Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability
cs.CV
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/official-stockfish/Stockfish
Project page: https://videoarena-bench.github.io
Terminology
Sources
- Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
- LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
- Are We on the Right Way for Evaluating Large Vision-Language Models?
- MIRAGE: The Illusion of Visual Understanding
- GameVerse: Can Vision-Language Models Learn from Video-based Reflection?
- GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
- Game-MUG: Multimodal Oriented Game Situation Understanding and Commentary Generation Dataset
- Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse
- GPT-4o System Card
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Qwen3-VL Technical Report
- MLVU: Benchmarking Multi-task Long Video Understanding
- Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
- Accelerating Self-Play Learning in Go
- DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning
- ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis
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