{"list":"other","total":52,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"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":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2209.14687","title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","created":"2022-09-29","cited_by_count":1416},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"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":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2505.13447","title":"Mean Flows for One-step Generative Modeling","created":"2025-05-19","cited_by_count":561},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504},{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485},{"id":"2505.09568","title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","created":"2025-05-14","cited_by_count":376},{"id":"2504.08837","title":"VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning","created":"2025-04-10","cited_by_count":323},{"id":"2504.06256","title":"Transfer between Modalities with MetaQueries","created":"2025-04-08","cited_by_count":236},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166},{"id":"2412.01981","title":"Free Process Rewards without Process Labels","created":"2024-12-02","cited_by_count":165},{"id":"2410.13863","title":"Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens","created":"2024-10-17","cited_by_count":147},{"id":"2406.04312","title":"ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization","created":"2024-06-06","cited_by_count":119},{"id":"2411.09502","title":"Golden Noise for Diffusion Models: A Learning Framework","created":"2024-11-14","cited_by_count":92},{"id":"2503.15477","title":"What Makes a Reward Model a Good Teacher? An Optimization Perspective","created":"2025-03-19","cited_by_count":73},{"id":"2506.09027","title":"Diffuse and Disperse: Image Generation with Representation Regularization","created":"2025-06-10","cited_by_count":70},{"id":"2507.21033","title":"GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset","created":"2025-07-28","cited_by_count":70},{"id":"2507.22062","title":"Meta CLIP 2: A Worldwide Scaling Recipe","created":"2025-07-29","cited_by_count":64},{"id":"2503.07703","title":"Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model","created":"2025-03-10","cited_by_count":62},{"id":"2510.15857","title":"BLIP3o-NEXT: Next Frontier of Native Image Generation","created":"2025-10-17","cited_by_count":54},{"id":"2509.21880","title":"No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping","created":"2025-09-26","cited_by_count":50},{"id":"2509.07295","title":"Reconstruction Alignment Improves Unified Multimodal Models","created":"2025-09-08","cited_by_count":49},{"id":"2502.17437","title":"Fractal Generative Models","created":"2025-02-24","cited_by_count":46},{"id":"2502.13129","title":"Is Noise Conditioning Necessary for Denoising Generative Models?","created":"2025-02-18","cited_by_count":44},{"id":"2503.19312","title":"ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning","created":"2025-03-25","cited_by_count":37},{"id":"2508.09968","title":"Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models","created":"2025-08-13","cited_by_count":35},{"id":"2505.23493","title":"R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation","created":"2025-05-29","cited_by_count":32},{"id":"2506.03164","title":"Test-Time Scaling of Diffusion Models via Noise Trajectory Search","created":"2025-05-24","cited_by_count":30},{"id":"2509.13232","title":"Single-stream Policy Optimization","created":"2025-09-16","cited_by_count":28},{"id":"2503.07596","title":"Denoising Hamiltonian Network for Physical Reasoning","created":"2025-03-10","cited_by_count":10},{"id":"2511.14760","title":"UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learning","created":"2025-11-18","cited_by_count":8},{"id":"2408.03459","title":"Can DPO Learn Diverse Human Values? A Theoretical Scaling Law","created":"2024-08-06","cited_by_count":7},{"id":"2507.07981","title":"Why is Your Language Model a Poor Implicit Reward Model?","created":"2025-07-10","cited_by_count":6},{"id":"2509.26074","title":"Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis","created":"2025-09-30","cited_by_count":2}],"next_cursor":null}