{"list":"other","total":86,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"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":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1606.06650","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","created":"2016-06-21","cited_by_count":1476},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"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":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"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":"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":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2310.08491","title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models","created":"2023-10-12","cited_by_count":575},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"2408.15240","title":"Generative Verifiers: Reward Modeling as Next-Token Prediction","created":"2024-08-27","cited_by_count":480},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"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":"2211.13221","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","created":"2022-11-23","cited_by_count":388},{"id":"2210.14896","title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","created":"2022-10-26","cited_by_count":379},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"2306.17563","title":"Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting","created":"2023-06-30","cited_by_count":307},{"id":"2310.03739","title":"Aligning Text-to-Image Diffusion Models with Reward Backpropagation","created":"2023-10-05","cited_by_count":288},{"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":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"2404.11018","title":"Many-Shot In-Context Learning","created":"2024-04-17","cited_by_count":206},{"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":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174},{"id":"2310.12921","title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning","created":"2023-10-19","cited_by_count":165},{"id":"2310.08576","title":"Learning to Act from Actionless Videos through Dense Correspondences","created":"2023-10-12","cited_by_count":164},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146},{"id":"2402.15194","title":"Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control","created":"2024-02-23","cited_by_count":143},{"id":"2406.13743","title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","created":"2024-06-19","cited_by_count":135},{"id":"2306.03872","title":"Deductive Verification of Chain-of-Thought Reasoning","created":"2023-06-06","cited_by_count":124},{"id":"2006.03647","title":"Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization","created":"2020-06-05","cited_by_count":120},{"id":"2407.08737","title":"Video Diffusion Alignment via Reward Gradients","created":"2024-07-11","cited_by_count":107},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87},{"id":"2405.18750","title":"T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback","created":"2024-05-29","cited_by_count":87},{"id":"2312.12490","title":"InstructVideo: Instructing Video Diffusion Models with Human Feedback","created":"2023-12-19","cited_by_count":86},{"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":"2401.12244","title":"Large-scale Reinforcement Learning for Diffusion Models","created":"2024-01-20","cited_by_count":78},{"id":"2401.09962","title":"CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects","created":"2024-01-18","cited_by_count":77},{"id":"2407.01094","title":"Evaluation of Text-to-Video Generation Models: A Dynamics Perspective","created":"2024-07-01","cited_by_count":67},{"id":"2407.05965","title":"T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models","created":"2024-07-08","cited_by_count":66},{"id":"2303.14302","title":"VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining","created":"2023-03-24","cited_by_count":65},{"id":"2401.07781","title":"Towards A Better Metric for Text-to-Video Generation","created":"2024-01-15","cited_by_count":51},{"id":"2306.07257","title":"MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images","created":"2023-06-12","cited_by_count":42},{"id":"2402.04764","title":"Code as Reward: Empowering Reinforcement Learning with VLMs","created":"2024-02-07","cited_by_count":39},{"id":"1804.09235","title":"On the effectiveness of task granularity for transfer learning","created":"2018-04-24","cited_by_count":35},{"id":"2406.14477","title":"SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset","created":"2024-06-20","cited_by_count":35},{"id":"2402.06118","title":"ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling","created":"2024-02-09","cited_by_count":34},{"id":"2411.18664","title":"Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling","created":"2024-11-27","cited_by_count":34},{"id":"2402.08552","title":"Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases","created":"2024-02-13","cited_by_count":30},{"id":"2409.06691","title":"Geometric-Averaged Preference Optimization for Soft Preference Labels","created":"2024-09-10","cited_by_count":18},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15},{"id":"2404.15100","title":"Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation","created":"2024-04-23","cited_by_count":15},{"id":"1812.01037","title":"TwoStreamVAN: Improving Motion Modeling in Video Generation","created":"2018-12-03","cited_by_count":9},{"id":"2404.01863","title":"Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models","created":"2024-04-02","cited_by_count":9}],"next_cursor":null}