Search papers, labs, and topics across Lattice.
9
0
12
5
Native computer use can be achieved at scale, enabling agents to outperform leading systems while significantly enhancing security against adversarial attacks.
GSR enables lightweight models to outperform heavily scaled counterparts, achieving near-perfect robustness to instruction rewording.
ResearchStudio-Reel not only automates research dissemination but does so with unprecedented quality, outperforming both traditional methods and leading LLMs in aesthetic appeal and information accuracy.
GASE reduces the sim-to-real performance gap to under 10% while outperforming existing methods in segmentation accuracy by over 10%.
Bridging the gap in multi-camera depth prediction, SurroundNEXO achieves a 33.2% reduction in single-view error by rethinking how we leverage ego-centric geometry.
YouZhi-LLM achieves unprecedented concurrency and accuracy in financial LLMs by dramatically reducing KV-cache overhead, setting a new standard for deployment efficiency.
Breaking the symmetry in adversarial distillation allows AAD-1 to generate videos that maintain dynamic motion without collapsing into static sequences.
Forget hand-crafted benchmarks: CUA-Gym's auto-generated training data lets computer-use agents crush existing open-source models on real-world tasks.
VLA models can be compressed to 29% of their original VRAM with minimal performance loss by intelligently quantizing different channels based on their impact on action execution.
