NeurIPS paper: neural compressed sensing boosts wet-lab info density by orders of magnitude
_onionesque · x · 2026-09-25
A NeurIPS-accepted paper by Eli Weinstein et al., "Lifting Biomolecular Data Acquisition," scales ML-driven science by raising wet-lab information density.
- Extends compressed sensing neurally to function space, measuring activity of multiple molecules simultaneously instead of one at a time.
- Deconvolves the molecule-activity map during training via co-design of experiments and learning algorithms.
- Provably yields orders-of-magnitude information-density gains, demonstrated on antibodies and cell therapies.
More from Research
- TorchCurves: Differentiable Learnable Parametric Curves for PyTorch — Alex Shtoff · 2026-11-11
- AI-assisted proof shows no voting rule beats Borda on strategyproofness — conitzer · 2026-11-11
- Markowitz mean-variance portfolio theory applied to mixing MCMC samplers — michaelchchoi · 2026-11-11
- AI agents run 24/7 for a month to rewrite Météo-France's AROME weather model — IgorCarron · 2026-11-11
- NYU's Steertuning Lets a Robot Learn a Chore From 5 Minutes of Human Demo — CyberRobooo · 2026-11-11
- New preprint maps human embryonic patterning in early organogenesis at spatial single-cell resolution — anshulkundaje · 2026-11-11