Search papers, labs, and topics across Lattice.
6
0
10
2
Task-CoEvolve slashes evaluation costs by 80% while maintaining performance parity with full-set validation in LLM harness optimization.
Even the most advanced AI models struggle with urban navigation, achieving only 17.1% accuracy compared to human performance of 77.3%.
GUSH3R achieves real-time dynamic human-scene reconstruction with photorealistic quality, outperforming traditional optimization methods in efficiency.
Wild3R achieves competitive performance against traditional optimization methods while eliminating the need for time-consuming scene-specific adjustments.
A single transformer model now beats specialized architectures at generating floorplans from diverse inputs, thanks to a unified markup language.
AI-written papers are surprisingly prone to hallucination, with even state-of-the-art models like ClaudeCode averaging over 10 factual errors per paper despite strong presentation.
