MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
Paper • 2506.22434 • Published • 10
Vision
-
-
VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
Paper • 2507.13348 • Published • 80 -
RewardDance: Reward Scaling in Visual Generation
Paper • 2509.08826 • Published • 73 -
Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs
Paper • 2510.18876 • Published • 37 -
Back to Basics: Let Denoising Generative Models Denoise
Paper • 2511.13720 • Published • 71 -
Diversity Has Always Been There in Your Visual Autoregressive Models
Paper • 2511.17074 • Published • 8 -
The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation
Paper • 2511.20256 • Published • 28 -
World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models
Paper • 2511.22787 • Published • 10 -
InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields
Paper • 2601.03252 • Published • 104 -
DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation
Paper • 2601.22904 • Published • 16 -
Unified Personalized Reward Model for Vision Generation
Paper • 2602.02380 • Published • 20 -
Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
Paper • 2602.11858 • Published • 61 -
DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories
Paper • 2602.10809 • Published • 59 -
PyVision-RL: Forging Open Agentic Vision Models via RL
Paper • 2602.20739 • Published • 32 -
Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs
Paper • 2603.09095 • Published • 29 -
EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
Paper • 2603.12267 • Published • 13 -
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing
Paper • 2603.11593 • Published • 25 -
UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
Paper • 2603.23500 • Published • 37 -
RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
Paper • 2603.25502 • Published • 58 -
MuRF: Unlocking the Multi-Scale Potential of Vision Foundation Models
Paper • 2603.25744 • Published • 13 -
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Paper • 2603.28767 • Published • 58 -
ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks
Paper • 2603.27862 • Published • 33 -
DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing
Paper • 2603.28713 • Published • 23 -
HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
Paper • 2603.17024 • Published • 110 -
Make Geometry Matter for Spatial Reasoning
Paper • 2603.26639 • Published • 33 -
Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
Paper • 2603.29620 • Published • 49 -
Watch Before You Answer: Learning from Visually Grounded Post-Training
Paper • 2604.05117 • Published • 36 -
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning
Paper • 2604.04746 • Published • 73 -
RewardFlow: Generate Images by Optimizing What You Reward
Paper • 2604.08536 • Published • 6 -
Generative Refinement Networks for Visual Synthesis
Paper • 2604.13030 • Published • 15 -
Reinforcing Multimodal Reasoning Against Visual Degradation
Paper • 2605.09262 • Published • 7 -
Qwen-Image-VAE-2.0 Technical Report
Paper • 2605.13565 • Published • 62 -
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
Paper • 2605.15128 • Published • 65 -
GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
Paper • 2605.21605 • Published • 16 -
InstructSAM: Segment Any Instance with Any Instructions
Paper • 2605.26102 • Published • 18 -
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
Paper • 2605.27365 • Published • 146 -
From Pixels to Words -- Towards Native One-Vision Models at Scale
Paper • 2605.28820 • Published • 76 -
GenClaw: Code-Driven Agentic Image Generation
Paper • 2605.30248 • Published • 41 -
Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators
Paper • 2606.06476 • Published • 15 -
Text-to-Image Models Need Less from Text Encoders Than You Think
Paper • 2606.03715 • Published • 11 -
Self-Evolving Visual Questioner
Paper • 2606.13929 • Published • 15 -
Semantic Browsing: Controllable Diversity for Image Generation
Paper • 2606.23679 • Published • 19 -
Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation
Paper • 2606.26907 • Published • 50 -
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Paper • 2607.01191 • Published • 19 -
Optimizing Visual Generative Models via Distribution-wise Rewards
Paper • 2607.02291 • Published • 18 -
Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes
Paper • 2607.13188 • Published • 34 -
ReferTrack: Referring Then Tracking for Embodied Visual Tracking
Paper • 2607.20061 • Published • 53 -
Beacon: Knowing When and How to Perform Agentic Visual Reasoning
Paper • 2607.28595 • Published • 53