collaborators

10 papers

cs.CV2026

Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models

Kaiwen Zheng, Guande He, Min Zhao +7

Autoregressive video diffusion with causal diffusion transformers has emerged as a major paradigm for real-time streaming video generation and action-conditioned interactive world…

cs.CV2026

Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency

Kaiwen Zheng, Yuji Wang, Qianli Ma +7

Although continuous-time consistency models (e.g., sCM, MeanFlow) are theoretically principled and empirically powerful for fast academic-scale diffusion, its applicability to larg…

cs.LG2026

The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation

Mingyi Liu

RLHF-aligned language models exhibit response homogenization: on TruthfulQA (n=790), 40-79% of questions produce a single semantic cluster across 10 i.i.d. samples. On affected que…

cs.LG2026

AVO: Agentic Variation Operators for Autonomous Evolutionary Search

Terry Chen, Zhifan Ye, Bing Xu +20

Agentic Variation Operators (AVO) are a new family of evolutionary variation operators that replace the fixed mutation, crossover, and hand-designed heuristics of classical evoluti…

cs.CV2026

InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression

Haotian Ye, Qiyuan He, Jiaqi Han +12

Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present…

cs.LG2026

NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning

Huayu Chen, Kaiwen Zheng, Qinsheng Zhang +8

Reinforcement Learning (RL) has played a central role in the recent surge of LLMs' math abilities by enabling self-improvement through binary verifier signals. In contrast, Supervi…