LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs Paper • 2501.06186 • Published Jan 10, 2025 • 67
Multi-Granularity Language-Guided Training for Multi-Object Tracking Paper • 2406.04844 • Published Jun 7, 2024 • 1
C-Drag: Chain-of-Thought Driven Motion Controller for Video Generation Paper • 2502.19868 • Published Feb 27, 2025 • 1