Hongyin Zhang

5 papers · 2023–2026 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🏆 Grand Slam

Venues

AAAI (1) ICLR (1) ICML (1) NeurIPS (1) RSS (1)

Top co-authors

Donglin Wang (5) Pengxiang Ding (3) Hongchao Lu (2) Zifeng Zhuang (2) Shangke Lyu (2) Han Zhao (2) Jinxin Liu (1) Yifan Qiao (1) Ying Peng (1) Bin Wang (1)

Research topics

Reinforcement Learning (4) Artificial Intelligence (3) Core AI (3) Methods (3) Computer Vision (1) Machine Learning (1) Robotics (1) Applications (1) Capabilities (1) Domain-Specific (1) Generation (1) Learning Types (1)

Keywords

offline reinforcement learning (2) reinforcement learning (2) test-time adaptation (1) flow matching (1) robot manipulation (1) bias-variance tradeoff (1) cumulative reward (1) policy extraction (1) sim-to-real gap (1) model-based optimization (1) vision-language-action model (1) offline rl (1) visual manipulation (1) legged robot locomotion (1) manipulation task (1) embodied artificial intelligence (1) robot decision making (1) perturbation modeling (1) online adaptive control (1) adaptive controller (1)

Papers

Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models AAAI 2026 GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation ICLR 2025 ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning ICML 2025 RL2AC: Reinforcement Learning-based Rapid Online Adaptive Control for Legged Robot Robust Locomotion RSS 2024 Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization NeurIPS 2023