works on

From the 1 of 10 linked papers with an AI index.

collaborators

10 papers

cs.LG2026

-OPSD: Deriving with Policy Optimization, Training with Self-Distillation

Jiawei Xu, Minghui Liu, Juzheng Zhang +2

The paper proposes β‑OPSD, a generalized on‑policy self‑distillation method that treats the KL regularization weight as a tunable parameter, enabling a controlled interpolation bet…

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.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.LG2026

GATES: Self-Distillation under Privileged Context with Consensus Gating

Alex Stein, Furong Huang, Tom Goldstein

We study self-distillation in settings where supervision is unreliable: there are no ground truth labels, verifiable rewards, or external graders to evaluate answers. We focus on d…

cs.CV2026

Image Generation with a Sphere Encoder

Kaiyu Yue, Menglin Jia, Ji Hou +1

We introduce the Sphere Encoder, an efficient generative framework capable of producing images in a single forward pass and competing with many-step diffusion models using fewer th…

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…