SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.07533 · 2023

VILA: On Pre-training for Visual Language Models

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. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Visual language models (VLMs) rapidly progressed with the recent success of large language models. There have been growing efforts on visual instruction tuning to extend the LLM with visual inputs, but lacks an in-depth study of the visual language pre-training process, where the model learns to perform joint modeling on both modalities. In this work, we examine the design options for VLM pre-training by augmenting LLM towards VLM through step-by-step controllable comparisons. We introduce three main findings: (1) freezing LLMs during pre-training can achieve decent zero-shot performance, but lack in-context learning capability, which requires unfreezing the LLM; (2) interleaved pre-training data is beneficial whereas image-text pairs alone are not optimal; (3) re-blending text-only instruction data to image-text data during instruction fine-tuning not only remedies the degradation of text-only tasks, but also boosts VLM task accuracy. With an enhanced pre-training recipe we build VILA, a Visual Language model family that consistently outperforms the state-of-the-art models, e.g., LLaVA-1.5, across main benchmarks without bells and whistles. Multi-modal pre-training also helps unveil appealing properties of VILA, including multi-image reasoning, enhanced in-context learning, and better world knowledge.

For agents

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

get_harvested_code_for_paper("2312.07533")
get_code_for_paper("2312.07533")
have("2312.07533")

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

curl https://syntology.ai/api/ran/2312.07533.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.07533.svg)](https://syntology.ai/paper/2312.07533)

Connect an agent — have() is free.