Kangwook Lee: Train Both Model Weights and Harness with Data, Links to Physics-Integrated Neural Network Paper on Cryogenic Storage
Kangwook_Lee · x · 2026-09-03
Kangwook Lee tweets that with data, one can and should train both model weights and the 'harness', linking to an arXiv paper. The paper presents a physics-integrated neural network framework for heat and mass transfer in cryogenic liquid storage, combining a conservation-based zero-dimensional nodal model with data-driven closures, validated on 48 experiments.
More from Research
- 'Transformers are samplers, not runtimes' — why residual streams can't host structured computation — gerardsans · 2026-09-03
- Information Bottleneck podcast to livestream Jonas Geiping on recurrent-depth models — ziv_ravid · 2026-09-03
- ICLR 2027's deanonymization policy wins fans; researcher urges slashing submission cap to 5 — peter_richtarik · 2026-09-03
- motion-bricks.cpp hits GitHub: tiny model generates animations in realtime on a desktop CPU — zhengyiluo · 2026-09-03
- Mostik bridges frontier and small models in latent space, tops ARC-AGI 3 at 1/20th the cost — SimplyAnnisa · 2026-09-03
- Mechanism Design Could Shape AI Behavior Without Understanding Neural Nets, Argues Economist — morqon · 2026-09-03