Search papers, labs, and topics across Lattice.
6
0
10
4
LDM achieves over 60% gains in multi-objective performance, revolutionizing how we approach open-ended hypothesis spaces in scientific discovery.
VANE's innovative approach to test-time training allows for selective and reversible adaptations, significantly boosting performance in dynamic manipulation tasks.
A maritime navigation policy trained purely in simulation can now successfully pilot a 17-ton vessel in real-world congested waters, zero-shot.
Quadrupedal robots can now swim more efficiently and stably thanks to a novel constrained reinforcement learning approach that tames destabilizing forces in complex fluid environments.
On-device LLM performance is heavily influenced by sequence length and model depth, with hardware heterogeneity creating efficiency traps that can be mitigated by architectural refinements like Multi-head Latent Attention.
Forget months of architecture search: this hardware co-design framework slashes the time to days and beats Qwen2.5-0.5B's perplexity by 19% at the same latency on NVIDIA Jetson Orin.
