1436 papers
This paper introduces IAG, the first input-aware backdoor attack on vision-language models for visual grounding, which utilizes a text-conditioned UNet to dynamically generate imperceptible, target-specific triggers that achieve high attack success rates across various models and datasets while maintaining stealth and robustness against defenses.
UltraUPConvNet is a computationally efficient, multi-task framework based on UPerNet and ConvNeXt that simultaneously performs ultrasound tissue segmentation and disease prediction, achieving state-of-the-art performance on a large-scale dataset with reduced computational overhead.
This paper introduces MICA, a privacy-preserving, speech-interactive multi-agent system that leverages Adaptive Step Fusion and a safety-audited coordination topology to deliver robust, real-time industrial assistance for assembly and maintenance tasks on resource-constrained hardware.
This paper introduces the ORIC framework and benchmark to evaluate and improve Large Vision-Language Models' object recognition capabilities under contextual incongruity, demonstrating that such scenarios significantly degrade performance and that targeted Visual Reinforcement Fine-Tuning can effectively mitigate these failures.
This paper introduces "Jr. AI Scientist," an autonomous system that mimics a novice researcher's workflow to generate novel, scientifically valuable papers building on real academic works, while simultaneously evaluating its performance through rigorous automated and human assessments to identify both its capabilities and the significant risks and limitations of current AI-driven scientific exploration.
This paper introduces the Angular Gradient Sign Method, a novel adversarial attack for hyperbolic networks that leverages the geometric decomposition of gradients to apply perturbations solely along angular (semantic) directions, thereby achieving higher fooling rates and revealing unique vulnerabilities in hierarchical embeddings compared to conventional Euclidean-based methods.
The paper proposes the Radiative-Structured Neural Operator (RSNO), a novel deep learning framework that reconstructs hyperspectral images from multispectral observations by learning continuous spectral mappings under radiative priors and employing angular-consistent projection to ensure physical consistency and eliminate color distortion.
This paper proposes "Shortcut Invariance," a targeted Jacobian regularization method that improves out-of-distribution generalization by injecting anisotropic noise into a disentangled latent space to flatten decision boundaries along shortcut-aligned axes, thereby eliminating the need for explicit shortcut labels or conflicting training samples.
This study introduces ForamDeepSlice, a high-accuracy deep learning framework that combines an ensemble of ConvNeXt-Large and EfficientNetV2-Small models with a rigorous specimen-level split dataset to achieve 95.64% accuracy in classifying foraminifera species from 2D micro-CT slices, while also providing an interactive dashboard for real-time identification and 3D matching.
This paper presents a two-step generative data augmentation framework combining rule-based mask warping and unpaired image-to-image translation to address the scarcity of masked face datasets, achieving performance improvements with minimal training data while explicitly noting its origins as a resource-constrained coursework project that lacked downstream quantitative evaluation.
The paper introduces SALVE, a unified framework that combines sparse autoencoders and feature-level saliency mapping to discover, validate, and precisely edit neural network weights, enabling interpretable and robust control over both convolutional and transformer-based models.
Re-Depth Anything is a test-time self-supervised framework that enhances monocular depth estimation by fusing foundation models with large-scale 2D diffusion priors to perform label-free refinement via generative re-lighting and Score Distillation Sampling, achieving state-of-the-art results without direct depth tensor optimization.
This paper introduces VOIC, a novel dual-decoder framework for monocular 3D Semantic Scene Completion that employs a Visible Region Label Extraction strategy to decouple visible-region perception from occluded-region reasoning, thereby mitigating feature dilution and achieving state-of-the-art performance on standard benchmarks.
This paper proposes "Efficient Vision Mamba," a computationally lightweight deep learning framework that combines multi-head selective state-space models with hybrid scanning to achieve state-of-the-art MRI super-resolution performance while drastically reducing parameters and computation compared to existing methods.
This paper presents a lightweight, two-stage multitask vision-language framework that integrates a Swin Transformer encoder with sequence-to-sequence decoders to achieve state-of-the-art, explainable visual question answering for crop disease identification with near-perfect classification accuracy and strong generalization capabilities.
MeanCache is a training-free framework that accelerates Flow Matching inference by replacing instantaneous velocity caching with an average-velocity approach using cached Jacobian-vector products and a trajectory-stability scheduling strategy, achieving significant speedups (up to 4.56X) while maintaining high generation quality across models like FLUX.1 and HunyuanVideo.
This paper demonstrates that neural networks learning equivariant operators in a latent space can effectively generalize to out-of-distribution symmetric transformations on simple datasets like rotated MNIST, while also highlighting the significant challenges involved in scaling this approach to more complex data.
This paper introduces Infinite Self-Attention (InfSA) and its linear-time variant, Linear-InfSA, a spectral reformulation of self-attention as a diffusion process on token graphs that achieves state-of-the-art ImageNet accuracy and enables efficient, memory-free inference at ultra-high resolutions (up to 9216×9216) by replacing the quadratic softmax cost with a Neumann series approximation.
This paper presents a computationally efficient, detection-gated deep learning pipeline that achieves state-of-the-art robustness and cross-dataset generalization in glottal segmentation from high-speed videoendoscopy, enabling reliable extraction of clinical biomarkers for distinguishing healthy from pathological vocal function.
This paper introduces GramCol and a motion-feature selection algorithm to generate Interpretable Motion-Attentive Maps (IMAPs) that effectively localize both motion and non-motion concepts in Video Diffusion Transformers without requiring gradient calculations or parameter updates.