Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMs

arXiv:2608.05592 · cs.CV · Submitted 2026-08-06 · Read on arXiv

cs.CV

Submitted: 2026-08-06

Updated: 2026-09-26

Terminology

• Verification — 48× in this paper · explained in 2 episodes
• Verifier — 24× in this paper · explained in 2 episodes
• Accuracy — 21× in this paper · explained in 1 episode
• Pruning — 18× in this paper · explained in 4 episodes
• Benchmark — 13× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Clustering — 5× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Generative AI — 3× in this paper · explained in 2 episodes
• Training-Free Framework — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Generalization — 2× in this paper · explained in 13 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• PaLM 2 Technical Report
• Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames
• MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens
• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• LongVILA: Scaling Long-Context Visual Language Models for Long Videos
• VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
• GPT-4o System Card
• LLaVA-OneVision: Easy Visual Task Transfer
• VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning
• Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
• Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding
• Qwen2 Technical Report
• mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality
• Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning
• Long Context Transfer from Language to Vision
• LLaVA-Video: Video Instruction Tuning With Synthetic Data
• FOCUS: Efficient Keyframe Selection for Long Video Understanding
• VideoLucy: Deep Memory Backtracking for Long 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