Search papers, labs, and topics across Lattice.
5
0
3
UniMPA, a Unified Memory-Prediction-Action model that addresses transition ambiguity by modeling the intended future state evolution through a shared action-grounded transition interface, is proposed.
Transforming noisy visual observations into reliable spatial guidance, AeroBelief achieves unprecedented navigation success rates for UAVs in complex environments.
Egocentric motion forecasting fails without explicit spatial goals; anchoring residual flow matching to predicted continuous 3D interaction targets eliminates structural drift and aligns full-body trajectories with human intent.
TINA+ uncovers that current concept erasure methods often fail to eliminate visual knowledge, revealing a hidden layer of understanding in diffusion models.
LookAgain's innovative closed-loop approach allows for real-time refinement of GUI grounding predictions, drastically improving accuracy on difficult tasks.
