REVIEW 4 cited by
MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Multimodal large language models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, a generalist MLLM typically underperforms compared with a specialist MLLM on most VL tasks, which can be attributed to task interference. In this paper, we propose a mixture of multimodal experts (MoME) to mitigate task interference and obtain a generalist MLLM. Our MoME is composed of two key components, a mixture of vision experts (MoVE) and a mixture of language experts (MoLE). MoVE can adaptively modulate the features transformed from various vision encoders, and has a strong compatibility in transformation architecture. MoLE incorporates sparsely gated experts into LLMs to achieve painless improvements with roughly unchanged inference costs. In response to task interference, our MoME specializes in both vision and language modality to adapt to task discrepancies. Extensive experiments show that MoME significantly improves the performance of generalist MLLMs across various VL tasks. The source code is released at https://github.com/JiuTian-VL/MoME
Forward citations
Cited by 4 Pith papers
-
Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models
Fine-tuning CLIP's visual encoder to match DINOv2's kernel-based similarity structure improves its fine-grained visual perception while preserving its alignment to text.
-
Neural Inhibition Improves Dynamic Routing and Mixture of Experts
Neural inhibition gating on MoE router inputs improves a synthetic digit/squares benchmark by about four points over plain MoE, but the language-model evidence is unreliable.
-
Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills
Mirage-1 combines a hierarchical multimodal skill memory with a skill-augmented Monte Carlo tree search to outperform prior GUI agents on Android and web online benchmarks.
-
MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping
Grouping instruction-tuning datasets by redundancy, uniqueness, or synergy of text-image interaction improves vision-language model accuracy over single-task and unselective multi-task tuning.
Discussion (0). Sign in to comment.