5 papers
Pixels to Proofs: Probabilistically-Safe Latent World Model Control via Parallel Conformal Robust MPC
Devesh Nath, Anutam Srinivasan, Haoran Yin +3
We present SLS^2, a framework for safe feedback motion planning from pixels using robust model predictive control (MPC) in learned latent world models. Our approach trains an actio…
Free Lunch for Unified Multimodal Models: Enhancing Generation via Reflective Rectification with Inherent Understanding
Yibo Jiang, Tao Wu, Rui Jiang +4
Unified Multimodal Models (UMMs) aim to integrate visual understanding and generation within a single structure. However, these models exhibit a notable capability mismatch, where…
Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-time Open-Vocabulary Object Detection
Yehao Lu, Minghe Weng, Zekang Xiao +5
The Mixture of Experts (MoE) architecture has excelled in Large Vision-Language Models (LVLMs), yet its potential in real-time open-vocabulary object detectors, which also leverage…
RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control
Teng Li, Guangcong Zheng, Rui Jiang +9
Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches. Ho…
Energy-Guided Optimization for Personalized Image Editing with Pretrained Text-to-Image Diffusion Models
Rui Jiang, Xinghe Fu, Guangcong Zheng +3
The rapid advancement of pretrained text-driven diffusion models has significantly enriched applications in image generation and editing. However, as the demand for personalized co…