Search papers, labs, and topics across Lattice.
7
0
10
12
Key research priorities for multi-agent embodied autonomous driving (MAEAD): verifiable shared-state maintenance, robust intent and plan alignment, and safe coordinated action under communication and computing constraints in real-world deployment are motivated.
Augmenting images from a model's own failures can lead to substantial performance boosts in multimodal tasks, outperforming conventional augmentation techniques.
CoTIR achieves superior image restoration by internalizing reasoning processes, outperforming traditional methods even in complex degradation settings.
UCE enables LLM agents to evolve their knowledge dynamically, achieving a staggering 96.3% success rate in complex tasks by leveraging a structured experience library.
LLMs can learn to reason better by validating "skill-based teachers" derived from past experiences, even when those teachers are sometimes wrong.
Finally, a way to train LLM agents to reason step-by-step without needing humans to check every intermediate thought.
Visual RL agents can recover near-perfect performance even under severe, dynamically changing visual corruptions by learning to disentangle task-relevant foreground from perturbation artifacts.
