MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm Paper β’ 2512.02895 β’ Published Dec 2, 2025 β’ 5
Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning Paper β’ 2508.16949 β’ Published Aug 23, 2025 β’ 24
Running 1.49k Chat-with-GPT4 π 1.49k Chat with GPT-4 using system instructions and streaming responses
Running Featured 997 ControlNet π 997 Transform images using ControlNet with various control modes