CineMME: From Dialogue Grounding to Narrative Reasoning in Multimodal Video Understanding
cs.CV
Submitted: 2026-11-11
Updated: 2026-11-11
Project page: https://cinemme.github.io
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- WhisperX: Time-Accurate Speech Transcription of Long-Form Audio
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
- Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
- OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios
- AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?
- SVAG-Bench: A Large-Scale Benchmark for Multi-Instance Spatio-temporal Video Action Grounding
- WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
- Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
- A Benchmark for Omni-Modal Reasoning in Long Videos
- OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs
- Xiaomi MiMo-VL-Miloco Technical Report
- MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
- OmniBench: Towards The Future of Universal Omni-Language Models
- Ministral 3
- EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding
- Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
- Qwen2.5 Technical Report
- CinePile: A Long Video Question Answering Dataset and Benchmark
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs