Search papers, labs, and topics across Lattice.
WeChat HPC, Tencent Inc.
4
0
8
4
Runtime load balancing in FVAttn slashes attention processing time by over four times, transforming video generation efficiency.
Physically aligned video models can boost robotic manipulation success rates by over 50% compared to traditional methods.
Egocentric human video can outperform traditional teleoperated robot data, achieving superior performance in embodied model pretraining with lower costs and greater diversity.
Current Vision-Language Models get stuck in Pokemon Legends: Z-A not because they can't plan, but because they can't get unstuck.
