3 papers
cs.CV2026
PhiZero: A World Model Built Around Physical Language
Shuyao Shang, Yuqi Wang, Ruopeng Gao +4
We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing physical world models typically…
cs.CV2026
UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer
Shuai Wang, Liang Li, Yang Chen +3
Unified Multimodal Models (UMMs) have emerged as a critical direction for general-purpose multimodal intelligence, integrating understanding and generation into a single framework.…
cs.CV2025
Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval
Chunxu Liu, Jiyuan Yang, Ruopeng Gao +4
Multimodal embeddings are widely used in downstream tasks such as multimodal retrieval, enabling alignment of interleaved modalities in a shared representation space. While recent…