1 citations · 1 across the 5 of their papers we have counts for
6 papers
OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills
Qiyuan Liu, Tingfeng Hui, Kun Zhan +2
LLM-based agents leverage third-party skills to extend their capabilities in open-world scenarios. However, third-party skills can introduce extra security vulnerabilities, as seem…
Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence
Bingji Yi, Qiyuan Liu, Yuwei Cheng +1
Synthetic data has been increasingly used to train frontier generative models. However, recent studies raise key concerns that iteratively retraining a generative model on its self…
Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey
Qiyuan Liu, Hao Xu, Xuhong Chen +3
Reward models (RMs) play a critical role in enhancing the reasoning performance of LLMs. For example, they can provide training signals to finetune LLMs during reinforcement learni…
Behavior Imitation for Manipulator Control and Grasping with Deep Reinforcement Learning
Liu Qiyuan
The existing Motion Imitation models typically require expert data obtained through MoCap devices, but the vast amount of training data needed is difficult to acquire, necessitatin…
Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions
Qiyuan Liu, Qi Zhou, Rui Yang +1
Recent work has shown that representation learning plays a critical role in sample-efficient reinforcement learning (RL) from pixels. Unfortunately, in real-world scenarios, repres…
CURO: Curriculum Learning for Relative Overgeneralization
Lin Shi, Qiyuan Liu, Bei Peng
Relative overgeneralization (RO) is a pathology that can arise in cooperative multi-agent tasks when the optimal joint action's utility falls below that of a sub-optimal joint acti…