1 citations · 2 across the 16 of their papers we have counts for
19 papers
CoRe: Co-Evolving Reward Models for Mitigating Latent Reward Hacking in Video Diffusion Models
Zhaolong Su, Yujin Han, Feng Wang +3
Latent reward models (LRMs) enable efficient alignment of video diffusion models by scoring intermediate states directly in latent space. However, we find that optimizing against a…
SkillRubric: Co-Evolving Actor Guidance and Evaluator Rubrics for Multimodal Agents
Bingqing Jiang, Guoxi Zhang, Jasper Wang +7
Recent work incorporates reusable skills distilled from past interactions into multimodal agent training, providing procedural guidance for long-horizon planning and tool use. Howe…
From Static to Dynamic: On-Policy Distillation from Image to Video Diffusion Models
Bingqing Jiang, Li Luo, Zichao Yu +3
On-policy distillation (OPD) specializes pretrained video diffusion models through teacher supervision along the student's own generation trajectory. Although large video models ar…
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…
ReBind: Multi-Reference Video Editing via Structured Instructions with Explicit Reference Relationships
Xinyu Liu, Shihao Li, Weihong Lin +10
Recent diffusion-based video generation models have made significant progress in multi-reference image-conditioned video editing. However, existing methods still struggle to coordi…
MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation
Yujie Wei, Yujin Han, Zhekai Chen +20
Video generation is rapidly evolving from single-shot synthesis to complex multi-shot audio-video (MSAV) narratives to meet real-world demands. However, evaluating such frontier mo…
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…
Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning
Xinyu Liu, Hangjie Yuan, Yujie Wei +9
Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vi…
Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance
Yujie Wei, Shiwei Zhang, Hangjie Yuan +8
Mixture-of-Experts (MoE) has emerged as a powerful paradigm for scaling model capacity while preserving computational efficiency. Despite its notable success in large language mode…
Exploiting Discriminative Codebook Prior for Autoregressive Image Generation
Longxiang Tang, Ruihang Chu, Xiang Wang +6
Advanced discrete token-based autoregressive image generation systems first tokenize images into sequences of token indices with a codebook, and then model these sequences in an au…
Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs
Yujin Han, Hao Chen, Andi Han +5
Although unified MLLMs aim to unify generation and understanding, they are considered to exhibit an internal gap, with understanding outperforming generation. Through large-scale e…
Corruption-Aware Training of Latent Video Diffusion Models for Robust Text-to-Video Generation
Chika Maduabuchi, Hao Chen, Yujin Han +1
Latent Video Diffusion Models (LVDMs) have achieved state-of-the-art generative quality for image and video generation; however, they remain brittle under noisy conditioning, where…
Capturing Conditional Dependence via Auto-regressive Diffusion Models
Xunpeng Huang, Yujin Han, Difan Zou +2
Diffusion models have demonstrated appealing performance in both image and video generation. However, many works discover that they struggle to capture important, high-level relati…
Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
Yujin Han, Andi Han, Wei Huang +2
Despite the remarkable success of diffusion models (DMs) in data generation, they exhibit specific failure cases with unsatisfactory outputs. We focus on one such limitation: the a…
Masked Autoencoders Are Effective Tokenizers for Diffusion Models
Hao Chen, Yujin Han, Fangyi Chen +7
Recent advances in latent diffusion models have demonstrated their effectiveness for high-resolution image synthesis. However, the properties of the latent space from tokenizer for…
Parallelized Autoregressive Visual Generation
Yuqing Wang, Shuhuai Ren, Zhijie Lin +6
Autoregressive models have emerged as a powerful approach for visual generation but suffer from slow inference speed due to their sequential token-by-token prediction process. In t…
Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension Ability
Yujin Han, Lei Xu, Sirui Chen +2
Large language models (LLMs) have shown remarkable capability in natural language tasks, yet debate persists on whether they truly comprehend deep structure (i.e., core semantics)…
Slight Corruption in Pre-training Data Makes Better Diffusion Models
Hao Chen, Yujin Han, Diganta Misra +6
Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-quality images, audios, and videos. They benefit significantly from extensive pre-training on…
Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference
Yujin Han, Difan Zou
Standard empirical risk minimization (ERM) models may prioritize learning spurious correlations between spurious features and true labels, leading to poor accuracy on groups where…