Saeyoon Oh's picture

4

Saeyoon Oh

saeyoonoh

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models

upvoted a paper 8 months ago

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling

upvoted a paper 8 months ago

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

View all activity

Organizations

upvoted a paper 10 days ago

Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models

Paper • 2606.16281 • Published 11 days ago • 34

upvoted 2 papers 8 months ago

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling

Paper • 2510.15346 • Published Oct 17, 2025 • 34

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

Paper • 2510.04767 • Published Oct 6, 2025 • 28

upvoted a paper 10 months ago

XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization

Paper • 2508.10395 • Published Aug 14, 2025 • 42