MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives Paper • 2512.14699 • Published 16 days ago • 27
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance Paper • 2512.08765 • Published 23 days ago • 128
VST Collection A comprehensive framework designed to cultivate VLMs with human-like visuospatial abilities. • 5 items • Updated Nov 12, 2025 • 6
Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations Paper • 2510.23607 • Published Oct 27, 2025 • 177
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs Paper • 2510.11696 • Published Oct 13, 2025 • 176
LongLive: Real-time Interactive Long Video Generation Paper • 2509.22622 • Published Sep 26, 2025 • 184
MiCo: Multi-image Contrast for Reinforcement Visual Reasoning Paper • 2506.22434 • Published Jun 27, 2025 • 10
Sonata: Self-Supervised Learning of Reliable Point Representations Paper • 2503.16429 • Published Mar 20, 2025 • 13
view article Article DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge Feb 7, 2025 • 266
ControlNeXt: Powerful and Efficient Control for Image and Video Generation Paper • 2408.06070 • Published Aug 12, 2024 • 55