VideoSlate: Stateful Commit Control for Temporally Grounded Agentic Video Reasoning
cs.CV
Submitted: 2026-10-12
Updated: 2026-10-12
Comments: 23 pages, including appendix
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Qwen3-VL Technical Report
- TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability
- Training Verifiers to Solve Math Word Problems
- Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos
- VITA: Towards Open-Source Interactive Omni Multimodal LLM
- AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn
- Exploring Advanced LLM Multi-Agent Systems Based on Blackboard Architecture
- LITA: Language Instructed Temporal-Localization Assistant
- Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
- Language Repository for Long Video Understanding
- LLaVA-OneVision: Easy Visual Task Transfer
- Universal Video Temporal Grounding with Generative Multi-modal Large Language Models
- Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
- Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input
- $R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
- HawkEye: Training Video-Text LLMs for Grounding Text in Videos
- Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
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