3204 papers
This paper proposes HART, an annotation-free framework that leverages a novel Advantage Preference Group Relative Policy Optimization (AP-GRPO) algorithm to enable Large Multimodal Models to autonomously identify and verify key high-resolution image regions, thereby improving reasoning performance without requiring costly human grounding labels.
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 introduces WildActor, a framework for unconstrained identity-preserving human video generation that leverages the large-scale Actor-18M dataset and novel attention mechanisms to overcome existing limitations in maintaining consistent full-body identities across dynamic shots, viewpoints, and motions.
This position paper argues that the evaluation of modern visual processing systems must shift from a reliance on single-metric benchmarks toward a human-centered, context-aware paradigm to better align with human perception and foster genuine innovation.
The paper proposes DeAR, a fine-grained adaptation framework for Vision-Language Models that decomposes attention heads into functional roles (Attribute, Generalization, and Mixed) using a Concept Entropy metric to selectively isolate task-specific learning from generalization capabilities, thereby achieving superior performance across diverse tasks while preserving zero-shot robustness.
The paper proposes the MSP framework, which mitigates hairstyle distraction and preserves structural information through Hairstyle-Oriented Augmentation, Cloth-Preserved Random Erasing, and Region-based Parsing Attention to achieve state-of-the-art performance in cloth-changing person re-identification.
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 proposes a robust framework combining the hybrid CoAtNet architecture with model soups ensembling to effectively classify Intangible Cultural Heritage images from the Mekong Delta, achieving state-of-the-art performance on the ICH-17 dataset by reducing variance and enhancing generalization in data-scarce, high-similarity settings.
This paper evaluates DINOv3 as a frozen backbone for blueberry robotic harvesting tasks, finding that while it excels in segmentation through stable patch-level representations, its detection performance is limited by scale variation and spatial aggregation challenges, suggesting it functions best as a semantic backbone requiring downstream spatial modeling tailored to fruit structures.
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.
This paper introduces CGL, a continual GUI learning framework that mitigates catastrophic forgetting by dynamically balancing Supervised Fine-Tuning and Reinforcement Learning through an entropy-guided proportion adjustment mechanism and a specialized gradient surgery strategy, validated by a new AndroidControl-CL benchmark.
This paper introduces LDP-Slicing, a lightweight, training-free framework that overcomes the utility limitations of applying Local Differential Privacy to high-dimensional images by decomposing pixel values into binary bit-planes and integrating perceptual obfuscation and optimized budget allocation to achieve rigorous privacy with high downstream task performance.
This paper introduces DeepScope, a deep learning-based system that analyzes microscopic images of unincubated water samples to detect fecal contamination in seconds with 93% accuracy and a cost of $0.44 per test, significantly outperforming traditional incubation methods in speed and affordability.
The paper introduces OptiRoulette, a stochastic meta-optimizer that dynamically selects update rules from a pool during training, demonstrating significantly faster convergence and higher test accuracy across multiple image-classification benchmarks compared to a standard AdamW baseline.
This paper proposes a unified linear representation for diffusion models and flow matching to theoretically demonstrate that the often weak correlation between noisy data and predicted targets in existing methods may adversely impact the learning process.
RECAP is a bio-inspired image classification method that couples untrained reservoir dynamics with a self-organizing Hebbian prototype readout to achieve robust, backpropagation-free learning capable of generalizing to corrupted inputs without prior exposure.
This paper reveals that pruning-based unlearning in diffusion models is inherently insecure because the locations of pruned weights act as side-channel signals that enable a novel, data-free, and training-free attack to fully revive erased concepts, prompting a call for safer pruning mechanisms that conceal these locations.
This paper introduces ObjChangeVR, a novel framework and corresponding dataset designed to enhance object state change reasoning in virtual reality by addressing the challenges of detecting background changes without direct interaction through viewpoint-aware retrieval and cross-view reasoning.
This paper proposes a margin-consistent deep subtyping framework for invasive lung adenocarcinoma that integrates attention-weighted aggregation, contrastive regularization, and a novel Perturbation Fidelity scoring mechanism to achieve robust, high-accuracy classification across multiple architectures and demonstrate cross-institutional generalizability on whole-slide images.
PaLMR is a novel framework that enhances the faithfulness of multimodal large language models by aligning both the reasoning process and outcomes through a perception-aligned data layer and a hierarchical reward fusion scheme, thereby significantly reducing visual hallucinations while achieving state-of-the-art performance on key benchmarks.