activity
20242026
collaborators

5 papers

cs.LG2026

Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model

Jiahao Wu, Ning Lu, Shengcai Liu +6

Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance perfor…

cs.LG2026

DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation

Yang Zhou, Can Jin, Zihan Dong +7

Reinforcement learning improves the reasoning ability of large language models but remains costly and sample-inefficient, as many rollouts provide weak learning signals. Difficulty…

cs.RO2026

Seeing Farther and Smarter: Value-Guided Multi-Path Reflection for VLM Policy Optimization

Yanting Yang, Shenyuan Gao, Qingwen Bu +2

Solving complex, long-horizon robotic manipulation tasks requires a deep understanding of physical interactions, reasoning about their long-term consequences, and precise high-leve…

cs.RO2025

UniVLA: Learning to Act Anywhere with Task-centric Latent Actions

Qingwen Bu, Yanting Yang, Jisong Cai +5

A generalist robot should perform effectively across various environments. However, most existing approaches heavily rely on scaling action-annotated data to enhance their capabili…

cs.AI2024

AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning

Minghao Chen, Yihang Li, Yanting Yang +3

Large Language Models (LLM) based agents have shown promise in autonomously completing tasks across various domains, e.g., robotics, games, and web navigation. However, these agent…