Similar Items: Tool Calling is Linearly Readable and Steerable in Language Models
- Bolek: A Multimodal Language Model for Molecular Reasoning
- Crafting Reversible SFT Behaviors in Large Language Models
- Compute Where it Counts: Self Optimizing Language Models
- Safety and accuracy follow different scaling laws in clinical large language models
- Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions
- Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph