15 citations · 46 across the 18 of their papers we have counts for
19 papers
Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions
Chenrui Fan, Yize Cheng, Ming Li +3
Reasoning language models increasingly use test-time compute to improve performance, but existing evaluations typically study this compute one question at a time. Yet when multiple…
TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos
Seungjae Lee, Yoonkyo Jung, Inkook Chun +8
Learning new robot tasks on new platforms and in new scenes from only a handful of demonstrations remains challenging. While videos of other embodiments - humans and different robo…
ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
Yongyuan Liang, Wei Chow, Feng Li +7
Unified multimodal models (UMMs) have emerged as a powerful paradigm for seamlessly unifying text and image understanding and generation. However, prevailing evaluations treat thes…
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
Xiyao Wang, Zhengyuan Yang, Chao Feng +10
Reinforcement learning (RL) has shown great effectiveness for fine-tuning large language models (LLMs) using tasks that are challenging yet easily verifiable, such as math reasonin…
MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning
Zikui Cai, Andrew Wang, Anirudh Satheesh +10
Despite rapid advances in vision-language models (VLMs), current benchmarks for multimodal reasoning fall short in three key dimensions. First, they overwhelmingly rely on static i…
TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
Ruijie Zheng, Yongyuan Liang, Shuaiyi Huang +5
Although large vision-language-action (VLA) models pretrained on extensive robot datasets offer promising generalist policies for robotic learning, they still struggle with spatial…
Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
Yongyuan Liang, Tingqiang Xu, Kaizhe Hu +3
Can we generate a control policy for an agent using just one demonstration of desired behaviors as a prompt, as effortlessly as creating an image from a textual description? In thi…
Is poisoning a real threat to LLM alignment? Maybe more so than you think
Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu +2
Recent advancements in Reinforcement Learning with Human Feedback (RLHF) have significantly impacted the alignment of Large Language Models (LLMs). The sensitivity of reinforcement…
Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
Xiangyu Liu, Chenghao Deng, Yanchao Sun +2
In light of the burgeoning success of reinforcement learning (RL) in diverse real-world applications, considerable focus has been directed towards ensuring RL policies are robust t…
ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
Tianying Ji, Yongyuan Liang, Yan Zeng +7
The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms. Leveraging this insight, we explo…
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
Ruijie Zheng, Yongyuan Liang, Xiyao Wang +7
We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks. Premier-T…
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
Guowei Xu, Ruijie Zheng, Yongyuan Liang +12
Visual reinforcement learning (RL) has shown promise in continuous control tasks. Despite its progress, current algorithms are still unsatisfactory in virtually every aspect of the…
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
Yongyuan Liang, Yanchao Sun, Ruijie Zheng +5
Deploying reinforcement learning (RL) systems requires robustness to uncertainty and model misspecification, yet prior robust RL methods typically only study noise introduced indep…
Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
Yongyuan Liang, Yanchao Sun, Ruijie Zheng +1
Recent studies reveal that a well-trained deep reinforcement learning (RL) policy can be particularly vulnerable to adversarial perturbations on input observations. Therefore, it i…
Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems
Yanchao Sun, Ruijie Zheng, Parisa Hassanzadeh +4
Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to share information and make good decisions. However, when deploying trained commu…
Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
Yanchao Sun, Ruijie Zheng, Yongyuan Liang +1
Evaluating the worst-case performance of a reinforcement learning (RL) agent under the strongest/optimal adversarial perturbations on state observations (within some constraints) i…
InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks
Yonggan Fu, Zhongzhi Yu, Yongan Zhang +6
The promise of Deep Neural Network (DNN) powered Internet of Thing (IoT) devices has motivated a tremendous demand for automated solutions to enable fast development and deployment…
FDNAS: Improving Data Privacy and Model Diversity in AutoML
Chunhui Zhang, Yongyuan Liang, Xiaoming Yuan +1
To prevent the leakage of private information while enabling automated machine intelligence, there is an emerging trend to integrate federated learning and Neural Architecture Sear…
Parallel Knowledge Transfer in Multi-Agent Reinforcement Learning
Yongyuan Liang, Bangwei Li
Multi-agent reinforcement learning is a standard framework for modeling multi-agent interactions applied in real-world scenarios. Inspired by experience sharing in human groups, le…