collaborators

8 papers

cs.CV2026

HERO: Hierarchical Extrapolation and Refresh for Efficient World Models

Quanjian Song, Xinyu Wang, Donghao Zhou +3

Generation-driven world models create immersive virtual environments but suffer slow inference due to the iterative nature of diffusion models. While recent advances have improved…

cs.LG2026

DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning

Zhongwei Wan, Yun Shen, Zhihao Dou +9

Reinforcement learning with verifiers (RLVR) is a central paradigm for improving large language model (LLM) reasoning, yet existing methods often suffer from limited exploration. P…

cs.CV2026

MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents

Peizhou Huang, Zixuan Zhong, Zhongwei Wan +12

Deep Research Agents (DRAs) generate citation-rich reports via multi-step search and synthesis, yet existing benchmarks mainly target text-only settings or short-form multimodal QA…

cs.CV2025

IdentityStory: Taming Your Identity-Preserving Generator for Human-Centric Story Generation

Donghao Zhou, Jingyu Lin, Guibao Shen +8

Recent visual generative models enable story generation with consistent characters from text, but human-centric story generation faces additional challenges, such as maintaining de…

cs.CV2025

StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors

Guibao Shen, Yihua Du, Wenhang Ge +7

The rapid growth of stereoscopic displays, including VR headsets and 3D cinemas, has led to increasing demand for high-quality stereo video content. However, producing 3D videos re…

cs.CV2025

SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency

Quanjian Song, Donghao Zhou, Jingyu Lin +5

Recent text-to-image models have revolutionized image generation, but they still struggle with maintaining concept consistency across generated images. While existing works focus o…