497 citations · 2.1k across the 297 of their papers we have counts for
45 papers · 1 filter
Can You Trust Your Preference Models? Stackelberg Games for Alignment
Riccardo Formenti, Aditya Agrawal, Vikas Garg
Language models are frequently aligned to human preferences via imperfect evaluators whose errors can be exploited during optimization. We train policies to search for comparisons…
Scaling Curriculum Learning For Autonomous Driving
Cevahir Koprulu, David Paz, Feng Tao +4
Batched simulators for autonomous driving have recently enabled training reinforcement learning (RL) agents at scale, encompassing thousands of traffic scenarios and billions of in…
Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers
Thiago Sandoval, Ufuk Topcu
Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired pol…
What We are Missing in Multimodal LLM Evaluation?
Po-han Li, Shenghui Chen, Sandeep Chinchali +1
Multimodal large language models (MLLMs) can process diverse inputs, e.g., text, images, audio, and video, and generate textual responses. While their capabilities have advanced ra…
Physically Viable World Models: A Case for Query-Conditioned Embodied AI
Adam J. Thorpe, Stepan Tretiakov, Cheng-Hsi Hsiao +6
World models for embodied AI must be physically viable: constructed to answer intervention queries by representing the physical structure governing action outcomes, rather than mer…
Neurosymbolic LoRA: Why and When to Tune Weights vs. Rewrite Prompts
Kevin Wang, Neel P. Bhatt, Cong Liu +7
Large language models (LLMs) can be adapted either through numerical updates that alter model parameters or symbolic manipulations that work on discrete prompts or logical constrai…