MM-Mem distills video input through a hierarchical memory of sensory buffer, episodic stream, and symbolic schema, optimized by a semantic information bottleneck and SIB-GRPO, to achieve SOTA on long-horizon video benchmarks.
Vgent: Graph-based retrieval- reasoning-augmented generation for long video understanding
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 3polarities
background 3representative citing papers
VisReflect generates continuous latent visual reflections to emphasize relevant visual features and guide attention in LVLMs, yielding 4.1% gains on image benchmarks and 1.8% on video benchmarks with 44% less inference time than zooming methods.
VideoStir introduces a spatio-temporal graph-based structure and intent-aware retrieval for long-video RAG, achieving competitive performance with SOTA methods via a new IR-600K dataset.
GLANCE introduces a bi-loop multi-agent framework with global-local coordination mechanisms that outperforms baselines by up to 33% on music-grounded nonlinear video editing tasks using a new MVEBench benchmark.
This is a survey that frames video MLLM research via a human-view formulation of perceptual representations, memory states, reasoning traces, and predictions, then reviews methods, datasets, benchmarks, and open problems.
PhotoCraft adds dynamically invoked working, episodic, and semantic memory to MLLM agents, reporting up to 18.5% gains in context-aware image retrieval on DISBench.
citing papers explorer
-
PhotoCraft: Agentic Reasoning with Hierarchical Self-Evolving Memory for Deep Image Search
PhotoCraft adds dynamically invoked working, episodic, and semantic memory to MLLM agents, reporting up to 18.5% gains in context-aware image retrieval on DISBench.