3 papers
cs.CV2025
What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards
Minh-Quan Le, Yuanzhi Zhu, Vicky Kalogeiton +1
Recent video diffusion models can synthesize visually compelling clips, yet often violate basic physical laws-objects float, accelerations drift, and collisions behave inconsistent…
cs.RO2025
DUViN: Diffusion-Based Underwater Visual Navigation via Knowledge-Transferred Depth Features
Jinghe Yang, Minh-Quan Le, Mingming Gong +1
Autonomous underwater navigation remains a challenging problem due to limited sensing capabilities and the difficulty of constructing accurate maps in underwater environments. In t…
cs.CV2025
Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment
Minh-Quan Le, Gaurav Mittal, Tianjian Meng +5
While diffusion models are powerful in generating high-quality, diverse synthetic data for object-centric tasks, existing methods struggle with scene-aware tasks such as Visual Que…