Yiming Wang

Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding

Do Large Language Models Truly Understand Geometric Structures?

Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation

Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning

RetroDiff: Retrosynthesis as Multi-stage Distribution Interpolation