From Context to EDUs: Faithful and Structured Context Compression via Elementary Discourse Unit Decomposition Paper • 2512.14244 • Published Dec 16, 2025 • 2
Running on Zero Featured 31 MiniCPM-V-4 5-Demo 💬 31 Analyze images and videos with visual reasoning capabilities
JustRL: Scaling a 1.5B LLM with a Simple RL Recipe Paper • 2512.16649 • Published Dec 18, 2025 • 26
FaithLens: Detecting and Explaining Faithfulness Hallucination Paper • 2512.20182 • Published Dec 23, 2025 • 9
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe Paper • 2509.18154 • Published Sep 16, 2025 • 53