collaborators

13 papers

cs.CL2026

Not All LLM Reasoning is Visible in the Chain-of-Thought

Vatsal Baherwani, Tom Goldstein, Ashwinee Panda

A key question for AI safety is whether a language model expresses all of its reasoning in its output tokens. We demonstrate a concrete failure mode where frontier models exhibit i…

cs.CL2026

Multi-Token Prediction via Self-Distillation

John Kirchenbauer, Abhimanyu Hans, Brian Bartoldson +3

Existing techniques for accelerating language model inference, such as speculative decoding, require training auxiliary speculator models and building and deploying complex inferen…

cs.LG2026

Speculating Experts Accelerates Inference for Mixture-of-Experts

Vivan Madan, Prajwal Singhania, Abhinav Bhatele +2

Mixture-of-Experts (MoE) models have gained popularity as a means of scaling the capacity of large language models (LLMs) while maintaining sparse activations and reduced per-token…

cs.AI2026

From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions

Rishab Alagharu, Ishneet Sukhvinder Singh, Shaibi Shamsudeen +2

Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal tokens that distinguish differe…

cs.LG2026

Identifying and Evaluating Inactive Heads in Pretrained LLMs

Pedro Sandoval-Segura, Xijun Wang, Ashwinee Panda +4

Attention is foundational to large language models (LLMs), enabling different heads to have diverse focus on relevant input tokens. However, learned behaviors like attention sinks,…

cs.CV2025

FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges

Kevin David Hayes, Micah Goldblum, Vikash Sehwag +3

Text-to-image (T2I) models are capable of generating visually impressive images, yet they often fail to accurately capture specific attributes in user prompts, such as the correct…