39 citations · 44 across the 11 of their papers we have counts for
11 papers
How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
Mateusz Dziemian, Maxwell Lin, Xiaohan Fu +28
LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure…
What You See Is What Matters: A Novel Visual and Physics-Based Metric for Evaluating Video Generation Quality
Zihan Wang, Songlin Li, Lingyan Hao +2
As video generation models advance rapidly, assessing the quality of generated videos has become increasingly critical. Existing metrics, such as Fréchet Video Distance (FVD), Ince…
I Can Tell What I am Doing: Toward Real-World Natural Language Grounding of Robot Experiences
Zihan Wang, Brian Liang, Varad Dhat +4
Understanding robot behaviors and experiences through natural language is crucial for developing intelligent and transparent robotic systems. Recent advancement in large language m…
Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback
Max Balsells, Marcel Torne, Zihan Wang +3
Ideally, we would place a robot in a real-world environment and leave it there improving on its own by gathering more experience autonomously. However, algorithms for autonomous ro…
Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing
Xinyu Hu, Pengfei Tang, Simiao Zuo +5
Large language models (LLMs) have made impressive progress in natural language processing. These models rely on proper human instructions (or prompts) to generate suitable response…
Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback
Marcel Torne, Max Balsells, Zihan Wang +4
Exploration and reward specification are fundamental and intertwined challenges for reinforcement learning. Solving sequential decision-making tasks requiring expansive exploration…
Guiding Pretraining in Reinforcement Learning with Large Language Models
Yuqing Du, Olivia Watkins, Zihan Wang +5
Reinforcement learning algorithms typically struggle in the absence of a dense, well-shaped reward function. Intrinsically motivated exploration methods address this limitation by…
Masked Imitation Learning: Discovering Environment-Invariant Modalities in Multimodal Demonstrations
Yilun Hao, Ruinan Wang, Zhangjie Cao +3
Multimodal demonstrations provide robots with an abundance of information to make sense of the world. However, such abundance may not always lead to good performance when it comes…
Weakly Supervised Correspondence Learning
Zihan Wang, Zhangjie Cao, Yilun Hao +1
Correspondence learning is a fundamental problem in robotics, which aims to learn a mapping between state, action pairs of agents of different dynamics or embodiments. However, cur…
Learning from Imperfect Demonstrations via Adversarial Confidence Transfer
Zhangjie Cao, Zihan Wang, Dorsa Sadigh
Existing learning from demonstration algorithms usually assume access to expert demonstrations. However, this assumption is limiting in many real-world applications since the colle…
A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies
Homanga Bharadhwaj, Zihan Wang, Yoshua Bengio +1
Learning effective visuomotor policies for robots purely from data is challenging, but also appealing since a learning-based system should not require manual tuning or calibration.…