Designing Protein Structures from Natural Language

Researchers prove AI models can cryptographically hide arbitrary capabilities using backdoor attacks that embed encrypted neural networks only triggered by secret inputs.

Researchers introduce RSI-Anything, a framework using predictive world models for recursive self-improvement, showing substantial gains in code repair, GUI tasks, and scientific optimization.

Researchers tested language models on Wikipedia Game navigation tasks across five languages and academic datasets, finding top models achieved human-comparable performance.

Researchers prove constructive bounds on neural network expressivity using algebraic topology, establishing architectural requirements for expressing complex topological spaces.

Researchers propose a reinforcement learning framework using masked PPO for optimizing bundle management and flow control in deep-space communications networks.