Yingbin Liang

6

Papers

24

Total Citations

Papers (6)

Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining

Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers

Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers

Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees

NeurIPS 2025arXiv

DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity