Long videos are encoded once into compact attachable neural weights via agentic distillation, enabling low-latency multi-turn understanding on frozen VLMs.
Visual context window extension: A new perspective for long video understanding
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
VideoChat-Flash applies hierarchical video token compression to achieve ~50x reduction in context length for long videos while maintaining near-original performance on long-context benchmarks.
InternVideo3 introduces Multimodal Contextual Reasoning and M^2LA attention to enable closed-loop evidence accumulation in long-video understanding and agentic tool use, reporting strong benchmark results.
UNIVID generates policy-aware captions for video moderation, reducing violation leakage by 42.7% and overkill rate by 37.0% while replacing over 1,000 policy-specific models with a single backbone.
citing papers explorer
-
From Content to Knowledge: Lightning Fast Long-Video Understanding with Neural Knowledge Representations
Long videos are encoded once into compact attachable neural weights via agentic distillation, enabling low-latency multi-turn understanding on frozen VLMs.
-
VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
VideoChat-Flash applies hierarchical video token compression to achieve ~50x reduction in context length for long videos while maintaining near-original performance on long-context benchmarks.
-
InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning
InternVideo3 introduces Multimodal Contextual Reasoning and M^2LA attention to enable closed-loop evidence accumulation in long-video understanding and agentic tool use, reporting strong benchmark results.
-
UNIVID: Unified Vision-Language Model for Video Moderation
UNIVID generates policy-aware captions for video moderation, reducing violation leakage by 42.7% and overkill rate by 37.0% while replacing over 1,000 policy-specific models with a single backbone.
- Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios