3390 papers
DocCogito is a unified framework for document understanding that aligns global layout perception with structured, region-grounded reasoning through a lightweight layout tower and a deterministic Visual-Semantic Chain, achieving state-of-the-art performance on multiple benchmarks by enforcing systematic coupling between layout priors and evidence-based reasoning.
This paper proposes AMR-CCR, an anchored modular retrieval framework with script-conditioned injection and multi-prototype dictionaries to address the challenges of continual, class-incremental ancient Chinese character recognition, accompanied by the new EvoCON benchmark for systematic evaluation.
This paper proposes a skeletal latent diffusion framework that leverages a differentiable skeletonization module and a large-scale MedSDF dataset to achieve high-fidelity, computationally efficient medical shape generation while effectively addressing challenges posed by anatomical geometric complexity and data scarcity.
This paper establishes a unified theoretical framework demonstrating that drifting models, which optimize kernel-based mean-shift discrepancies, are mathematically equivalent to score-matching objectives on kernel-smoothed distributions, thereby precisely connecting them to diffusion models and clarifying their relationship with Distribution Matching Distillation.
The paper proposes EvolveReason, a self-evolving reasoning paradigm that combines a human-like chain-of-thought framework, a forgery latent-space distribution capture module, and a reinforcement learning-based self-evolution strategy to enhance the accuracy, detail, and reliability of explainable deepfake facial image identification.
This paper introduces SketchGraphNet, a memory-efficient hybrid graph transformer that models free-hand sketches as structured graphs to achieve state-of-the-art recognition accuracy on the newly constructed 3.44-million-sample SketchGraph benchmark while significantly reducing computational resource requirements.
The paper proposes ACCURATE, a robust 3D reconstruction framework that combines image segmentation with geometry-constrained topology traversal and dynamic programming to achieve high-accuracy reconstruction of arbitrary-shaped, deformable continuum bodies like guidewires and catheters under biplanar X-ray imaging.
This paper proposes a semantic geometric framework that leverages small vehicles as metric anchors within a decoupled stereoscopic projection model to recover absolute scale from monocular UAV images, thereby enabling scale-adaptive satellite image cropping and significantly improving cross-view geo-localization robustness under real-world scale ambiguity.
This paper introduces UniLongGen, a training-free inference strategy that improves long-horizon interleaved image generation by dynamically curating context to discard accumulated visual noise, thereby overcoming the reliability collapse caused by dense visual token interference in unified multimodal models.
The paper introduces CONSTANT, a novel one-shot handwriting generation framework that leverages Style-Aware Quantization and a latent patch-based contrastive objective within a diffusion model to overcome existing limitations in capturing diverse writer styles and generating high-quality, realistic handwritten images across multiple languages.
DreamSAC is a framework that enhances extrapolative generalization in physics simulations by combining an unsupervised symmetry exploration strategy, which actively probes conservation laws via a Hamiltonian-based curiosity bonus, with a Hamiltonian-based world model that learns invariant physical states from raw observations through a novel contrastive objective.
ReconDrive is a fast, feed-forward framework that adapts the VGGT foundation model with hybrid prediction heads and static-dynamic composition to achieve high-fidelity, scalable 4D Gaussian Splatting for autonomous driving scenes, outperforming existing feed-forward methods while matching the quality of slower optimization-based approaches.
This paper proposes an active inference-based framework for micro-gesture recognition that utilizes Expected Free Energy-guided temporal sampling and uncertainty-aware adaptive learning to overcome challenges like low amplitude, noise, and inter-subject variability, demonstrating significant performance improvements on the SMG dataset.
PureCC is a novel concept customization framework that employs a decoupled learning objective and a dual-branch training pipeline to achieve high-fidelity text-to-image personalization while effectively preserving the original model's behavior and capabilities.
Brain-WM is a pioneering brain glioblastoma world model that utilizes a novel Y-shaped Mixture-of-Transformers architecture to unify next-step treatment prediction and future MRI generation, effectively capturing the co-evolutionary dynamics between tumor progression and treatment response to optimize clinical outcomes.
The paper proposes SiamGM, a real-time Siamese network for satellite video object tracking that integrates a geometry-aware Inter-Frame Graph Attention module and a motion-guided optimization strategy to effectively address challenges like small targets and occlusions while achieving 130 FPS without computational overhead.
The paper proposes GRD-Net, a novel architecture combining a generative adversarial network with a region-of-interest attention module to improve industrial surface anomaly detection and localization by learning from normal products and synthetic defects while focusing on relevant areas, thereby reducing reliance on biased post-processing algorithms.
This paper proposes an efficient multi-task RGB-D scene understanding model that integrates an enhanced fusion encoder, specialized feature interaction layers, and a dynamic adaptive loss function to simultaneously perform semantic, instance, and panoptic segmentation, orientation estimation, and scene classification with improved accuracy and speed across multiple datasets.
This paper systematically evaluates four training objectives—Cross-Entropy, Prototype, Triplet, and Average Precision Losses—for out-of-distribution detection in image classification, revealing that while they achieve comparable in-distribution accuracy, Cross-Entropy Loss delivers the most consistent performance across both near- and far-OOD scenarios under standardized protocols.
This paper presents a semi-supervised deep generative anomaly detection framework, utilizing a residual autoencoder with a dense bottleneck, that achieves high-accuracy, real-time defect detection and localization on high-speed pharmaceutical Blow-Fill-Seal production lines while operating within strict 500 ms timing constraints.