Search papers, labs, and topics across Lattice.
7
0
9
0
Atria Dawn Preview is introduced, a foundation agentic language model designed for scientific research and engineering workflows, with the goal of expanding the frontier of agent productivity in the real world.
Instead of relying on brittle prompt histories or rigid hand-coded workflows, LLM agents can now autonomously construct, debug, and evolve their own graph-structured execution policies purely from contrastive trial and error.
A novel NMPC framework allows tiltable-multirotors to perform complex aerial manipulations while seamlessly handling disturbances and singular configurations.
A novel control strategy allows multi-link aerial robots to seamlessly combine disturbance resistance and adaptive compliance, revolutionizing their performance in contact-rich environments.
CoFL-S achieves superior navigation performance by leveraging language-conditioned flow fields, outperforming traditional action representations in both simulation and real-world applications.
MiniMax-M2 proves that massive parameter counts don't always translate to better agentic performance; strategic activation of a smaller subset can unlock frontier-level intelligence.
Automating LLM fine-tuning is now possible: a multi-agent system, TREX, matches or exceeds human performance on a diverse set of real-world tasks.
