Lila Sciences' first NeurIPS paper: MOSAIC any-to-any flow matching for molecules and spectra
CatAstro_Piyush · x · 2026-11-21
Lila Sciences will present its first NeurIPS paper (in Sydney) introducing MOSAIC, a multimodal flow matching transformer over molecular 3D structure and UV/IR/Raman spectra. The key insight: experiments are expensive and data-limited, but each yields multiple coupled measurements; random masking lets any modality serve as conditioning input or prediction target, extracting multiple supervised denoising tasks from a single experiment. On QM9S, MOSAIC achieves 88.8% molecular graph recovery, beating the strongest spectra-to-structure baseline by 23.2% in structure generation while also outperforming a structure-to-spectra specialist model; ablations show the any-to-any objective improves structure generation across model sizes.
More from Research
- EFE-98 sim benchmark hits 0.98 correlation with real-robot rankings at 1/10 the cost — ManlingLi_ · 2026-11-21
- Terence Tao blogs on the Riemann hypothesis, weighs AI-generated proofs and Masullo manuscript — burny_tech · 2026-11-21
- Crowd replay of claimed RH proof: 35 contributors verify 18.76% of Lean modules in 4 hours — RexDouglass · 2026-11-21
- FrontierRSI, a new recursive self-improvement benchmark, launches with builder interview — Madisonkanna · 2026-11-21
- 4 Independent Kernels Verify Landmark Lean Proof of Riemann Hypothesis Theorems — altryne · 2026-11-21
- 112M-param PhiloLM trained from scratch on philosophy texts in 15 hours on a $350 GPU — antcroca159 · 2026-11-21