V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs

First screen, captured 2 years ago.

Looks similar

Screenshot of arxiv.org: LLaVA-O1: Let Vision Language Models Reason Step-by-Step

LLaVA-O1: Let Vision Language Models Reason Step-by-Step (arxiv.org)

158 points by lnyan 1 year ago | 26 comments

Screenshot of arxiv.org: Mini-Gemini: Mining the Potential of Multi-Modality Vision Language Models

Mini-Gemini: Mining the Potential of Multi-Modality Vision Language Models (arxiv.org)

76 points by milliondreams 2 years ago | 6 comments

Screenshot of arxiv.org: Mixing Visual and Textual Code

Mixing Visual and Textual Code (arxiv.org)

68 points by doppioandante 4 months ago | 42 comments

Screenshot of arxiv.org: MM1: Methods, Analysis and Insights from Multimodal LLM Pre-training

MM1: Methods, Analysis and Insights from Multimodal LLM Pre-training (arxiv.org)

142 points by lord_sudo 2 years ago | 58 comments

Screenshot of arxiv.org: Vision Transformers Need Registers

Vision Transformers Need Registers (arxiv.org)

74 points by felineflock 1 year ago | 9 comments

Screenshot of arxiv.org: 16-Bit to 1-Bit: Visual KV Cache Quantization for Efficient Multimodal LLMs

16-Bit to 1-Bit: Visual KV Cache Quantization for Efficient Multimodal LLMs (arxiv.org)

83 points by PaulHoule 1 year ago | 1 comments