EventLens: Event-Structure Reinforcement Learning for Video Understanding
cs.CV, cs.AI, cs.MM
Submitted: 2026-10-12
Updated: 2026-10-12
Comments: 22 pages, 8 figures, 13 tables. Project page: https://lostgreen.github.io/EventLens/
Project page: https://lostgreen.github.io/EventLens
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
- Towards Event-oriented Long Video Understanding
- Breaking Down Video LLM Benchmarks: Knowledge, Spatial Perception, or True Temporal Understanding?
- ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking
- Distilling the Knowledge in a Neural Network
- TempCore: Are Video QA Benchmarks Temporally Grounded?
- R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement Learning
- InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling
- VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
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