Model alignment using inter-modal bridges

• URL: http://arxiv.org/abs/2505.12322v1
• Date: Sun, 18 May 2025 09:30:02 GMT
• Title: Model alignment using inter-modal bridges
• Authors: Ali Gholamzadeh, Noor Sajid,
• Abstract summary: Existing methods require extensive paired training data or are constrained to specific domains.<n>We introduce a semi-supervised approach for model alignment via conditional flow matching.<n>Our method provides a data-efficient solution for inter-modal model alignment with minimal supervision.
• Score: 0.6906005491572401
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Foundation models have demonstrated remarkable performance across modalities such as language and vision. However, model reuse across distinct modalities (e.g., text and vision) remains limited due to the difficulty of aligning internal representations. Existing methods require extensive paired training data or are constrained to specific domains. We introduce a semi-supervised approach for model alignment via conditional flow matching. The conditional flow between latent spaces of different modalities (e.g., text-to-image or biological-to-artificial neuronal activity) can be learned in two settings: ($1$) solving a (balanced or unbalanced) optimal transport problem with an inter-space bridge cost, and ($2$) performing memory-efficient alignment using labelled exemplars. Despite being constrained by the original models' capacity, our method--under both settings--matches downstream task performance of end-to-end trained models on object recognition and image generation tasks across MNIST, ImageNet, and \cite{majaj2015simple} datasets, particularly when labelled training data is scarce ($<20\%$). Our method provides a data-efficient solution for inter-modal model alignment with minimal supervision.

Related papers

• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You [0.19285000127136376]
  Multimodal models have demonstrated powerful capabilities in complex tasks requiring alignment.<n>Existing models typically rely on paired samples, which are expensive or infeasible to obtain in many domains.<n>We introduce an effective regularization technique that preserves the latent space of unimodal encoders.
  arXiv  Detail & Related papers  (2025-06-20T10:32:54Z)
• Task-Specific Adaptation with Restricted Model Access [23.114703555189937]
  "Gray-box" fine-tuning approaches, where the model's architecture and weights remain hidden, allow only gradient propagation.<n>We introduce a novel yet simple and effective framework that adapts to new tasks using two lightweight learnable modules at the model's input and output.<n>We evaluate our approaches across several backbones on benchmarks such as text-image alignment, text-video alignment, and sketch-image alignment.
  arXiv  Detail & Related papers  (2025-02-02T13:29:44Z)
• Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent [74.02034188307857]
  Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data.<n>We find existing methods inevitably discard task-specific information that, while causing conflicts, is crucial for performance.<n>Our approach consistently outperforms previous methods, achieving state-of-the-art results across diverse architectures and tasks in both vision and NLP domains.
  arXiv  Detail & Related papers  (2025-01-02T12:45:21Z)
• Parameter Competition Balancing for Model Merging [13.66727853299506]
  PCB-Merging is a training-free technique that adjusts the coefficients of each parameter for effective model merging. PCB-Merging achieves substantial performance enhancements across multiple modalities, domains, model sizes, number of tasks, fine-tuning forms, and large language models.
  arXiv  Detail & Related papers  (2024-10-03T11:17:58Z)
• Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging [21.918559935122786]
  Model merging is a promising way to combine multiple task-specific models into a single multitask model without extra training. Traditional model merging methods often show significant performance gaps compared to fine-tuned models. We show that both shared and exclusive task-specific knowledge are crucial for merging performance, but directly merging exclusive knowledge hinders overall performance. We propose Twin-Merging, a method that encompasses two principal stages: (1) modularizing knowledge into shared and exclusive components, with compression to reduce redundancy and enhance efficiency; (2) dynamically merging shared and task-specific knowledge based on the input.
  arXiv  Detail & Related papers  (2024-06-17T02:31:55Z)
• Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion [86.6191592951269]
  Merging models fine-tuned from common extensively pretrained large model but specialized for different tasks has been demonstrated as a cheap and scalable strategy to construct a multitask model that performs well across diverse tasks. We propose the CONtinuous relaxation dis (Concrete) subspace learning method to identify a common lowdimensional subspace and utilize its shared information track interference problem without sacrificing performance.
  arXiv  Detail & Related papers  (2023-12-11T07:24:54Z)
• Switchable Representation Learning Framework with Self-compatibility [50.48336074436792]
  We propose a Switchable representation learning Framework with Self-Compatibility (SFSC) SFSC generates a series of compatible sub-models with different capacities through one training process. SFSC achieves state-of-the-art performance on the evaluated datasets.
  arXiv  Detail & Related papers  (2022-06-16T16:46:32Z)
• Data Summarization via Bilevel Optimization [48.89977988203108]
  A simple yet powerful approach is to operate on small subsets of data. In this work, we propose a generic coreset framework that formulates the coreset selection as a cardinality-constrained bilevel optimization problem.
  arXiv  Detail & Related papers  (2021-09-26T09:08:38Z)
• Multiscale Deep Equilibrium Models [162.15362280927476]
  We propose a new class of implicit networks, the multiscale deep equilibrium model (MDEQ) An MDEQ directly solves for and backpropagates through the equilibrium points of multiple feature resolutions simultaneously. We illustrate the effectiveness of this approach on two large-scale vision tasks: ImageNet classification and semantic segmentation on high-resolution images from the Cityscapes dataset.
  arXiv  Detail & Related papers  (2020-06-15T18:07:44Z)

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.