Search papers, labs, and topics across Lattice.
5
0
9
3
LLMs can now generate reliable hardware reference models with 95% accuracy thanks to a novel co-evolutionary verification mechanism that weeds out correlated hallucinations between model and testbench.
LLMs can now reliably fix decompiled code, but only if you make them *execute* it.
Achieve higher quality 3D Gaussian Splatting reconstructions of objects from mobile phone captures using fewer images, thanks to a novel object-centered capture guidance system.
SynthFix achieves up to 32% better accuracy in code vulnerability repair by intelligently combining supervised and reward-based training strategies.
Context-augmented RL lets smaller MLLMs punch *way* above their weight, rivaling much larger models on reasoning tasks while dodging reward hacking.
