Search papers, labs, and topics across Lattice.
6
0
12
CT-VAM achieves competitive performance with a fraction of the parameters, enabling efficient real-time control for robotic manipulation.
VLBM achieves state-of-the-art OOD robustness while maintaining high in-distribution accuracy, outperforming existing methods by a notable margin.
MONA unlocks faster LLM pretraining and superior downstream performance by turbocharging the Muon optimizer with Nesterov-style acceleration, leaving AdamW in the dust.
A 440MB multilingual translation model now rivals commercial APIs, opening the door for performant on-device translation.
Android API research is built on shaky ground: official API lists are surprisingly inconsistent, leading to potentially flawed conclusions.
LLMs still fail to follow complex instructions that entangle content, formatting, control flow, and real-world constraints, despite progress on simpler benchmarks.
