Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox
• 22
AI & ML interests
None defined yet.
Recent Activity
Papers
ThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning
Breaking Diffusion: Parallel Reasoning with Draft Refinement
Articles
Article
Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox
microsoft
• • 22 Article
The Agent Said It Was Done. The Database Disagreed.
microsoft
• • 91
ositanachi
published an article 4 months ago
Article
Hugging Face Models on Foundry Managed Compute
microsoft
• • 21
Article
Differential Transformer V2
microsoft
• • 53
Article
Introducing OptiMind, a research model designed for optimization
microsoft
• • 35