Diffusion-CAM: Faithful Visual Explanations for dMLLMs

• URL: http://arxiv.org/abs/2604.11005v1
• Date: Mon, 13 Apr 2026 05:14:18 GMT
• Title: Diffusion-CAM: Faithful Visual Explanations for dMLLMs
• Abstract summary: Diffusion-CAM is the first interpretability method specifically tailored for dMLLMs.<n>We derive raw activation maps by differentiably probing intermediate representations in the backbone.<n>Our experiments demonstrate that Diffusion-CAM significantly outperforms SoTA methods in both localization accuracy and visual fidelity.
• Score: 8.78213424930081
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional autoregressive models that produce sequential activations, diffusion-based architectures generate tokens via parallel denoising, resulting in smooth, distributed activation patterns across the entire sequence. Consequently, existing Class Activation Mapping (CAM) methods, which are tailored for local, sequential dependencies, are ill-suited for interpreting these non-autoregressive behaviors. To bridge this gap, we propose Diffusion-CAM, the first interpretability method specifically tailored for dMLLMs. We derive raw activation maps by differentiably probing intermediate representations in the transformer backbone, accordingly capturing both latent features and their class-specific gradients. To address the inherent stochasticity of these raw signals, we incorporate four key modules to resolve spatial ambiguity and mitigate intra-image confounders and redundant token correlations. Extensive experiments demonstrate that Diffusion-CAM significantly outperforms SoTA methods in both localization accuracy and visual fidelity, establishing a new standard for understanding the parallel generation process of diffusion multimodal systems.

Related papers

• MLLM-Guided Semantic Correction for Text-to-Video Generation [66.7723669725808]
  We introduce a training-free, interpretable mid-generation correction framework that integrates multimodal large language model feedback.<n>We propose two key modules: a Semantic Assessment Supervisor that generates intermediate preview frames for semantic evaluations and deviation diagnostics, and a Semantic Modification Assistant that corrects semantic drift during inference.<n>Our method improves semantic alignment, visual fidelity, and temporal consistency without modifying model parameters.
  arXiv  Detail & Related papers  (2026-08-17T12:54:10Z)
• Towards Generalized Image Manipulation Localization via Score-based Model [38.03898206912958]
  We propose DiffIML, a novel framework that introduces score-based generative modeling to IML.<n>Under this formulation, diffusion models serve as an effective numerical solver for the learned score function.<n>Experiments on eight non-generative and three generative benchmarks demonstrate that DiffIML consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-16T08:39:54Z)
• Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion [66.78268790956493]
  We introduce Omni-Diffusion, the first any-to-any multimodal language model built entirely on mask-based discrete diffusion models.<n>Our method outperforms or performs on par with existing multimodal systems that process two or more modalities.
  arXiv  Detail & Related papers  (2026-03-06T18:59:57Z)
• Bridging the Discrete-Continuous Gap: Unified Multimodal Generation via Coupled Manifold Discrete Absorbing Diffusion [60.186310080523135]
  Bifurcation of generative modeling into autoregressive approaches for discrete data (text) and diffusion approaches for continuous data (images) hinders development of truly unified multimodal systems.<n>We propose textbfCoM-DAD, a novel probabilistic framework that reformulates multimodal generation as a hierarchical dual-process.<n>Our method demonstrates superior stability over standard masked modeling, establishing a new paradigm for scalable, unified text-image generation.
  arXiv  Detail & Related papers  (2026-01-07T16:21:19Z)
• Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL [19.094835780362775]
  Few-Shot Class-Incremental Learning (FSCIL) challenges models to sequentially learn new classes from minimal examples.<n>Current FSCIL methods often struggle with generalization due to their reliance on limited datasets.<n>This paper introduces Diffusion-Classifier Synergy (DCS), a novel framework that establishes a mutual boosting loop between diffusion model and FSCIL classifier.
  arXiv  Detail & Related papers  (2025-10-04T01:48:52Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion [52.315729095824906]
  MLLM Semantic-Corrected Ping-Pong-Ahead Diffusion (PPAD) is a novel framework that introduces a Multimodal Large Language Model (MLLM) as a semantic observer during inference.<n>It performs real-time analysis on intermediate generations, identifies latent semantic inconsistencies, and translates feedback into controllable signals that actively guide the remaining denoising steps.<n>Extensive experiments demonstrate PPAD's significant improvements.
  arXiv  Detail & Related papers  (2025-05-26T14:42:35Z)
• Unifying Autoregressive and Diffusion-Based Sequence Generation [3.1853022872760186]
  We present significant extensions to diffusion-based sequence generation models, blurring the line with autoregressive language models.<n>We introduce hyperschedules, which assign distinct noise schedules to individual token positions.<n>Second, we propose two hybrid token-wise noising processes that interpolate between absorbing and uniform processes, enabling the model to fix past mistakes.
  arXiv  Detail & Related papers  (2025-04-08T20:32:10Z)
• Diffusion Features to Bridge Domain Gap for Semantic Segmentation [2.8616666231199424]
  This paper investigates the approach that leverages the sampling and fusion techniques to harness the features of diffusion models efficiently. By leveraging the strength of text-to-image generation capability, we introduce a new training framework designed to implicitly learn posterior knowledge from it.
  arXiv  Detail & Related papers  (2024-06-02T15:33:46Z)
• Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning [52.72369034247396]
  We propose the diffusion glancing transformer, which employs a modality diffusion process and residual glancing sampling. DIFFGLAT achieves better generation accuracy while maintaining fast decoding speed compared with both autoregressive and non-autoregressive models.
  arXiv  Detail & Related papers  (2022-12-20T13:36:25Z)

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.