VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding
cs.CV
Submitted: 2026-05-21
Updated: 2026-10-13
Project page: https://videoodyssey-project.github.io/Abstract
Terminology
Sources
- Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
- LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
- Qwen3-VL Technical Report
- CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding
- VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Video-R1: Reinforcing Video Reasoning in MLLMs
- Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
- AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?
- LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding
- WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
- Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
- LLaVA-OneVision: Easy Visual Task Transfer
- OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs
- VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
- OmniBench: Towards The Future of Universal Omni-Language Models
- Ola: Pushing the Frontiers of Omni-Modal Language Model
- OpenAI GPT-5 System Card
- LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs
- Kimi-VL Technical Report
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