ByteDance Seed releases MLIP-liquid-corrections: 2M molecular configs for liquid simulations
_akhaliq · x · 2026-11-06
ByteDance's Seed team published the MLIP-liquid-corrections dataset on Hugging Face, targeting accuracy of machine-learning interatomic potentials (MLIPs) in liquid simulations.
- Provides BSSE (basis set superposition error) and ATM (Axilrod–Teller–Muto three-body) correction labels for 2M molecular configurations derived from OMol25, with 1.61M ATM rows and 420k BSSE rows
- Intended for fine-tuning MLIPs so liquid-phase molecular dynamics simulations get more accurate energies and interactions
- Released as CSV with SMILES/mapped SMILES and atom-count metadata under a cc-by-4.0 license
- Companion paper available on arXiv (2611.06109)
More from Research
- Meta's real-time avatars: distillation recipe cuts 120 model evals to 2, a 60x speedup for infinite video — altryne · 2026-11-07
- Free primer book derives math foundations from VAEs and diffusion to WGANs — kalyan_kpl · 2026-11-07
- Kenneth Stanley at ARC Prize summit: why open-endedness is essential to AGI but brutal to benchmark — GregKamradt · 2026-11-07
- GLASS preprint teaser: graph-led LLM-assisted scoring of open-ended responses without human coding — GolinoHudson · 2026-11-07
- LLMs can read and patch weights, but 20 fine-tuning steps erase the edits — kevinpl07 · 2026-11-07
- FlexiTac-Gen launches: AI-agent-assisted tool to design custom tactile sensors, accepted to CoRL 2026 — Haoyu_Xiong_ · 2026-11-07