Runnable models
8 selected runnable models items across 5 daily issues. Each headline links to its source.
Start reading selected stories
- Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining (2026-10-09)
- Beyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding (2026-10-08)
- Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputs (2026-10-08)
- Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods (2026-10-07)
- Calibrated Answers About Randomized Trials From a 4-Billion-Parameter Open Model: A Registered Test and a License-Clean Release (2026-10-07)
- Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection (2026-10-02)
- Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection (2026-10-01)
- PrivMeSA: Privacy-Aware Self-Evolving Multi-Agent System for Medicine via Local-Remote LLM Collaboration (2026-10-01)