Search papers, labs, and topics across Lattice.
4
11
9
3
Combining language supervision with future latent alignment in VLA models leads to unprecedented stability and transfer performance across diverse robotic tasks.
Positional leakage in 3D masked autoencoders can be mitigated, leading to significantly improved semantic representation quality.
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.
LLMs struggle to actively collaborate and continuously adapt in complex, interactive environments, despite showing proficiency in goal interpretation.
