Modularized Dynamic-Granularity Video LLM for Multi-Event Long Video Understanding

TL;DR - MoD-VLLM is a video LLM framework for understanding multi-event long videos, using an iterative, self-reflective loop that grounds question-relevant segments and adaptively allocates visual token budget. It matters because long-video understanding is bottlenecked by limited token budgets versus the need to capture many key events.

• Uses two coupled modules in a closed loop: a Positive-Negative Video Segments Grounding module (distinguishes relevant vs. irrelevant segments) and a Modularized Dynamic-Granularity Reflection module (a scheduler assigning fine-grained encoding to positive segments, coarse-grained to negative ones).
• Introduces a dynamic-granularity reinforcement learning strategy to jointly learn grounding policies and adaptive visual representation.
• Proposes MEventBench, a new benchmark for complex multi-event long-video reasoning.
• Reports outperforming state-of-the-art baselines across several long-video benchmarks and MEventBench (specific metrics not provided in the abstract).