paper-with-me

홈 › Papers

MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts

2024-07-31 · Xi Victoria Lin, Akshat Shrivastava, Liang Luo, Srinivasan Iyer, Mike Lewis, Gargi Ghosh, Luke Zettlemoyer, Armen Aghajanyan

We introduce MoMa, a novel modality-aware mixture-of-experts (MoE) architecture designed for pre-training mixed-modal, early-fusion language models. MoMa processes images and text in arbitrary sequences by dividing expert modules into modality-specific groups. These groups exclusively process designated tokens while employing learned routing within each group to maintain semantically informed adaptivity. Our empirical results reveal substantial pre-training efficiency gains through this modality-specific parameter allocation. Under a 1-trillion-token training budget, the MoMa 1.4B model, featuring 4 text experts and 4 image experts, achieves impressive FLOPs savings: 3.7x overall, with 2.6x for text and 5.2x for image processing compared to a compute-equivalent dense baseline, measured by pre-training loss. This outperforms the standard expert-choice MoE with 8 mixed-modal experts, which achieves 3x overall FLOPs savings (3x for text, 2.8x for image). Combining MoMa with mixture-of-depths (MoD) further improves pre-training FLOPs savings to 4.2x overall (text: 3.4x, image: 5.3x), although this combination hurts performance in causal inference due to increased sensitivity to router accuracy. These results demonstrate MoMa's potential to significantly advance the efficiency of mixed-modal, early-fusion language model pre-training, paving the way for more resource-efficient and capable multimodal AI systems.

📄 PDF Abstract BibTeX arXiv:2407.21770

Code (0)

등록된 구현이 없습니다.

Tasks

Causal InferenceLanguage ModellingMixture-of-Experts

Methods 이 논문이 사용한 방법론

Causal inference Causal inference is the process of drawing a conclusion about a causal connection based on the conditions of the occurrence of an effect. The main difference between causal…
MoE 설명 없음

Similar Papers 제목 키워드 기반

MoMA: A Mixture-of-Multimodal-Agents Architecture for Enhancing Clinical Prediction Modelling

2025-08-07 · Jifan Gao, Mahmudur Rahman, John Caskey, Madeline Oguss 외 arxiv

Multimodal electronic health record (EHR) data provide richer, complementary insights into patient health compared to single-modality data. However, effectively integrating diverse data modalities for clinical prediction…

AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality Masking

2024-09-26 · Shiqi Sun, Yantao Lu, Ning Liu, Bo Jiang 외

Camera-LiDAR fusion models significantly enhance perception performance in autonomous driving. The fusion mechanism leverages the strengths of each modality while minimizing their weaknesses. Moreover, in practice, camer…

Autonomous Driving

Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories

2023-02-07 · Suyu Ge, Chenyan Xiong, Corby Rosset, Arnold Overwijk 외

In this paper we improve the zero-shot generalization ability of language models via Mixture-Of-Memory Augmentation (MoMA), a mechanism that retrieves augmentation documents from multiple information corpora ("external m…

RetrievalZero-shot Generalization

Scaling Laws for Native Multimodal Models Scaling Laws for Native Multimodal Models

2025-04-10 · Mustafa Shukor, Enrico Fini, Victor Guilherme Turrisi da Costa, Matthieu Cord 외

Building general-purpose models that can effectively perceive the world through multimodal signals has been a long-standing goal. Current approaches involve integrating separately pre-trained components, such as connecti…

Mixture-of-Experts

ReMoMask: Retrieval-Augmented Masked Motion Generation

2025-08-04 · Zhengdao Li, Siheng Wang, Zeyu Zhang, Hao Tang arxiv

Text-to-Motion (T2M) generation aims to synthesize realistic and semantically aligned human motion sequences from natural language descriptions. However, current approaches face dual challenges: Generative models (e.g., …

Cross-Modal Retrieval