LiveVLM introduces VSB and PaR to compress and retrieve KV cache in streaming video LLMs, enabling LLaVA-OneVision to reach SOTA accuracy among training-free query-agnostic and training-based online models.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
Proposes a three-part generative anonymization pipeline using disentangled variational encoding, manifold-aware identity replacement, and distilled latent diffusion to protect face identities in MRAG while preserving non-identity attributes.
citing papers explorer
-
LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval
LiveVLM introduces VSB and PaR to compress and retrieve KV cache in streaming video LLMs, enabling LLaVA-OneVision to reach SOTA accuracy among training-free query-agnostic and training-based online models.
-
Identity-Decoupled Anonymization for Visual Evidence in Multi-modal Retrieval-Augmented Generation
Proposes a three-part generative anonymization pipeline using disentangled variational encoding, manifold-aware identity replacement, and distilled latent diffusion to protect face identities in MRAG while preserving non-identity attributes.