paper-with-me

홈 › Papers

Large Multi-modal Models Can Interpret Features in Large Multi-modal Models

2024-11-22 · Kaichen Zhang, Yifei Shen, Bo Li, Ziwei Liu

Recent advances in Large Multimodal Models (LMMs) lead to significant breakthroughs in both academia and industry. One question that arises is how we, as humans, can understand their internal neural representations. This paper takes an initial step towards addressing this question by presenting a versatile framework to identify and interpret the semantics within LMMs. Specifically, 1) we first apply a Sparse Autoencoder(SAE) to disentangle the representations into human understandable features. 2) We then present an automatic interpretation framework to interpreted the open-semantic features learned in SAE by the LMMs themselves. We employ this framework to analyze the LLaVA-NeXT-8B model using the LLaVA-OV-72B model, demonstrating that these features can effectively steer the model's behavior. Our results contribute to a deeper understanding of why LMMs excel in specific tasks, including EQ tests, and illuminate the nature of their mistakes along with potential strategies for their rectification. These findings offer new insights into the internal mechanisms of LMMs and suggest parallels with the cognitive processes of the human brain.

📄 PDF Abstract BibTeX arXiv:2411.14982

Code (1)

EvolvingLMMs-Lab/multimodal-sae 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Insights into a radiology-specialised multimodal large language model with sparse autoencoders

2025-07-17 · Kenza Bouzid, Shruthi Bannur, Felix Meissen, Daniel Coelho de Castro 외 arxiv

Interpretability can improve the safety, transparency and trust of AI models, which is especially important in healthcare applications where decisions often carry significant consequences. Mechanistic interpretability, p…

Multi-Faceted Multimodal Monosemanticity

2025-02-16 · Hanqi Yan, Xiangxiang Cui, Lu Yin, Paul Pu Liang 외

Humans experience the world through multiple modalities, such as, vision, language, and speech, making it natural to explore the commonality and distinctions among them. In this work, we take a data-driven approach to ad…

AttributeImage GenerationText to Image GenerationText-to-Image Generation

Interpretable multimodal sentiment analysis based on textual modality descriptions by using large-scale language models

2023-05-07 · Sixia Li, Shogo Okada

Multimodal sentiment analysis is an important area for understanding the user's internal states. Deep learning methods were effective, but the problem of poor interpretability has gradually gained attention. Previous wor…

Multimodal Sentiment AnalysisSentiment Analysis

Efficient Large-Scale Multi-Modal Classification

2018-02-06 · D. Kiela, E. Grave, A. Joulin, T. Mikolov

While the incipient internet was largely text-based, the modern digital world is becoming increasingly multi-modal. Here, we examine multi-modal classification where one modality is discrete, e.g. text, and the other is …

ClassificationComputational EfficiencyGeneral ClassificationMulti-modal Classification

Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning

2026-01-27 · Chuan Qin, Constantin Venhoff, Sonia Joseph, Fanyi Xiao 외 arxiv

Contrastive Language-Image Pre-training (CLIP) has become a cornerstone in vision-language representation learning, powering diverse downstream tasks and serving as the default vision backbone in multimodal large languag…

Representation LearningContrastive Learning