4146 papers
This paper introduces Implicit U-KAN 2.0, a novel medical image segmentation model that combines second-order neural ordinary differential equations (SONO) with MultiKAN layers in a two-phase encoder-decoder architecture to achieve superior performance, enhanced interpretability, and dimension-independent approximation capabilities while reducing computational costs.
This paper presents a large-scale analysis of 326 image classification models across nine quality dimensions beyond accuracy, revealing that vision-language models, self-supervised initialization, and dataset size significantly influence model behavior, and introduces the QUBA score to holistically rank and recommend models based on specific user needs.
This paper introduces DeCon, a self-supervised learning framework that jointly pre-trains encoders and decoders using a weighted contrastive loss, achieving state-of-the-art performance across various dense prediction tasks and datasets by significantly enhancing representation quality compared to conventional encoder-only approaches.
This paper presents a unified physics-based framework that leverages Vision-Language Models and a novel VLM-Guided Relative Movement Dynamics (RMD) representation to automatically generate reward functions for synthesizing scalable, long-horizon human-object interactions across diverse object types without manual reward engineering.
This paper introduces \data, a dataset of fine-grained interaction prompts, and proposes \model, a novel framework leveraging Multimodal Large Language Models for prompt decomposition, image critique, and targeted refinement to significantly enhance the generation of complex object interactions in text-to-image synthesis.
This paper introduces Inception, the first multi-turn jailbreak attack that exploits the memory mechanisms of text-to-image systems by embedding malicious intent across segmented and recursively expanded conversational turns, achieving a 20% higher success rate than state-of-the-art methods in bypassing safety filters.
This paper proposes the Channel-Spatial Attention Synergy Network (CSASN), a novel multitask learning framework that integrates dual-branch EfficientNet and ViT architectures with attention mechanisms to effectively address data imbalance and morphological heterogeneity for the accurate diagnosis of rare thyroid carcinoma subtypes using ultrasound imaging.
This paper characterizes Apple's Synthetic Defocus Noise Pattern (SDNP) found in iPhone portrait-mode images, proposing a modeling method to mitigate its interference with PRNU-based camera source verification while demonstrating its utility for tracing images across different iPhone models and iOS versions.
This paper introduces Multi-Objective Balanced Covering (MoB), a novel visual token pruning framework that leverages Hausdorff distance and -covering theory to derive a closed-form error bound and dynamically balance prompt alignment with visual preservation, achieving significant inference acceleration with minimal performance loss across diverse multimodal models.
This paper introduces the Urdu Newspaper Benchmark (UNB) dataset and a novel pipeline combining YOLOv11x for layout analysis, SwinIR for super-resolution, and fine-tuned LLMs to demonstrate that modern language models significantly outperform traditional OCR systems in recognizing complex, low-quality Urdu newspaper text.
This paper proposes "Feature Mixing," an extremely simple and fast modality-agnostic method for multimodal outlier synthesis that achieves state-of-the-art performance in out-of-distribution detection and segmentation while offering significant speedups, alongside the introduction of a new multimodal dataset called CARLA-OOD.
This paper introduces the BAH dataset, a multimodal collection of 1,427 videos from 300 participants annotated for ambivalence and hesitancy recognition, alongside baseline benchmarking results that highlight the need for advanced models to support personalized digital health interventions.
This paper introduces TADA, a targeted diffusion-based augmentation framework that selectively generates synthetic images for hard-to-learn examples to improve classifier generalization with significantly reduced computational overhead compared to full-dataset augmentation.
This paper presents a low-power, cost-effective diffractive optical system that integrates a passive diffractive layer with a shallow neural network to remotely and accurately reconstruct 3D structural vibration spectra, overcoming the scalability and complexity limitations of traditional Structural Health Monitoring solutions.
EgoWorld is a novel framework that reconstructs semantically coherent egocentric views from rich exocentric observations—including point clouds, 3D hand poses, and text—by leveraging depth estimation and diffusion models to overcome the limitations of existing 2D-based translation methods and achieve state-of-the-art performance across diverse datasets.
This paper proposes the Partial Weakly-Supervised Oriented Object Detection (PWOOD) framework, which leverages partially weak annotations and unlabeled data through an Orientation-and-Scale-aware Student model and a Class-Agnostic Pseudo-Label Filtering strategy to achieve performance comparable to semi-supervised methods while significantly reducing annotation costs.
This paper introduces Fast Equivariant Imaging (FEI), a novel unsupervised learning framework that leverages the Augmented Lagrangian method and auxiliary Plug-and-Play denoisers to achieve a 10x training acceleration and improved generalization for deep imaging tasks like X-ray CT reconstruction and inpainting without requiring ground-truth data.
This paper proposes D2Dewarp, a fine-grained document image dewarping model that leverages dual-dimensional horizontal-vertical geometric representation learning and a new large-scale dataset (DocDewarpHV) to achieve superior rectification results compared to state-of-the-art methods.
VITA is a novel, noise-free, and conditioning-free flow matching framework that accelerates inference by directly mapping visual representations to structured latent actions via a jointly trained autoencoder and flow latent decoding, achieving state-of-the-art performance on diverse robotic tasks.
This paper introduces Persistent Homology Convolutions, a novel method that captures local topological features in histopathology slides, demonstrating that this approach outperforms standard CNNs in classification accuracy and hyperparameter robustness by effectively integrating geometric information into deep learning models.