This paper proposes an anatomically aware frequency-and-structure-guided vision transformer (AA-ViT) for accurate and non-invasive contrast enhanced MRI (CEMRI) synthesis using pre-contrast MRI modali…

PASTA proposes a novel, twofold stealthy backdoor attack that enables high-success-rate backdoor activation across arbitrary patches in Vision Transformers by leveraging the Trigger Radiating Effect (…

The paper proposes an SE ViT-BiLSTM hybrid model for enhanced intrusion detection in IIoT and IoMT environments, achieving superior performance on real-world datasets, especially after data balancing.

This paper presents FlexViT, a reconfigurable FPGA accelerator for efficient Vision Transformer (ViT) inference on edge devices, achieving up to 2.74x speedup on accelerator-executed layers.

Zamba2-VL is a new suite of vision-language models built on the Zamba2 hybrid architecture, achieving state-of-the-art performance and significantly improved inference efficiency compared to leading T…

This paper proposes DPNeXt, a streamlined multi-scale feature fusion decoder for Multi-Task Learning (MTL) in robotics perception systems, improving frozen VFM utilization and mitigating negative indu…

This paper proposes Twins, a unified continuous token space for multimodal models using ViT and VAE features, and addresses optimization imbalance with a focal regression objective.

The paper introduces Text-Conditioned Layer-wise Internal Alignment (TC-LIA), a model-agnostic method that significantly improves the detection of 'mirage'—when Vision-Language Models confidently answ…

This paper introduces a method for generating diagnostic saliency maps for vision-language models using transformer models, revealing how the models allocate focus across visual elements during answer…

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quali…

This paper formalizes the binding problem using information theory and develops a probing method to measure binding information in deep learning representations, demonstrating that binding is crucial…

The paper proposes MMGuard, a proactive defense mechanism that injects unlearnable, human-imperceptible perturbations into multimodal data to prevent unauthorized fine-tuning of Large Vision-Language…

This paper investigates the application of Parameter-Efficient Fine-Tuning (PEFT) methods, specifically adapters and LoRA, to large pretrained models for instance segmentation, demonstrating that thes…

This study systematically evaluates Vision Mamba models for detecting AI-generated images, finding that while they show promise, their current strengths and limitations must be understood relative to…

This paper proposes using color statistics, specifically through novel color transformations, to detect AI-generated synthetic images by exploiting the color-imitation weaknesses of current generative…

The paper presents SenseNova-Vision, a unified multimodal model for computer vision tasks using natural language instructions and optional visual prompts, trained primarily on a new corpus and requiri…

RayDer introduces a unified, feed-forward transformer that simplifies self-supervised novel view synthesis (NVS) by consolidating camera estimation, scene reconstruction, and rendering into a single,…

The paper proposes VRPO, a reinforcement learning-based optimization strategy that replaces static alignment losses in diffusion models, significantly improving both convergence and image fidelity.

The paper introduces Pocket-Dentist, an efficiency-aware benchmark and model that demonstrates that compact, smaller Vision-Language Models (VLMs) can outperform larger models in accuracy while drasti…