SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.04334 · 2024

DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

Most large multimodal models (LMMs) are implemented by feeding visual tokens as a sequence into the first layer of a large language model (LLM). The resulting architecture is simple but significantly increases computation and memory costs, as it has to handle a large number of additional tokens in its input layer. This paper presents a new architecture DeepStack for LMMs. Considering $N$ layers in the language and vision transformer of LMMs, we stack the visual tokens into $N$ groups and feed each group to its aligned transformer layer \textit{from bottom to top}. Surprisingly, this simple method greatly enhances the power of LMMs to model interactions among visual tokens across layers but with minimal additional cost. We apply DeepStack to both language and vision transformer in LMMs, and validate the effectiveness of DeepStack LMMs with extensive empirical results. Using the same context length, our DeepStack 7B and 13B parameters surpass their counterparts by \textbf{2.7} and \textbf{2.9} on average across \textbf{9} benchmarks, respectively. Using only one-fifth of the context length, DeepStack rivals closely to the counterparts that use the full context length. These gains are particularly pronounced on high-resolution tasks, e.g., \textbf{4.2}, \textbf{11.0}, and \textbf{4.0} improvements on TextVQA, DocVQA, and InfoVQA compared to LLaVA-1.5-7B, respectively. We further apply DeepStack to vision transformer layers, which brings us a similar amount of improvements, \textbf{3.8} on average compared with LLaVA-1.5-7B.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.04334")
get_code_for_paper("2406.04334")
have("2406.04334")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.04334.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.04334.svg)](https://syntology.ai/paper/2406.04334)

Connect an agent — have() is free.