GS-DFT: Gaussian Splatting scales DFT simulations to 2,742 atoms on 4 H200s
AllThingsApx · x · 2026-09-28
AllThingsApx highlights the new GS-DFT paper: adaptive bases are pushing differentiable density functional theory to larger systems, reaching 2,742 atoms on four H200 GPUs. The authors see reliable forces at lower compute cost as the next frontier.
Full details are covered in the companion paper post (arXiv:2609.31483): GS-DFT represents molecular orbitals as a jointly optimized cloud of Gaussians trained without data, matching the largest conventional basis sets with far fewer parameters.
Related event: GS-DFT Scales Quantum Chemistry to 2,742 Atoms via Gaussian Splatting(4 posts)→
More from Research
- Continual-ARC: lifelong ARC-AGI stream finds agent harness persistence rarely beats simple caching — unifyai · 2026-11-16
- DySENSE: MIT's GenAI framework synthesizes satellite imagery with dynamic city energy maps — MIT · 2026-11-16
- WebArena-Pro: a 300-task multimodal benchmark across 20 self-hosted apps for web agents — McGill-NLP · 2026-11-16
- Training-free page-sparse decode in llama.cpp: 1.72× faster 128k decoding on an RTX 5090 — topppggg · 2026-11-16
- Training Qwen3-8B to drive a simulated hand spawns a dedicated internal 'pressure' direction — repligate · 2026-11-16
- Google Research open-sources PaperOrchestra, a multi-agent framework for writing AI papers — google-research · 2026-11-16