9 papers
FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching
Ruchang Yao, Shi Guo, Junhao Zhuang +7
Recent video super-resolution (VSR) models achieve efficient one-step generation through diffusion distillation. However, high-resolution inference remains costly, and distilled mo…
DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation
Jiahao Zhan, Yan Wang, Yongrui Ma +5
Streaming video generation has benefited from distribution matching distillation (DMD), which matches the joint distribution of video frames to a video teacher's approximation of t…
Agentic Visual Generation: From Generative Models to Agentic Control
Yinming Huang, Shuyuan Tu, Xi Yan +7
Visual generation is evolving from generative models used through a single invocation into agentic control processes that can plan, select tools, inspect intermediate synthesized o…
PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation
Jiahao Zhan, Zizhang Li, Hong-Xing Yu +1
We introduce PerpetualWonder, a hybrid generative simulator that enables long-horizon, action-conditioned 4D scene generation from a single image. Current works fail at this task b…
CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation
Mingzhe Zheng, Dingjie Song, Guanyu Zhou +7
Large Language Models (LLMs) have demonstrated remarkable proficiency in generating highly structured texts. However, while exhibiting a high degree of structural organization, mov…
TreeMind: Automatically Reproducing Android Bug Reports via LLM-empowered Monte Carlo Tree Search
Zhengyu Chen, Zhaoyi Meng, Wenxiang Zhao +5
Automatically reproducing Android app crashes from textual bug reports is challenging, particularly when the reports are incomplete and the modern UI exhibits high combinatorial co…
MAC: A Live Benchmark for Multimodal Large Language Models in Scientific Understanding
Mohan Jiang, Jin Gao, Jiahao Zhan +1
As multimodal large language models (MLLMs) grow increasingly capable, fixed benchmarks are gradually losing their effectiveness in evaluating high-level scientific understanding.…
Fake it till You Make it: Reward Modeling as Discriminative Prediction
Runtao Liu, Jiahao Zhan, Yingqing He +3
An effective reward model plays a pivotal role in reinforcement learning for post-training enhancement of visual generative models. However, current approaches of reward modeling s…
Generalizing Motion Planners with Mixture of Experts for Autonomous Driving
Qiao Sun, Huimin Wang, Jiahao Zhan +7
Large real-world driving datasets have sparked significant research into various aspects of data-driven motion planners for autonomous driving. These include data augmentation, mod…