TALK: One-Shot Batch Design for Protein Variant Effect Prediction
cs.CE, cs.LG
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/joehuang618/TALK
Project page: https://www.proteingym.org
Terminology
Sources
- Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
- Near-optimal Nonmyopic Value of Information in Graphical Models
- Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
- Few-shot Protein Fitness Prediction via In-context Learning and Test-time Training
Related papers
- Constrained Sensing and Reliable State Estimation with Shallow Recurrent Decoders on a TRIGA Mark II Reactor
- DREChanNet: Patient-Relative iEEG Model for Channel-Wise Epileptogenic Zone Localization
- A matrix-free, differentiable PyTorch solver for phase-field fracture: Formulation, benchmarks, and inverse analysis
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business
- Colour me shocked: Exact Molecular Hessians from local MLIPs in O(N) time using sparse differentiation!
- In-context learning as a retraining-free paradigm for constitutive modeling