Not brute-force scaling: professor praises domain-crafted architecture and loss design in gene-regulation model
anshulkundaje · x · 2026-11-12
Anshul Kundaje stresses the model is not a brute-force scaling exercise: its architecture, training scheme, loss functions and data normalization were carefully crafted by people with deep domain knowledge, calling the methods section a gold mine of non-trivial extensions over prior SOTA.
More from Research
- Anthropic scaled 1,000 Claude agents to formalize Fermat's Last Theorem — SimplyAnnisa · 2026-11-12
- NeurIPS paper gives RNNs provable state-estimation guarantees via control-theory observers — chriswolfvision · 2026-11-12
- NeurIPS paper proves when RNN+MLP can provably recover true robot state — chriswolfvision · 2026-11-12
- Curated 9-paper reading list for LLM quantization beginners, from QLoRA to BitNet — East-Muffin-6472 · 2026-11-12
- A Quick Diagnostic Guide to 4 Common ML Training Errors and Their Causes — cneuralnetwork · 2026-11-12
- DLS runs 1.5x-2.4x faster than tangermeme on A100, verified within numerical precision — anshulkundaje · 2026-11-12