CORTEXA
← Browse
arxivcs.CV2026-06-25

DnA: Denoising Attention for Visual Tasks

Ron Campos, Subhajit Maity, Xin Li, Srijan Das, Aritra Dutta

The softmax activation in multihead attention (MHA) is the de facto standard for attention-based models in visual perception tasks. However, standard softmax can produce noisy attention patterns that dilute relevant features and degrade its performance. In this paper, we propose Denoising Attention or DnA, in which, first, a positive query identifies which image features belong to the correct class, and a negative query identifies closely associated but irrelevant image features. DnA then projects these interactions into two distinct subspaces with larger principal angles, promoting subspace separation and improved discriminability. Using a ViT-B backbone, our proposed DnA achieves an absolute gain of 0.8% on ImageNet-1K compared to the baseline. We further show improvements across multiple visual understanding tasks, including video understanding with video transformers (1.8%) and video LLMs (0.5%). Our extensive empirical analyses justify the design choices involving two interacting subspaces and the denoising effect of DnA.

View free PDFSource page

Related papers

arxivcs.CV2026-07-02

LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression

Bowen Yuan, Zijian Wang, Yadan Luo, Shijie Wang, Zi Huang

Large vision-language models (LVLMs) exhibit strong reasoning ability but suffer from visual forgetting during long-horizon decoding, where attention progressively drifts away from visual evidence. Existing methods largely treat this issue as a late-stage attention decay problem…

View free PDFSource page
arxivcs.AIcs.CV2026-06-25

Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds

Jiaming Bian, Bingliang Li, Yuehao Wu, Pichao Wang, Zhi Wang, Hailan Ma, et al.

As embodied AI and world models increasingly operate in dynamic 3D environments, visual perception must move beyond passively interpreting given observations toward actively deciding what to observe. We study this problem through camera planning in dynamic 3D story worlds, where…

View free PDFSource page
arxivcs.CV2026-06-25

Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models

Shravan Venkatraman, Ritesh Thawkar, Omkar Thawakar, Rao Muhammad Anwer, Hisham Cholakkal, Salman Khan, et al.

Recently, self-evolving large multimodal models (LMMs) have received attention for improving visual reasoning in a purely unsupervised setting. However, multi-role self-play and self-consistency reward schemes in existing self-evolving LMMs optimize answer agreement without ensur…

View free PDFSource page
arxivcs.CVcs.CL2026-07-01

Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge Distillation

Jaehyun Jang, Eunseop Yoon, Hee Suk Yoon, SooHwan Eom, Mark A. Hasegawa-Johnson, Chang D. Yoo

While knowledge distillation (KD) is widely adopted for training lightweight models by leveraging supervision from larger teacher models, relying solely on output token distributions has proven insufficient for compressing Multimodal Large Language Models (MLLMs). Since output to…

View free PDFSource page
arxivcs.CV2026-07-07

AVA-VLM: Adaptive Visual Attention-Vision Language Model for In-the-Wild Construction Site Monitoring

Younggun Kim, Taeheon Kim, Youngseo Kim, Seunghee Park

Vision-Language Models (VLMs) are promising for construction-site monitoring, and recent construction-tailored VLMs have primarily adapted pretrained VLMs through direct QA-style fine-tuning from a single global image. We argue that this direct paradigm remains limited for in-the…

View free PDFSource page