FractAL introduces soft acquisition-strategy selection for batch-mode active learning
anshulkundaje · x · 2026-10-08
- Rushil Gupta, with Romain Lopez from Anshul Kundaje's group, released FractAL, a soft-strategy selection method for batch-mode active learning.
- Practitioners usually must pick an acquisition strategy before any labeling, but the best one changes with dataset, model, and task; FractAL removes the need to commit to just one.
- The work targets AI-guided experimental design in real wet labs, where setting up the predictive problem and designing an effective strategy is still 'shooting in the dark'.
- A preprint accompanies the release.
More from Research
- Building a computer out of fluids: simulating OpenAI's Navier–Stokes Turing machine — kfountou · 2026-10-08
- D-OPCD distills agent harness gains into diffusion weights, lifting T2I scores 60.52 to 65.09 — Wenxuan Wang · 2026-10-08
- QuadTok: quadtree visual tokenizer saves 10% tokens, hits 2.08 gFID on ImageNet 256 — Yucheng Mao · 2026-10-08
- PhysEvo: recursive self-improvement around a frozen model hits 62% on RoboDojo, 84% on real robot — Wenqing Tian · 2026-10-08
- RL perspective explains on-policy distillation collapse via implicit-reward hacking — Han Cui · 2026-10-08
- SketchSSM cuts linear-attention state traffic 10x, speeds decode up to 7.3x on B300 — sehoonkim418 · 2026-10-08