Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
Paper
•
2503.01743
•
Published
•
65
Backlog
-
-
Phi-4 Technical Report
Paper • 2412.08905 • Published • 111 -
Visual-RFT: Visual Reinforcement Fine-Tuning
Paper • 2503.01785 • Published • 59 -
When an LLM is apprehensive about its answers -- and when its uncertainty is justified
Paper • 2503.01688 • Published • 19 -
Predictive Data Selection: The Data That Predicts Is the Data That Teaches
Paper • 2503.00808 • Published • 51 -
Chain of Draft: Thinking Faster by Writing Less
Paper • 2502.18600 • Published • 44 -
Multi-Turn Code Generation Through Single-Step Rewards
Paper • 2502.20380 • Published • 29 -
Self-rewarding correction for mathematical reasoning
Paper • 2502.19613 • Published • 75 -
START: Self-taught Reasoner with Tools
Paper • 2503.04625 • Published • 77 -
MPO: Boosting LLM Agents with Meta Plan Optimization
Paper • 2503.02682 • Published • 23