Visual RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 43

All topics

Self-supervised Hierarchical Visual Reasoning with World Model
May 17, 2026Yuanfei Xu, Lin Liu, Wengang Zhou +2World Model Learning World Models
Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, Anhui, China
Identifiable Token Correspondence for World Models
May 15, 2026Youngin Kim, Ray Sun, Inho Kim +2World Model Learning Transformer-Based RL
Interdisciplinary Program in Artificial Intelligence, Seoul National University · Department of Computer Science and Engineering, Seoul National University · KRAFTON
Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning
May 11, 2026Raphael Trumpp, Ömer Veysel Çağatan, Barış Akgün +1RL Benchmarks Robot Policy Generalization
TUM School of Engineering and Design · Technical University of Munich · KUIS AI Center +2
RELO: Reinforcement Learning to Localize for Visual Object Tracking
May 8, 2026Xin Chen, Chuanyu Sun, Jiao Xu +4Reinforcement Learning Visual Object Tracking
City University of Hong Kong · Dalian University of Technology · Hunyuan Team, Tencent
Anatomical Landmark-Guided Deep Reinforcement Learning for Autonomous Gastric Navigation
May 8, 2026Haoxuan Wu, Sishen Yuan, Haitao Gao +3RL Control Endoscopy
Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China
Learning Visual Feature-Based World Models via Residual Latent Action
May 8, 2026Xinyu Zhang, Zhengtong Xu, Yutian Tao +3Latent Action Learning World Model Learning
Rutgers University · Purdue University · University of Wisconsin-Madison
ELVIS: Ensemble-Calibrated Latent Imagination for Long-Horizon Visual MPC
May 6, 2026Yurui Du, Pinhao Song, Yutong Hu +1Visual SSMs Model Predictive Control
KU Leuven, Dept. Electrical Engineering, Research unit Processing Speech and Images, B-3000 Leuven, Belgium · Flanders Make at KU Leuven, B-3000 Leuven, Belgium · KU Leuven, Dept. Mechanical Engineering, Research unit Robotics, Automation and Mechatronics, B-3000 Leuven, Belgium
Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift
Apr 30, 2026Haiyang ZhaoDistribution Shift Robustness OOD Generalization
University of Georgia United States
GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning
Apr 28, 2026Yufei Jia, Heng Zhang, Ziheng Zhang +39Robotics Simulation Visual RL
Language-Conditioned World Modeling for Visual Navigation
Mar 23, 2026Yifei Dong, Fengyi Wu, Yilong Dai +8World Model Learning Vision-Language Navigation
University of Washington · National University of Singapore · Clemson University +2
Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models
Mar 17, 2026Yanru Wu, Weiduo Yuan, Esteban Martinez Licon +4Long-Horizon Robotic Manipulation Robot Skill Learning
USC Physical Superintelligence Lab
KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning
Jan 20, 2026Egor Cherepanov, Daniil Zelezetsky, Alexey K. Kovalev +1RL Benchmarks Reinforcement Learning
1AXXX, Moscow, Russia · 2MIRAI, Moscow, Russia
SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning
Nov 12, 2025Tairan Huang, Yulin Jin, Junxu Liu +2Adversarial Attacks Adversarial Perturbations
The Hong Kong Polytechnic University Hong Kong, China

May 17, 2026, cs.AIJ/K move · Enter open · S save

Self-supervised Hierarchical Visual Reasoning with World Model

Yuanfei Xu, Lin Liu, Wengang Zhou, Mingxiao Feng+1

Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, Anhui, China

World Model Learning World Models Latent Visual Reasoning Representation Learning for RL Visual RL Self-Supervised Visual Representation Learning

Open paper AskPDF arXiv

3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning due to their vast state spaces. Effective reasoning representations are essential in such settings. While existing self-supervised visual foresight reasoning approaches often suffer from multi-step error accumulation, many recent studies resort to injecting domain-specific knowledge for more stable guidance. Our key insight is that the photorealistic fidelity of visual reasoning representations is secondary; what truly matters is providing informative, task-relevant signals. To this end, we propose ResDreamer, a hierarchical world model in which each higher-level layer is trained to reconstruct the residuals of the layer below. This design enables progressive abstraction of increasingly sophisticated world dynamics and fosters the emergence of richer latent representations. Drawing inspiration from the "Bitter Lesson", ResDreamer trains its reasoning representations in a purely self-supervised manner. The higher-level residual representations are used to modulate lower-level predictions, allowing the world model to scale effectively with only linearly increasing cross-layer communication costs. Experiments show that ResDreamer achieves state-of-the-art sample efficiency and parameter efficiency. This scalable hierarchical visual foresight reasoning architecture paves the way for more capable online RL agents in open-ended, dynamic environments. The code is accessible at https://github.com/XuYuanFei01/ResDreamer.

Momentum

Related topics

Latest papers 43