PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning

• URL: http://arxiv.org/abs/2507.08064v2
• Date: Mon, 28 Jul 2025 13:36:38 GMT
• Title: PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning
• Authors: Yibo Lyu, Rui Shao, Gongwei Chen, Yijie Zhu, Weili Guan, Liqiang Nie,
• Abstract summary: We propose a Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning.<n>Our approach improves unified multimodal retrieval from both structural and learning perspectives.
• Score: 54.73049408950049
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As multimedia content expands, the demand for unified multimodal retrieval (UMR) in real-world applications increases. Recent work leverages multimodal large language models (MLLMs) to tackle this task. However, their large parameter size results in high training costs and low inference efficiency. To address this, we propose PUMA: a Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning. Our approach improves UMR from both structural and learning perspectives. (1) Structurally, we propose Layer-Pruned Self-Distillation, which prunes MLLMs by keeping only shallow layers while distilling features from dropped deep layers as teacher signals. This reduces parameters and preserves representation capability. (2) On the learning side, we introduce Modality-Adaptive Contrastive Learning Loss (MAC-Loss), which separates in-batch negatives into harder intra-modality and easier inter-modality groups based on the target modality, assigning different temperature strategies to enhance learning efficiency. Experiments show our method significantly reduces resource usage while maintaining strong performance.

Related papers

• MokA: Multimodal Low-Rank Adaptation for MLLMs [11.440424554587674]
  Multimodal low-rank Adaptation (MokA) is a multimodal-aware efficient fine-tuning strategy.<n>MokA compresses unimodal information by modality-specific parameters while explicitly enhancing cross-modal interaction.
  arXiv  Detail & Related papers  (2025-06-05T16:04:08Z)
• Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying [7.9925771591348065]
  Core contrastive learning paradigm remains largely unchanged from CLIP-style models to MLLMs.<n>In this work, we conduct a detailed analysis of the gradients of the info-NCE loss with respect to the query, positive, and negative samples.<n>We propose to explicitly amplify the gradients associated with hard negative samples, thereby encouraging the model to learn more discriminative embeddings.
  arXiv  Detail & Related papers  (2025-05-28T11:18:19Z)
• Efficient Multi-modal Long Context Learning for Training-free Adaptation [96.21248144937627]
  This paper introduces Efficient Multi-Modal Long Context Learning (EMLoC)<n>It embeds demonstration examples directly into the model input.<n>It condenses long-context multimodal inputs into compact, task-specific memory representations.
  arXiv  Detail & Related papers  (2025-05-26T10:49:44Z)
• TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models [23.916205754112774]
  Multimodal Large Language Models (MLLMs) have shown remarkable versatility in understanding diverse multimodal data and tasks.<n>We propose TAMP, a simple yet effective pruning framework tailored for MLLMs.<n>We validate our method on two state-of-the-art MLLMs: LLaVA-NeXT, designed for vision-language tasks, and VideoLLaMA2, capable of processing audio, visual, and language modalities.
  arXiv  Detail & Related papers  (2025-04-14T05:44:38Z)
• LLMs Can Evolve Continually on Modality for X-Modal Reasoning [62.2874638875554]
  Existing methods rely heavily on modal-specific pretraining and joint-modal tuning, leading to significant computational burdens when expanding to new modalities. We propose PathWeave, a flexible and scalable framework with modal-Path sWitching and ExpAnsion abilities. PathWeave performs comparably to state-of-the-art MLLMs while concurrently reducing parameter training burdens by 98.73%.
  arXiv  Detail & Related papers  (2024-10-26T13:19:57Z)
• LLaVA-KD: A Framework of Distilling Multimodal Large Language Models [72.68665884790002]
  We propose a novel framework to transfer knowledge from l-MLLMs to s-MLLMs.<n>We introduce Multimodal Distillation (MDist) to transfer teacher model's robust representations across both visual and linguistic modalities.<n>We also propose a three-stage training scheme to fully exploit the potential of the proposed distillation strategy.
  arXiv  Detail & Related papers  (2024-10-21T17:41:28Z)
• On Effects of Steering Latent Representation for Large Language Model Unlearning [4.058064008234271]
  Representation Misdirection for Unlearning (RMU) is an effective method for large language model (LLM) unlearning.<n>We show that steering forget representations in the intermediate layer reduces token confidence, causing LLMs to generate wrong or nonsense responses.<n>We propose Adaptive RMU--a simple yet effective alternative method that makes unlearning effective with most layers.
  arXiv  Detail & Related papers  (2024-08-12T15:24:50Z)
• CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models [68.64605538559312]
  In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives. Inspired by our findings, we propose a measurement to quantitatively evaluate the learning balance. In addition, we introduce an auxiliary loss regularization method to promote updating of the generation distribution of MLLMs.
  arXiv  Detail & Related papers  (2024-07-29T23:18:55Z)
• Improving Discriminative Multi-Modal Learning with Large-Scale Pre-Trained Models [51.5543321122664]
  This paper investigates how to better leverage large-scale pre-trained uni-modal models to enhance discriminative multi-modal learning. We introduce Multi-Modal Low-Rank Adaptation learning (MMLoRA)
  arXiv  Detail & Related papers  (2023-10-08T15:01:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.