Minjae Lee

Draft-based Approximate Inference for LLMs

ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs

VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data

Generating Multi-Table Time Series EHR from Latent Space with Minimal Preprocessing

In-batch Ensemble Drafting: Toward Fast and Robust Speculative Decoding for Multimodal Language Models