X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages

by   Feilong Chen, et al.

Large language models (LLMs) have demonstrated remarkable language abilities. GPT-4, based on advanced LLMs, exhibits extraordinary multimodal capabilities beyond previous visual language models. We attribute this to the use of more advanced LLMs compared with previous multimodal models. Unfortunately, the model architecture and training strategies of GPT-4 are unknown. To endow LLMs with multimodal capabilities, we propose X-LLM, which converts Multi-modalities (images, speech, videos) into foreign languages using X2L interfaces and inputs them into a large Language model (ChatGLM). Specifically, X-LLM aligns multiple frozen single-modal encoders and a frozen LLM using X2L interfaces, where “X” denotes multi-modalities such as image, speech, and videos, and “L” denotes languages. X-LLM's training consists of three stages: (1) Converting Multimodal Information: The first stage trains each X2L interface to align with its respective single-modal encoder separately to convert multimodal information into languages. (2) Aligning X2L representations with the LLM: single-modal encoders are aligned with the LLM through X2L interfaces independently. (3) Integrating multiple modalities: all single-modal encoders are aligned with the LLM through X2L interfaces to integrate multimodal capabilities into the LLM. Our experiments show that X-LLM demonstrates impressive multimodel chat abilities, sometimes exhibiting the behaviors of multimodal GPT-4 on unseen images/instructions, and yields a 84.5% relative score compared with GPT-4 on a synthetic multimodal instruction-following dataset. And we also conduct quantitative tests on using LLM for ASR and multimodal ASR, hoping to promote the era of LLM-based speech recognition.


page 3

page 9

page 18

page 19

page 20


PandaGPT: One Model To Instruction-Follow Them All

We present PandaGPT, an approach to emPower large lANguage moDels with v...

ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst

Building general-purpose models that can perceive diverse real-world mod...

SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities

Multi-modal large language models are regarded as a crucial step towards...

Masked Audio Text Encoders are Effective Multi-Modal Rescorers

Masked Language Models (MLMs) have proven to be effective for second-pas...

Stone Needle: A General Multimodal Large-scale Model Framework towards Healthcare

In healthcare, multimodal data is prevalent and requires to be comprehen...

LMEye: An Interactive Perception Network for Large Language Models

Training a Large Visual Language Model (LVLM) from scratch, like GPT-4, ...

StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data

The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 ha...

Please sign up or login with your details

Forgot password? Click here to reset