6 papers
Contact-Anchored Policies: Contact Conditioning Creates Strong Robot Utility Models
Zichen Jeff Cui, Omar Rayyan, Haritheja Etukuru +16
The prevalent paradigm in robot learning attempts to generalize across environments, embodiments, and tasks with language prompts at runtime. A fundamental tension limits this appr…
InterpDetect: Interpretable Signals for Detecting Hallucinations in Retrieval-Augmented Generation
Likun Tan, Kuan-Wei Huang, Joy Shi +1
Retrieval-Augmented Generation (RAG) integrates external knowledge to mitigate hallucinations, yet models often generate outputs inconsistent with retrieved content. Accurate hallu…
FRED: Financial Retrieval-Enhanced Detection and Editing of Hallucinations in Language Models
Likun Tan, Kuan-Wei Huang, Kevin Wu
Hallucinations in large language models pose a critical challenge for applications requiring factual reliability, particularly in high-stakes domains such as finance. This work pre…
Can Large Language Models Match the Conclusions of Systematic Reviews?
Christopher Polzak, Alejandro Lozano, Min Woo Sun +4
Systematic reviews (SR), in which experts summarize and analyze evidence across individual studies to provide insights on a specialized topic, are a cornerstone for evidence-based…
PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement
Tewodros Ayalew, Xiao Zhang, Kevin Yuanbo Wu +3
We present PROGRESSOR, a novel framework that learns a task-agnostic reward function from videos, enabling policy training through goal-conditioned reinforcement learning (RL) with…
Emergenet: A Digital Twin of Sequence Evolution for Scalable Emergence Risk Assessment of Animal Influenza A Strains
Kevin Yuanbo Wu, Jin Li, Aaron Esser-Kahn +1
Despite having triggered devastating pandemics in the past, our ability to quantitatively assess the emergence potential of individual strains of animal influenza viruses remains l…