works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.LG2026

Critic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning

Daoyi Li, Yixian Zhang, Chao Yu +2

Offline-to-online (O2O) reinforcement learning aims to leverage policies pretrained on static datasets while improving them through online interaction. However, directly reusing an…

cs.RO2026

Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents

Yixian Zhang, Huanming Zhang, Feng Gao +13

The paper introduces Harness VLA, a memory-augmented framework that combines a frozen vision‑language‑action model with a small set of analytic manipulation primitives to improve r…

cs.RO2026

STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning

Zhihao Liu, Qiuyi Gu, Yitao Wang +16

Real-world robot learning increasingly relies on heterogeneous data, but demonstrations and rollouts often mix useful progress with stalls, corrections, and suboptimal behavior. Ef…

cs.CV2026

CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs

Zhengru Fang, Yanan Ma, Yu Guo +5

When a chest X-ray shows consolidation but the question asks which finding is present, a medical vision-language model may answer "No consolidation." This is more than an incorrect…

cs.RO2026

SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling

Yixian Zhang, Shu'ang Yu, Tonghe Zhang +6

Training expressive flow-based policies with off-policy reinforcement learning is notoriously unstable due to gradient pathologies in the multi-step action sampling process. We tra…

cs.LG2025

Bidirectional Soft Actor-Critic: Leveraging Forward and Reverse KL Divergence for Efficient Reinforcement Learning

Yixian Zhang, Huaze Tang, Changxu Wei +1

The Soft Actor-Critic (SAC) algorithm, a state-of-the-art method in maximum entropy reinforcement learning, traditionally relies on minimizing reverse Kullback-Leibler (KL) diverge…