Search papers, labs, and topics across Lattice.
6
0
8
3
UBEP slashes All-to-All latency by over 52%, unlocking the full potential of Mixture-of-Experts models on superpod architectures.
Robots can now navigate crowded spaces more effectively by understanding human intentions, thanks to a new method that integrates rich visual cues into their decision-making process.
Realistic pedestrian simulations can significantly improve the training and evaluation of human-aware navigation systems, bridging the gap between simulated and real-world interactions.
LLMs show significant variability in the actionability of their UX critiques, with some models outperforming others across different product categories.
Hallucinations in video models can be mitigated by intelligently patching visual tokens, leading to a 50.60% improvement in response accuracy.
MXFP4 quantization just got a whole lot better: BATQuant recovers up to 96.43% of full-precision performance in LLMs and MLLMs, even under aggressive W4A4KV16 settings, by preventing outlier propagation across quantization blocks.
