Scaling Law Hypothesis for Multimodal Model

• URL: http://arxiv.org/abs/2409.06754v4
• Date: Mon, 11 Nov 2024 18:32:16 GMT
• Title: Scaling Law Hypothesis for Multimodal Model
• Abstract summary: We propose a scaling law hypothesis for multimodal models processing text, audio, images, and video within a shared token and embedding space. Our framework predicts model performance based on modality-specific compression and tokenization efficiency, extending established scaling laws from text-based decoder models to mixed-modality systems.
• Score: 8.215178209572201
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a scaling law hypothesis for multimodal models processing text, audio, images, and video within a shared token and embedding space. Our framework predicts model performance based on modality-specific compression and tokenization efficiency, extending established scaling laws from text-based decoder models to mixed-modality systems. We explore whether leveraging more training data in multiple modalities can reduce the size of the multimodal model, enabling efficient deployment on resource-constrained devices.

Related papers

• Scaling Native Multimodal Pre-Training From Scratch [15.178882099650174]
  We investigate the optimal model size and token count for training a vision-language model under a fixed computational budget.<n>We show minimal objective loss adheres to a predictable compute law, whereas compute-optimal model sizes and token counts scale as power laws.<n>Downstream evaluations reveal that native multimodal pre-training induces positive cross-modal transfer.
  arXiv  Detail & Related papers  (2026-07-24T07:13:52Z)
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
  We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
  arXiv  Detail & Related papers  (2025-10-15T16:25:18Z)
• Sample-efficient Integration of New Modalities into Large Language Models [48.81776019848246]
  Multimodal foundation models can process several modalities.<n>We introduce a method for sample-efficient modality integration into Large Language Models.<n>We find that SEMI achieves a significant boost in sample efficiency during few-shot integration of new modalities.
  arXiv  Detail & Related papers  (2025-09-04T18:41:59Z)
• Show-o2: Improved Native Unified Multimodal Models [57.34173415412808]
  Show-o2 is a native unified multimodal models that leverage autoregressive modeling and flow matching.<n>Built upon a 3D causal variational autoencoder space, unified visual representations are constructed through a dual-path of spatial (-temporal) fusion.
  arXiv  Detail & Related papers  (2025-06-18T15:39:15Z)
• Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces [10.85468238780625]
  We propose a novel framework for building multimodal diffusion models on arbitrary state spaces.<n>By introducing an innovative decoupled noise schedule for each modality, we enable both unconditional and modality-conditioned generation within a single model simultaneously.
  arXiv  Detail & Related papers  (2025-06-09T16:20:20Z)
• Unifying Multimodal Large Language Model Capabilities and Modalities via Model Merging [103.98582374569789]
  Model merging aims to combine multiple expert models into a single model, thereby reducing storage and serving costs.<n>Previous studies have primarily focused on merging visual classification models or Large Language Models (LLMs) for code and math tasks.<n>We introduce the model merging benchmark for MLLMs, which includes multiple tasks such as VQA, Geometry, Chart, OCR, and Grounding, providing both LoRA and full fine-tuning models.
  arXiv  Detail & Related papers  (2025-05-26T12:23:14Z)
• 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)
• LatentLLM: Attention-Aware Joint Tensor Compression [50.33925662486034]
  Large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources.<n>We propose a new framework to convert such LLMs/LMMs into a reduced-dimension latent structure.
  arXiv  Detail & Related papers  (2025-05-23T22:39:54Z)
• Token Communication-Driven Multimodal Large Models in Resource-Constrained Multiuser Networks [7.137830911253685]
  multimodal large models pose challenges for deploying intelligent applications at the wireless edge.<n>These constraints manifest as limited bandwidth, computational capacity, and stringent latency requirements.<n>We propose a token communication paradigm that facilitates decentralized proliferations across user devices and edge infrastructure.
  arXiv  Detail & Related papers  (2025-05-06T14:17:05Z)
• Platonic Grounding for Efficient Multimodal Language Models [22.715168904364756]
  We motivate and propose a simple modification to existing multimodal frameworks that rely on aligning pretrained models. Our work also has implications for combining pretrained models into larger systems efficiently.
  arXiv  Detail & Related papers  (2025-04-27T18:56:26Z)
• From Unimodal to Multimodal: Scaling up Projectors to Align Modalities [16.733970553781887]
  We propose a novel approach that aligns vision and language modalities using only projection layers on pretrained, frozen unimodal encoders. Our method exploits the high semantic similarity between embedding spaces of well-trained vision and language models. It involves selecting semantically similar encoders in the latent space, curating a concept-rich dataset of image-caption pairs, and training simple projectors.
  arXiv  Detail & Related papers  (2024-09-28T17:57:32Z)
• Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient Adaptation [70.22782550540714]
  Quantization-aware Scale LeArning method based on multimodal Warmup, termed QSLAW. We introduce a Quantization-aware Scale LeArning method based on multimodal Warmup, termed QSLAW.
  arXiv  Detail & Related papers  (2024-08-07T12:42:09Z)
• DiffMM: Multi-Modal Diffusion Model for Recommendation [19.43775593283657]
  We propose a novel multi-modal graph diffusion model for recommendation called DiffMM. Our framework integrates a modality-aware graph diffusion model with a cross-modal contrastive learning paradigm to improve modality-aware user representation learning.
  arXiv  Detail & Related papers  (2024-06-17T17:35:54Z)
• MM-Lego: Modular Biomedical Multimodal Models with Minimal Fine-Tuning [10.774128925670183]
  Multimodal Lego (MM-Lego) is a modular and general-purpose fusion and model merging framework. We show that MM-Lego can be used as a model merging method with end-to-end fusion models without any fine-tuning. It achieves state-of-the-art results on six benchmarked multimodal biomedical tasks.
  arXiv  Detail & Related papers  (2024-05-30T11:14:01Z)
• Multi-modal Auto-regressive Modeling via Visual Words [96.25078866446053]
  We propose the concept of visual tokens, which maps the visual features to probability distributions over Large Multi-modal Models' vocabulary. We further explore the distribution of visual features in the semantic space within LMM and the possibility of using text embeddings to represent visual information.
  arXiv  Detail & Related papers  (2024-03-12T14:58:52Z)
• Model Composition for Multimodal Large Language Models [71.5729418523411]
  We propose a new paradigm through the model composition of existing MLLMs to create a new model that retains the modal understanding capabilities of each original model. Our basic implementation, NaiveMC, demonstrates the effectiveness of this paradigm by reusing modality encoders and merging LLM parameters.
  arXiv  Detail & Related papers  (2024-02-20T06:38:10Z)
• Efficient Multimodal Diffusion Models Using Joint Data Infilling with Partially Shared U-Net [20.437172251393257]
  Partially Shared U-Net (PS-U-Net) is an efficient multimodal diffusion model that allows text and image inputs to pass through dedicated layers and skip-connections for preserving modality-specific fine-grained details. Inspired by image inpainting, we also propose a new efficient multimodal sampling method that introduces new scenarios for conditional generation while only requiring a simple joint distribution to be learned. Our empirical exploration of the MS-COCO dataset demonstrates that our method generates multimodal text and image data with higher quality compared to existing multimodal diffusion models.
  arXiv  Detail & Related papers  (2023-11-28T04:34:44Z)
• Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [62.70450216120704]
  Unsupervised pre-training has shown great success in skeleton-based action understanding. We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL. UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
  arXiv  Detail & Related papers  (2023-11-06T13:56:57Z)
• 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)
• Vertical Layering of Quantized Neural Networks for Heterogeneous Inference [57.42762335081385]
  We study a new vertical-layered representation of neural network weights for encapsulating all quantized models into a single one. We can theoretically achieve any precision network for on-demand service while only needing to train and maintain one model.
  arXiv  Detail & Related papers  (2022-12-10T15:57:38Z)
• Multimodal E-Commerce Product Classification Using Hierarchical Fusion [0.0]
  The proposed method significantly outperformed the unimodal models' performance and the reported performance of similar models on our specific task. We did experiments with multiple fusing techniques and found, that the best performing technique to combine the individual embedding of the unimodal network is based on combining concatenation and averaging the feature vectors.
  arXiv  Detail & Related papers  (2022-07-07T14:04:42Z)

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.