AI Papers - 2026-01-27

Today's papers: - RACA: Representation-Aware Coverage Criteria for LLM Safety Testing: https://arxiv.org/abs/2602.02280v1 - ReasonCACHE: Teaching LLMs To Reason Without Weight Updates: https://arxiv.org/abs/2602.02366v1 - Poly-attention: a general scheme for higher-order self-attention: https://arxiv.org/abs/2602.02422v1 - Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory: https://arxiv.org/abs/2602.02393v1 - World-Gymnast: Training Robots with Reinforcement Learning in a World Model: https://arxiv.org/abs/2602.02454v1 This podcast is from Colin Davis (colin-davis.com) using Claude & Elevenlabs.