10 papers
Mismatch Matters: On-Policy Distillation Beyond Token Agreement
Zichao Yu, Chengzhi Yu, Shengze Xu +4
On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement, where students exploit repet…
Toward Native Multimodal Modeling: A Roadmap
Siyu An, Junru Lu, Junnan Dong +18
Multimodal modeling represents a vital step from modality-agnostic reasoning toward world modeling. While early approaches predominantly rely on late-fusion that assembles encoders…
Relative Score Policy Optimization for Diffusion Language Models
Zichao Yu, Shengze Xu, Bingqing Jiang +2
Diffusion large language models (dLLMs) offer a promising route to parallel and efficient text generation, but improving their reasoning ability requires effective post-training. R…
AesRM: Improving Video Aesthetics with Expert-Level Feedback
Yujin Han, Yujie Wei, Yefei He +7
Despite rapid advances in photorealistic video generation, real-world applications such as filmmaking require video aesthetics, e.g., harmonious colors and cinematic lighting, beyo…
ProFlow: Zero-Shot Physics-Consistent Sampling via Proximal Flow Guidance
Zichao Yu, Ming Li, Wenyi Zhang +2
Inferring physical fields from sparse observations while strictly satisfying partial differential equations (PDEs) is a fundamental challenge in computational physics. Recently, de…
Fast-ARDiff: An Entropy-informed Acceleration Framework for Continuous Space Autoregressive Generation
Zhen Zou, Xiaoxiao Ma, Jie Huang +2
Autoregressive(AR)-diffusion hybrid paradigms combine AR's structured modeling with diffusion's photorealistic synthesis, yet suffer from high latency due to sequential AR generati…