Visco
PulseAugur coverage of Visco — every cluster mentioning Visco across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New VisCo attack uses images to jailbreak multimodal LLMs
Researchers have developed a novel method called VisCo (Visual Contextual Attack) to jailbreak multimodal large language models (MLLMs) by injecting harmful content through image-driven context. This technique goes beyo…
-
VisCo framework uses LLMs for efficient visual token compression
Researchers have developed VisCo, a novel framework for compressing visual tokens in vision-language models (VLMs). Unlike previous methods that require extensive retraining or external modules, VisCo leverages the VLM'…
-
New methods slash OmniLLM token costs, boosting efficiency and accuracy · 9 sources tracked
Researchers have developed several novel methods for compressing token sequences in omnimodal large language models (OmniLLMs) to reduce memory and inference costs. These approaches, including OmniDelta, OmniScope, Prog…