Introduces Personal VCL formalization and benchmark revealing LMM context gaps, plus an Agentic Context Bank baseline that boosts personalized visual reasoning.
PEARL: Personalized streaming video understanding model
3 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
A diffusion model with dynamic modality gating and cross-modal mutual learning restores missing features in VLMs bi-directionally while preserving the original model's generalization.
VisionClaw couples continuous egocentric vision on smart glasses with speech-driven AI agents to enable hands-free real-world tasks, with lab and field studies showing faster completion and a shift toward opportunistic delegation.
citing papers explorer
-
Personal Visual Context Learning in Large Multimodal Models
Introduces Personal VCL formalization and benchmark revealing LMM context gaps, plus an Agentic Context Bank baseline that boosts personalized visual reasoning.
-
Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration
A diffusion model with dynamic modality gating and cross-modal mutual learning restores missing features in VLMs bi-directionally while preserving the original model's generalization.
-
VisionClaw: Always-On AI Agents through Smart Glasses
VisionClaw couples continuous egocentric vision on smart glasses with speech-driven AI agents to enable hands-free real-world tasks, with lab and field studies showing faster completion and a shift toward opportunistic delegation.