37 citations · 37 across the 13 of their papers we have counts for
7 papers · 1 filter
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…
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…
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…
Where and What to Reward? Understanding Generalization Between Verifiable and Open-Ended Domains in Reinforcement Learning
Shangjian Yin, Yu Fu, Yue Dong +1
Reinforcement learning with verifiable rewards (RLVR) is widely used to improve the reasoning capability of language models, since model-generated answers can be easily verified by…
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…
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…
Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language Models
Longxuan Yu, Yu Fu, Shaorong Zhang +4
Autoregressive (AR) language models enforce a fixed left-to-right generation order, creating a fundamental limitation when the required output structure conflicts with natural reas…