1 citations · 2 across the 10 of their papers we have counts for
12 papers
4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding
Zhangquan Chen, Manyuan Zhang, Xinlei Yu +9
Dynamic spatial reasoning from monocular video is essential for bridging visual intelligence and the physical world, yet remains challenging for vision-language models (VLMs). Prio…
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
Xiangyuan Xue, Yifan Zhou, Zidong Wang +5
Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficult because current methods are largely…
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
Zile Wang, Zexiang Liu, Jiaxing Li +20
With the advancement of interactive video generation, diffusion models have increasingly demonstrated their potential as world models. However, existing approaches still struggle t…
Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation
Xiaoyu Yue, Zidong Wang, Yuqing Wang +5
Recent studies have demonstrated the importance of high-quality visual representations in image generation and have highlighted the limitations of generative models in image unders…
Transition Models: Rethinking the Generative Learning Objective
Zidong Wang, Yiyuan Zhang, Xiaoyu Yue +4
A fundamental dilemma in generative modeling persists: iterative diffusion models achieve outstanding fidelity, but at a significant computational cost, while efficient few-step al…
Native-Resolution Image Synthesis
Zidong Wang, Lei Bai, Xiangyu Yue +2
We introduce native-resolution image synthesis, a novel generative modeling paradigm that enables the synthesis of images at arbitrary resolutions and aspect ratios. This approach…
Exploring Representation-Aligned Latent Space for Better Generation
Wanghan Xu, Xiaoyu Yue, Zidong Wang +6
Generative models serve as powerful tools for modeling the real world, with mainstream diffusion models, particularly those based on the latent diffusion model paradigm, achieving…
FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model
ZiDong Wang, Zeyu Lu, Di Huang +4
\textit{Nature is infinitely resolution-free}. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing imag…
Diffusion Models Need Visual Priors for Image Generation
Xiaoyu Yue, Zidong Wang, Zeyu Lu +5
Conventional class-guided diffusion models generally succeed in generating images with correct semantic content, but often struggle with texture details. This limitation stems from…
ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems
Xiangyuan Xue, Zeyu Lu, Di Huang +3
Much previous AI research has focused on developing monolithic models to maximize their intelligence, with the primary goal of enhancing performance on specific tasks. In contrast,…
PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplines
ZiDong Wang, Zeyu Lu, Di Huang +4
In this paper, we introduce PredBench, a benchmark tailored for the holistic evaluation of spatio-temporal prediction networks. Despite significant progress in this field, there re…
FiT: Flexible Vision Transformer for Diffusion Model
Zeyu Lu, Zidong Wang, Di Huang +4
Nature is infinitely resolution-free. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolut…