Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulation

• URL: http://arxiv.org/abs/2607.02968v1
• Date: Fri, 03 Jul 2026 05:21:46 GMT
• Title: Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulation
• Abstract summary: Massive Activations (MAs) have been widely observed in Transformer-based models, yet their structure and functional roles in Diffusion Transformers (DiTs) remain insufficiently understood.<n>We introduce Eliciting Massive Activation (EMA), a training-free framework that leverages Massive Activations as a unified modulation signal.
• Score: 32.88834222160239
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Massive Activations (MAs) have been widely observed in Transformer-based models, yet their structure and functional roles in Diffusion Transformers (DiTs) remain insufficiently understood. In this work, we systematically analyze MAs in representative DiTs and find that they are spatially distributed across image tokens while concentrated in a small set of fixed feature dimensions. We further show that these dimensions are closely aligned with AdaLN residual scaling factors and are primarily modulated by the denoising timestep rather than text conditions. This structure leads to two task-dependent effects: for generation, MAs are critical for fine-grained detail synthesis while having limited influence on global semantics; for understanding, their shared high-magnitude directions make raw DiT features overly similar across spatial tokens and weaken dense feature discrimination. Based on these findings, we introduce Eliciting Massive Activation (EMA), a training-free framework that leverages Massive Activations (MAs) as a unified modulation signal to improve both generative and representational capabilities of DiTs. For generation, EMA proposes MA-driven Detail G}uidance (DG), which suppresses MA dimensions to construct a detail-deficient counterfactual prediction and guides sampling toward finer visual details. DG further supports efficient partial-forward inference, integration with classifier-free guidance, and token-level Local DG for refining selected image regions. For understanding, EMA introduces MA-modulated REPresentation extraction (MREP), which uses pretrained AdaLN channel-wise modulation to reduce MA directional dominance and concatenates spatially normalized MA maps to preserve useful spatial structure. Extensive experiments demonstrate that EMA consistently improves both the generation quality and representation capability of DiTs.

Related papers

• MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion [33.838877596911445]
  Multimodal Knowledge Graph Completion (MKGC) requires inferring missing entities from structural, textual, and visual cues.<n>Existing diffusion-based MKGC methods usually denoise directly on raw multimodal features.<n>We propose MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts.
  arXiv  Detail & Related papers  (2026-07-17T03:39:43Z)
• SIGMA: Bridging Structural and Distributional Gaps for Vision Foundation Model Adaptation [5.145184780729273]
  Vision Foundation Models (VFMs) have demonstrated impressive representational capabilities.<n>textbfScale-textbfIntegrated textbfGlobal textbfModulation textbfAdapter (textbfAdapter)
  arXiv  Detail & Related papers  (2026-05-27T03:17:46Z)
• A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models [56.03096341469333]
  We investigate the origins of massive activations in large language models (LLMs)<n>We identify a specific layer named the textbfMassive Emergence Layer (ME Layer), that is consistently observed across model families.<n>We show that, within the ME Layer both the RMSNorm and the FFN parameters jointly contribute to the emergence of massive activations.<n>Motivated by this limitation, we propose a simple and effective method to reduce the rigidity of the massive activation token.
  arXiv  Detail & Related papers  (2026-05-08T21:37:27Z)
• Beyond Weight Adaptation: Feature-Space Domain Injection for Cross-Modal Ship Re-Identification [3.6907522136316975]
  Cross-Modality Ship Re-Identification (CMS Re-ID) is critical for achieving all-day and all-weather maritime target tracking.<n>We explore the potential of Vision Foundation Models (VFMs) in bridging modality gaps.<n>We propose a novel PEFT strategy termed Domain Representation Injection (DRI)
  arXiv  Detail & Related papers  (2025-12-24T02:30:23Z)
• Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers [33.765941209545986]
  Diffusion Transformers (DiTs) have emerged as a powerful backbone for visual generation.<n>Recent observations reveal emphMassive Activations (MAs) in their internal feature maps.<n>We propose textbfDetail textbfGuidance (textbfDG) to explicitly enhance local detail fidelity for DiTs.
  arXiv  Detail & Related papers  (2025-10-13T15:39:13Z)
• Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing [92.61216319417208]
  We propose a novel frequency domain-based diffusion model, named ours, for fully exploiting the beneficial knowledge in unpaired clear data.<n>Inspired by the strong generative ability shown by Diffusion Models (DMs), we tackle the dehazing task from the perspective of frequency domain reconstruction.
  arXiv  Detail & Related papers  (2025-07-02T01:22:46Z)
• Weight Spectra Induced Efficient Model Adaptation [54.8615621415845]
  Fine-tuning large-scale foundation models incurs prohibitive computational costs.<n>We show that fine-tuning predominantly amplifies the top singular values while leaving the remainder largely intact.<n>We propose a novel method that leverages learnable rescaling of top singular directions.
  arXiv  Detail & Related papers  (2025-05-29T05:03:29Z)
• FreSca: Scaling in Frequency Space Enhances Diffusion Models [55.75504192166779]
  This paper explores frequency-based control within latent diffusion models.<n>We introduce FreSca, a novel framework that decomposes noise difference into low- and high-frequency components.<n>FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control.
  arXiv  Detail & Related papers  (2025-04-02T22:03:11Z)
• Modality Prompts for Arbitrary Modality Salient Object Detection [57.610000247519196]
  This paper delves into the task of arbitrary modality salient object detection (AM SOD) It aims to detect salient objects from arbitrary modalities, eg RGB images, RGB-D images, and RGB-D-T images. A novel modality-adaptive Transformer (MAT) will be proposed to investigate two fundamental challenges of AM SOD.
  arXiv  Detail & Related papers  (2024-05-06T11:02:02Z)
• Calibrating Undisciplined Over-Smoothing in Transformer for Weakly Supervised Semantic Segmentation [51.14107156747967]
  Weakly supervised semantic segmentation (WSSS) has attracted considerable attention because it requires fewer annotations than fully supervised approaches.<n>We propose an Adaptive Re-Activation Mechanism (AReAM) to control deep-level attention to undisciplined over-smoothing.<n>AReAM substantially improves segmentation performance compared with existing WSSS methods, reducing noise while sharpening focus on relevant semantic regions.
  arXiv  Detail & Related papers  (2023-05-04T19:11:33Z)

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.