Improves stability and consistency for multi-turn image editing by training autoregressive diffusion editors with Single-Turn Distribution Matching Distillation and Teacher-Forcing Guidance. Combines a single-turn teacher for visual-quality supervision and trajectory-based teacher-forcing to preserve edits across successive turns.
Embodied AI2026
Learns executable language-conditioned local navigation by pretraining on instruction-conditioned Internet egocentric videos, aligning learned visual dynamics with simulated action labels, then jointly fine-tuning for navigation. Achieves high success rates on short-horizon benchmarks (86.5% OVON, 94.9% HabitatGS-LN) with real-robot validation and released code/data.