9 papers
Beyond Uniform Subspaces: Spectrum-Aware and Depth-Adaptive Fusion for Multi-Task Model Merging
Ruxi Gu, Zilei Wang, Wei Wang
Model merging aims to consolidate multiple task-specific models without access to extra training process. However, existing subspace-based methods largely rely on a uniform treatme…
Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory
Runjia Qian, Zile Wang, Jihai Zhang +14
Interactive world models extend video generation from offline clip synthesis toward persistent simulation of interactive virtual worlds, enabling applications in games, robotics, e…
Riemann-1.0: An Embodied World Action Model for Physical AI
Haofeng Sun, Jiangbo Pei, Fei Kang +13
We introduce Riemann-1.0, a fully causal autoregressive World Action Model for embodied intelligence. Riemann-1.0 jointly models multi-view visual observations, robot states, and e…
DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation
Jiaxing Li, Kai Zou, Cindy Zhou +7
Existing autoregressive video distillation methods commonly adopt a Distribution Matching Distillation (DMD)-based multi-stage pipeline. However, they typically decouple the initia…
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…
Exploring Motion-Language Alignment for Text-driven Motion Generation
Ruxi Gu, Zilei Wang, Wei Wang
Text-driven human motion generation aims to synthesize realistic motion sequences that follow textual descriptions. Despite recent advances, accurately aligning motion dynamics wit…
OmniAlpha: Aligning Transparency-Aware Generation via Multi-Task Unified Reinforcement Learning
Hao Yu, Jinglin Wang, Jiabo Zhan +7
Transparency-aware generation requires modeling not only RGB appearance but also alpha-based opacity and cross-layer composition, which are essential for tasks such as image mattin…
AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation Learning
Zile Wang, Hao Yu, Jiabo Zhan +1
Recent advances in latent diffusion models have achieved remarkable results in high-fidelity RGB image synthesis by leveraging pretrained VAEs to compress and reconstruct pixel dat…
Multi-scale Spatial-temporal Interaction Network for Video Anomaly Detection
Zhiyuan Ning, Zhangxun Li, Zhengliang Guo +2
Video Anomaly Detection (VAD) is an essential yet challenging task in signal processing. Since certain anomalies cannot be detected by isolated analysis of either temporal or spati…