MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization Paper • 2507.14683 • Published Jul 19, 2025 • 134
SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training Paper • 2506.05301 • Published Jun 5, 2025 • 59
MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search Paper • 2505.19209 • Published May 25, 2025 • 23
