-12-30","cited_by_count":156},{"id":"2312.10240","title":"Rich Human Feedback for Text-to-Image Generation","created":"2023-12-15","cited_by_count":141},{"id":"2410.01257","title":"HelpSteer2-Preference: Complementing Ratings with Preferences","created":"2024-10-02","cited_by_count":130},{"id":"2405.14705","title":"Learning Multi-dimensional Human Preference for Text-to-Image Generation","created":"2024-05-23","cited_by_count":106},{"id":"2311.13443","title":"Guided Flows for Generative Modeling and Decision Making","created":"2023-11-22","cited_by_count":101},{"id":"1906.02386","title":"Deep Reinforcement Learning for Multi-objective Optimization","created":"2019-06-06","cited_by_count":90},{"id":"2402.14809","title":"CriticBench: Benchmarking LLMs for Critique-Correct Reasoning","created":"2024-02-22","cited_by_count":88},{"id":"2402.10210","title":"Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation","created":"2024-02-15","cited_by_count":85},{"id":"2406.04485","title":"GenAI Arena: An Open Evaluation Platform for Generative Models","created":"2024-06-06","cited_by_count":82},{"id":"2401.12244","title":"Large-scale Reinforcement Learning for Diffusion Models","created":"2024-01-20","cited_by_count":78},{"id":"2305.14324","title":"Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration","created":"2023-05-23","cited_by_count":74},{"id":"2412.04814","title":"LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment","created":"2024-12-06","cited_by_count":53},{"id":"2412.02617","title":"Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback","created":"2024-12-03","cited_by_count":47},{"id":"2410.05227","title":"The Dawn of Video Generation: Preliminary Explorations with SORA-like Models","created":"2024-10-07","cited_by_count":31},{"id":"2410.05760","title":"Training-free Diffusion Model Alignment with Sampling Demons","created":"2024-10-08","cited_by_count":31},{"id":"2311.15657","title":"Enhancing Diffusion Models with Text-Encoder Reinforcement Learning","created":"2023-11-27","cited_by_count":30},{"id":"2410.05328","title":"Reward Learning From Preference With Ties","created":"2024-10-05","cited_by_count":14}],"next_cursor":null}