Search papers, labs, and topics across Lattice.
7
0
11
0
Most video world models fail basic physics tests, with even the best models exhibiting significant physical inconsistencies across mechanics, optics, and fluids.
Only 5.4% of coding agent attempts successfully complete a migration while preserving behavioral correctness, exposing a critical gap in current AI capabilities for software evolution.
Agents struggle to significantly improve training algorithms, with the best only achieving 25% of the potential optimization gap.
AdvFD not only boosts visual quality in generative models but also tackles the pitfalls of static feature spaces that lead to stagnation in performance.
Switching music tokenization can halve the Frechet Music Distance, proving that representation trumps model size in text-to-music generation.
PhysRAG not only elevates visual fidelity in video generation but also ensures compliance with physical laws, setting a new benchmark for realism in AI-generated content.
GPT-5 can only solve 37% of PhD-level 3D geometry coding problems, suggesting AI can't reliably automate complex scientific coding tasks yet.
