1 citations · 1 across the 2 of their papers we have counts for
5 papers
Code Monitor Red Teaming for Public-Test-Passing Code
Junchi Liao, Jiawen Deng, Fuji Ren
Visible tests are a common gate for LLM-generated code, but passing them does not certify specification correctness. We study a deployment-like monitoring problem: after code has p…
Using Language Models as Closed-Loop High-Level Planners for Robotics Applications: A Brief Overview and Benchmarks
Hao Wang, Sathwik Karnik, Bea Lim +1
Large Language Models (LLMs) and Vision Language Models (VLMs) have become popular tools for embodied high-level planning. However, their deployment in black-box settings often lea…
Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion
Sathwik Karnik, Juyeop Kim, Sanmi Koyejo +2
Text-to-image diffusion models often memorize training data, revealing a fundamental failure to generalize beyond the training set. Current mitigation strategies typically sacrific…
Preemptive Detection and Steering of LLM Misalignment via Latent Reachability
Sathwik Karnik, Somil Bansal
Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach --…
Embodied Red Teaming for Auditing Robotic Foundation Models
Sathwik Karnik, Zhang-Wei Hong, Nishant Abhangi +5
Language-conditioned robot models have the potential to enable robots to perform a wide range of tasks based on natural language instructions. However, assessing their safety and e…