← Search

Yisong Wang

5 accepted papers

2025

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

CVPR 2025poster

We present JanusFlow, a powerful framework that unifies image understanding and generation in a single model.JanusFlow introduces a minimalist architecture that integrates autoregressive language models with rectified flow, a state-of-the-art method in generative modeling.Our key finding demonstrate…

2024

HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments

ICLR 2024poster

Recent advances in high-fidelity virtual environments serve as one of the major driving forces for building intelligent embodied agents to perceive, reason and interact with the physical world. Typically, these environments remain unchanged unless agents interact with them. However, in real-world sc…

2024

Interaction-centric Spatio-Temporal Context Reasoning for Multi-Person Video HOI Recognition

ECCV 2024poster

"Understanding human-object interaction (HOI) in videos represents a fundamental yet intricate challenge in computer vision, requiring perception and reasoning across both spatial and temporal domains. Despite previous success of object detection and tracking, multi-person video HOI recognition stil…