collaborators

9 papers

stat.ME2026

FlowSDR: Sufficient Dimension Reduction via Conditional Normalizing Flows

Yuexiao Dong, Kenichiro Mcalinn, Edoardo Airoldi +1

Sufficient dimension reduction (SDR) seeks a low-dimensional linear projection of predictors that preserves the conditional distribution of the response. Existing methods target th…

cs.CL2026

Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models

Longxuan Yu, Shaorong Zhang, Yu Fu +3

Masked diffusion language models (MDLMs) re-predict every position at each denoising step, but standard samplers commit tokens once revealed, leaving this revision capability unuse…

cs.CL2026

DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs

Longxuan Yu, Yunshu Wu, Yu Fu +5

Discrete Masked diffusion language models generate text by iterative parallel decoding, but few-step decoding suffers from a tradeoff between length and quality: with a fixed step…

cs.LG2026

GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero

Shangjian Yin, Yu Fu, Yue Dong +1

Post-training has become a crucial step for unlocking the capabilities of large language models, with reinforcement learning (RL) emerging as a critical paradigm. Recent RL-based p…

cs.LG2026

Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation

Yu Fu, Longxuan Yu, Haz Sameen Shahgir +4

Safety alignment often improves robustness to harmful queries at the cost of reasoning ability, a tradeoff known as the safety tax. A common cause is distributional mismatch: super…

cs.CR2026

MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks

Xinkai Zhang, Zhipeng Wei, Huanli Gong +4

Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can g…