Search papers, labs, and topics across Lattice.
6
0
12
3
Combining language supervision with future latent alignment in VLA models leads to unprecedented stability and transfer performance across diverse robotic tasks.
LLMs can now rank millions of candidates with significant accuracy gains thanks to a novel K-means clustering and graph-based ensemble approach that overcomes context length limitations.
Unlock scalable autonomous driving simulation with AnyScene, a framework that generates controllable, high-fidelity driving scenes from arbitrary BEV layouts and camera configurations.
By dynamically injecting frequency-aware n-gram features, X-GRAM achieves state-of-the-art accuracy with smaller embedding tables, offering a practical path to scaling memory-augmented architectures.
Ditching caches for compiler-managed data streams, Li Auto's M100 architecture achieves higher utilization than GPUs on autonomous driving tasks, hinting at a new path for efficient AI inference.
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.
