Search papers, labs, and topics across Lattice.
4
0
7
5
Agents struggle with long-horizon tasks, achieving only a 15.2% success rate even with advanced models, highlighting a critical gap in current AI capabilities.
Robots can now plan 9x faster and achieve significantly higher success rates by decoupling action prediction from video generation in World-Action Models.
VLMs can now self-evolve from *zero* data, thanks to a multi-agent RL framework that synthesizes its own visual concepts and reasoning tasks.
Forget end-to-end VLAs: GigaBrain-0.5M* leverages world models and reinforcement learning to achieve a 30% performance boost on complex robotic manipulation tasks, showcasing reliable long-horizon execution.
