collaborators

6 papers

cs.LG2026

Reinforcement Learning without Ground-Truth Solutions can Improve LLMs

Yingyu Lin, Qiyue Gao, Nikki Lijing Kuang +6

Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applicability to tasks where the gr…

cs.LG2026

On the -Free Inference Complexity of Absorbing Discrete Diffusion

Xunpeng Huang, Yingyu Lin, Nishant Jain +4

Absorbing discrete diffusion has emerged as a dominant framework for discrete data generation. However, a significant disparity remains between its empirical success and theoretica…

cs.CR2025

Purifying Approximate Differential Privacy with Randomized Post-processing

Yingyu Lin, Erchi Wang, Yi-An Ma +1

We propose a framework to convert -approximate Differential Privacy (DP) mechanisms into -pure DP mechanisms under certain conditions, a proce…

cs.CL2025

Beyond Length: Quantifying Long-Range Information for Long-Context LLM Pretraining Data

Haoran Deng, Yingyu Lin, Zhenghao Lin +4

Long-context language models unlock advanced capabilities in reasoning, code generation, and document summarization by leveraging dependencies across extended spans of text. Howeve…

stat.ML2025

Almost Linear Convergence under Minimal Score Assumptions: Quantized Transition Diffusion

Xunpeng Huang, Yingyu Lin, Nikki Lijing Kuang +4

Continuous diffusion models have demonstrated remarkable performance in data generation across various domains, yet their efficiency remains constrained by two critical limitations…

cs.LG2025

A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery

Yingyu Lin, Yuxing Huang, Wenqin Liu +6

Real-world data often violates the equal-variance assumption (homoscedasticity), making it essential to account for heteroscedastic noise in causal discovery. In this work, we expl…