3340 papers
This paper introduces MAviS, a domain-adaptive multimodal conversational assistant for avian species that leverages the newly created MAviS-Dataset and is evaluated on the MAviS-Bench to achieve state-of-the-art performance in fine-grained bird species understanding and multimodal question answering.
This paper proposes a training-centered approach that combines adversarial training with a lightweight feature-map smoothing block to generate saliency maps that are simultaneously sparse, input-stable, and output-stable, thereby enhancing their perceived trustworthiness and sufficiency.
This paper introduces StructSAM, a novel token merging framework that preserves structural boundaries and spectral properties in Segment Anything Models (SAM) by using gradient-based energy scores and grid-based screening to achieve significant computational savings with minimal accuracy loss across natural and medical imaging benchmarks.
Faster-HEAL is a lightweight, privacy-preserving collaborative perception framework that addresses the challenges of heterogeneous autonomous vehicles by using low-rank visual prompt fine-tuning and pyramid fusion to align diverse features into a unified space, achieving superior detection performance with significantly reduced computational overhead compared to state-of-the-art methods.
This paper proposes a lightweight, digital-twin-based framework for edge-assisted vehicle tracking and collision prediction that achieves approximately 88% accuracy by relying on object detection and K-D tree-indexed path maps instead of computationally intensive trajectory prediction models.
The AgrI Challenge introduces a data-centric competition framework featuring Cross-Team Validation to demonstrate that while single-source training suffers from significant generalization gaps in agricultural vision, collaborative multi-source training on independently collected, heterogeneous datasets dramatically improves model robustness and real-world performance.
The paper introduces N-Tree Diffusion (NT-Diffusion), a hierarchical diffusion model that improves long-horizon wildfire risk forecasting by sharing early denoising stages across prediction horizons to reduce computational redundancy while maintaining probabilistic accuracy.
By tracking macaque V4 neural responses during visual discrimination learning, the study demonstrates that task learning increases information redundancy rather than reducing it, supporting a Bayesian generative inference model where redundancy enhances the information carried by individual neurons.
This paper introduces AQuA, a fine-grained dataset that categorizes ambiguous visual questions into four levels with corresponding optimal response strategies, demonstrating that fine-tuning Vision-Language Models on this dataset enables them to effectively recognize ambiguity and adaptively generate context-appropriate responses such as seeking clarification or listing alternatives, thereby outperforming existing baselines.
This paper proposes an interpretable 3D Concept Bottleneck Model that integrates morphological and hemodynamic clinical features to classify intracranial aneurysms with high accuracy (up to 93.33%) while ensuring clinical transparency and regulatory compliance.
This paper introduces VIVECaption, a systematic two-sided approach that combines a comprehensive evaluation taxonomy with a gold-standard dataset creation methodology and model alignment strategy to significantly improve image-caption alignment quality for training text-to-image and text-to-video generative models using copyright-safe "vegan" data.
This paper addresses the lack of specialized dental datasets by proposing a framework that uses Vision-Language Models with guided prompts to generate high-quality, holistic captions for single-tooth RGB images, thereby enabling more comprehensive dental image analysis.
The paper introduces UnSCAR, a scalable and controllable universal image restoration framework that utilizes a multi-branch mixture-of-experts architecture to overcome the limitations of catastrophic forgetting and performance degradation in existing all-in-one models when handling multiple real-world degradations.
This paper introduces QdaVPR, a novel query-based visual place recognition model that achieves state-of-the-art domain-agnostic performance across diverse environmental conditions by employing a dual-level adversarial learning framework and query-based triplet supervision trained on augmented synthetic domains.
This paper proposes DTPSR, a novel diffusion-based image super-resolution framework that leverages disentangled textual priors across spatial and frequency dimensions, supported by a new large-scale dataset and multi-branch guidance, to achieve high perceptual quality and semantic controllability.
This paper addresses the underexplored challenge of generalization in online reinforcement learning for mobile GUI agents by introducing the AndroidWorld-Generalization benchmark and a scalable GRPO-based training system, demonstrating that while RL significantly improves zero-shot performance on unseen task instances, generalization to new templates and applications remains difficult and benefits from test-time few-shot adaptation.
The paper proposes Data Agent, an end-to-end dynamic data selection framework that formulates sample selection as a training-aware sequential decision-making problem to accelerate model training while preserving performance across diverse datasets and tasks.
RPG-SAM is a training-free one-shot polyp segmentation framework that improves performance by addressing regional and response heterogeneity through reliability-weighted prototype mining, geometric adaptive threshold selection, and iterative boundary refinement, achieving a 5.56% mIoU gain on the Kvasir dataset.
DogWeave is a novel framework that reconstructs high-fidelity 3D canine models from a single RGB image by refining parametric meshes into detailed SDF representations via diffusion-enhanced normal optimization and generating view-consistent textures through conditional inpainting, thereby overcoming challenges like self-occlusion and fur detail to outperform existing state-of-the-art methods.
Med-Evo is a novel self-evolution framework for medical multimodal large language models that leverages label-free reinforcement learning, featuring Feature-driven Pseudo Labeling and Hard-Soft Reward mechanisms, to significantly enhance model performance on unlabeled test data without requiring additional annotated medical datasets.