The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Paper • 2604.11297 • Published Apr 13 • 144
daVinci-Dev: Agent-native Mid-training for Software Engineering Paper • 2601.18418 • Published Jan 26 • 126
MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation Paper • 2601.06874 • Published Jan 11 • 13
LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation Paper • 2512.23576 • Published Dec 29, 2025 • 66
BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping Paper • 2510.18927 • Published Oct 21, 2025 • 85
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling Paper • 2506.20512 • Published Jun 25, 2025 • 49
Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale Paper • 2409.17115 • Published Sep 25, 2024 • 64
