13 citations · 57 across the 21 of their papers we have counts for
22 papers
When Protection Overrides Consequences: Understanding Protection Mode in Large Language Model Decision-Making
Yuanfan Li, Junyi Chen, Qi Zhou +3
Frontier language models excel at complex tasks yet may prioritize protection over larger physical consequences in simple, urgent decisions. GPT-5.6 Sol, for example, moves a girl…
Long-Horizon Embodied Decision-Making via Multimodal Memory Compression
Bingxuan Li, Rui Yang, Cheng Qian +6
Agents are increasingly expected to act not only as task executors, but also as decision-makers on behalf of human users. This shift requires agents to accumulate evidence over lon…
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
Rui Yang, Qianhui Wu, Yuxi Chen +7
Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despite rapid progress, the stronges…
AsyncWebRL: Efficient Asynchronous Reinforcement Learning for Multi-Step Visual Web Agents
Hao Bai, Rui Yang, Chenlu Ye +3
Training vision-language web agents with multi-step RL is compute-intensive, with two dominant forms of inefficiency: idle GPUs in synchronous RL, and trajectories that use more st…
PRO-CUA: Process-Reward Optimization for Computer Use Agents
Yifei He, Rui Yang, Hao Bai +2
Computer use agents (CUAs) have shown strong potential for automating complex digital workflows, yet their training remains constrained by costly live environment interaction and l…
GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL
Rui Yang, Qianhui Wu, Zhaoyang Wang +8
Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a shortage of high-quality, action-align…
Rethinking Diverse Human Preference Learning through Principal Component Analysis
Feng Luo, Rui Yang, Hao Sun +5
Understanding human preferences is crucial for improving foundation models and building personalized AI systems. However, preferences are inherently diverse and complex, making it…
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Rui Yang, Hanyang Chen, Junyu Zhang +10
Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks. While language-centric embodied agents have…
DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models
Chengke Zou, Xingang Guo, Rui Yang +3
The rapid advancements in Vision-Language Models (VLMs) have shown great potential in tackling mathematical reasoning tasks that involve visual context. Unlike humans who can relia…
Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling
Jiawei Xu, Rui Yang, Shuang Qiu +4
Learning policy from offline datasets through offline reinforcement learning (RL) holds promise for scaling data-driven decision-making while avoiding unsafe and costly online inte…
Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
Rui Yang, Ruomeng Ding, Yong Lin +2
Reward models trained on human preference data have been proven to effectively align Large Language Models (LLMs) with human intent within the framework of reinforcement learning f…
Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
Rui Yang, Xiaoman Pan, Feng Luo +4
We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems. However, it is g…
GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models
Mianchu Wang, Rui Yang, Xi Chen +3
Offline Goal-Conditioned RL (GCRL) offers a feasible paradigm for learning general-purpose policies from diverse and multi-task offline datasets. Despite notable recent progress, t…
Corruption-Robust Offline Reinforcement Learning with General Function Approximation
Chenlu Ye, Rui Yang, Quanquan Gu +1
We investigate the problem of corruption robustness in offline reinforcement learning (RL) with general function approximation, where an adversary can corrupt each sample in the of…
Towards Robust Offline Reinforcement Learning under Diverse Data Corruption
Rui Yang, Han Zhong, Jiawei Xu +4
Offline reinforcement learning (RL) presents a promising approach for learning reinforced policies from offline datasets without the need for costly or unsafe interactions with the…
What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?
Rui Yang, Yong Lin, Xiaoteng Ma +3
Offline goal-conditioned RL (GCRL) offers a way to train general-purpose agents from fully offline datasets. In addition to being conservative within the dataset, the generalizatio…
Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping
Hao Sun, Lei Han, Rui Yang +3
In this work, we study the simple yet universally applicable case of reward shaping in value-based Deep Reinforcement Learning (DRL). We show that reward shifting in the form of th…
RORL: Robust Offline Reinforcement Learning via Conservative Smoothing
Rui Yang, Chenjia Bai, Xiaoteng Ma +3
Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks. Due to the distribution shift issue,…
Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL
Rui Yang, Yiming Lu, Wenzhe Li +6
Solving goal-conditioned tasks with sparse rewards using self-supervised learning is promising because of its simplicity and stability over current reinforcement learning (RL) algo…
MHER: Model-based Hindsight Experience Replay
Rui Yang, Meng Fang, Lei Han +3
Solving multi-goal reinforcement learning (RL) problems with sparse rewards is generally challenging. Existing approaches have utilized goal relabeling on collected experiences to…
Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning
Rui Yang, Jiafei Lyu, Yu Yang +5
Multi-goal reinforcement learning is widely applied in planning and robot manipulation. Two main challenges in multi-goal reinforcement learning are sparse rewards and sample ineff…
FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization
Lanqing Li, Rui Yang, Dijun Luo
We study the offline meta-reinforcement learning (OMRL) problem, a paradigm which enables reinforcement learning (RL) algorithms to quickly adapt to unseen tasks without any intera…