Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping

• URL: http://arxiv.org/abs/2602.06850v1
• Date: Fri, 06 Feb 2026 16:39:10 GMT
• Title: Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping
• Authors: Chao Zhou, Tianyi Wei, Yiling Chen, Wenbo Zhou, Nenghai Yu,
• Abstract summary: Multi-condition control is bottlenecked by the conventional concatenate-and-attend'' strategy.<n>Our analysis reveals that much of this cross-modal interaction is spatially or semantically redundant.<n>We propose Position-aligned and Keyword-scoped Attention (PKA), a highly efficient framework designed to eliminate these redundancies.
• Score: 61.459927600301654
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While modern text-to-image models excel at prompt-based generation, they often lack the fine-grained control necessary for specific user requirements like spatial layouts or subject appearances. Multi-condition control addresses this, yet its integration into Diffusion Transformers (DiTs) is bottlenecked by the conventional ``concatenate-and-attend'' strategy, which suffers from quadratic computational and memory overhead as the number of conditions scales. Our analysis reveals that much of this cross-modal interaction is spatially or semantically redundant. To this end, we propose Position-aligned and Keyword-scoped Attention (PKA), a highly efficient framework designed to eliminate these redundancies. Specifically, Position-Aligned Attention (PAA) linearizes spatial control by enforcing localized patch alignment, while Keyword-Scoped Attention (KSA) prunes irrelevant subject-driven interactions via semantic-aware masking. To facilitate efficient learning, we further introduce a Conditional Sensitivity-Aware Sampling (CSAS) strategy that reweights the training objective towards critical denoising phases, drastically accelerating convergence and enhancing conditional fidelity. Empirically, PKA delivers a 10.0$\times$ inference speedup and a 5.1$\times$ VRAM saving, providing a scalable and resource-friendly solution for high-fidelity multi-conditioned generation.

Related papers

• OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RL [63.388513841293616]
  Existing forgery detection methods fail to handle the interleaved text, images, and videos prevalent in real-world misinformation.<n>To bridge this gap, this paper targets to develop a unified framework for omnibus vision-language forgery detection and grounding.<n>We propose textbf OmniVL-Guard, a balanced reinforcement learning framework for omnibus vision-language forgery detection and grounding.
  arXiv  Detail & Related papers  (2026-02-11T09:41:36Z)
• MEIC-DT: Memory-Efficient Incremental Clustering for Long-Text Coreference Resolution with Dual-Threshold Constraints [42.81232562487108]
  textbfMEIC-DT is a memory-efficient incremental clustering approach based on a lightweight Transformer.<n>We show that MEIC-DT achieves highly competitive coreference performance under stringent memory constraints.
  arXiv  Detail & Related papers  (2025-12-31T08:26:34Z)
• Training-free Context-adaptive Attention for Efficient Long Context Modeling [57.703159205740185]
  Training-free Context-adaptive Attention (TCA-Attention) is a training-free sparse attention mechanism that selectively attends to only the informative tokens for efficient long-context inference.<n>TCA-Attention achieves a 2.8$times$ speedup and reduces KV cache by 61% at 128K context length while maintaining performance comparable to full attention.
  arXiv  Detail & Related papers  (2025-12-10T01:54:57Z)
• Adaptive Learning for IRS-Assisted Wireless Networks: Securing Opportunistic Communications Against Byzantine Eavesdroppers [7.256056777973974]
  We propose a joint learning framework for Byzantine-resilient spectrum sensing and secure intelligent reflecting surface (IRS)<n>We develop an augmented-Lagrangian alternating algorithm with projected updates and provide provable sublinear convergence, with accelerated rates under mild local curvature.<n> Simulations across diverse network conditions show higher detection probability at fixed false-alarm rate under adversarial attacks, large reductions in sum MSE for honest users, strong suppression of eavesdropper signal power, and fast convergence.
  arXiv  Detail & Related papers  (2025-08-11T17:28:25Z)
• Optimal Batch-Size Control for Low-Latency Federated Learning with Device Heterogeneity [30.53961003855146]
  Federated learning (FL) has emerged as a popular approach for collaborative machine learning in sixth-generation (6G) networks.<n>The deployment of FL algorithms is expected to empower a wide range of Internet-of-Things (IoT) applications, e.g., autonomous driving, augmented reality, and healthcare.<n>We propose a novel C$2$-aware framework for optimal batch-size control that minimizes end-to-end (E2E) learning latency while ensuring convergence.
  arXiv  Detail & Related papers  (2025-07-21T13:24:38Z)
• CS-VLM: Compressed Sensing Attention for Efficient Vision-Language Representation Learning [0.0]
  We introduce the Compressed Sensing Attention Transformer (CSAT), a novel architecture that reimagines attention computation through the lens of compressed sensing.<n>CSAT exploits the inherent compressibility of both visual and textual representations especially evident in video, where temporal redundancy is high, and in language, where cross-modal grounding is often sparse.
  arXiv  Detail & Related papers  (2025-06-30T02:11:20Z)
• Is Attention Required for Transformer Inference? Explore Function-preserving Attention Replacement [13.38679135071682]
  We propose a Function-preserving Attention Replacement framework that replaces all attention blocks in pretrained transformers with learnable sequence-to-sequence modules.<n>We validate FAR on the DeiT vision transformer family and demonstrate that it matches the accuracy of the original models on ImageNet and multiple downstream tasks with reduced parameters and latency.
  arXiv  Detail & Related papers  (2025-05-24T02:23:46Z)
• Analyzing the Training Dynamics of Image Restoration Transformers: A Revisit to Layer Normalization [20.67671141789497]
  Conventional LayerNorm leads feature magnitude divergence, up to a million scale, and collapses channel-wise entropy.<n>We introduce Image Restoration Transformer Tailored Layer Normalization(i-LN), a surprisingly simple drop-in replacement for conventional LayerNorm.
  arXiv  Detail & Related papers  (2025-04-09T07:06:44Z)
• Multi-Modality Driven LoRA for Adverse Condition Depth Estimation [61.525312117638116]
  We propose Multi-Modality Driven LoRA (MMD-LoRA) for Adverse Condition Depth Estimation.<n>It consists of two core components: Prompt Driven Domain Alignment (PDDA) and Visual-Text Consistent Contrastive Learning (VTCCL)<n>It achieves state-of-the-art performance on the nuScenes and Oxford RobotCar datasets.
  arXiv  Detail & Related papers  (2024-12-28T14:23:58Z)
• Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers [58.5711048151424]
  We introduce SPARSEK Attention, a novel sparse attention mechanism designed to overcome computational and memory obstacles. Our approach integrates a scoring network and a differentiable top-k mask operator, SPARSEK, to select a constant number of KV pairs for each query. Experimental results reveal that SPARSEK Attention outperforms previous sparse attention methods.
  arXiv  Detail & Related papers  (2024-06-24T15:55:59Z)
• 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)
• Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding [53.377028000325424]
  We propose an Iterative Alignment Network (IA-Net) for temporal sentence grounding task. We pad multi-modal features with learnable parameters to alleviate the nowhere-to-attend problem of non-matched frame-word pairs. We also devise a calibration module following each attention module to refine the alignment knowledge.
  arXiv  Detail & Related papers  (2021-09-14T02:08:23Z)

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.