works on

From the 1 of 14 linked papers with an AI index.

collaborators

14 papers

cs.AI2026

MemWM: Memory-Augmented Text-Based World Model

Yujun Wang, Tao Zhang, Jinhe Bi +9

World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent next-state predictions can sti…

cs.AI2026

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning

Jinhe Bi, Chennan Zhou, Zengjie Jin +10

On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories…

cs.RO2026

TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors

Pinhan Fu, Xianda Guo, Xuetao Li +5

The paper introduces TrustVLA, an inference-time defense that detects and mitigates visual backdoor triggers in vision‑language‑action models by monitoring epistemic uncertainty an…

cs.LG2026

EchoRL: Reinforcement Learning via Rollout Echoing

Jinhe Bi, Aniri, Minglai Yang +9

Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models. However, as training proceed…

cs.CR2026

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems

Yunhao Feng, Yifan Ding, Yingshui Tan +6

Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We…

cs.CV2026

ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving

Xianda Guo, Ruijun Zhang, Yiqun Duan +9

Depth estimation is a fundamental component of spatial perception for autonomous driving and other unmanned systems operating in open urban environments. Existing depth datasets su…