Sprout: Building Dynamic Memory While Reasoning for Agentic Video Understanding
cs.CV
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/HKUST-LongGroup/Sprout
Terminology
Sources
- MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism
- VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning
- Kwai Keye-VL-2.0 Technical Report
- Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning
- SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing
- Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models
- MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models