Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
3
0
8
Over 70% of sparse autoencoder features exhibit fundamentally mismatched input and output semantics, breaking the common assumption that what activates a feature directly mirrors its downstream causal effect.
A 440MB multilingual translation model now rivals commercial APIs, opening the door for performant on-device translation.
Forget fine-tuning: DM0 shows that pretraining a VLA model from scratch on diverse embodied and non-embodied data leads to SOTA performance in physical AI tasks.