1863 papers
This paper introduces OddGridBench, a benchmark revealing that current multimodal large language models significantly underperform humans in detecting fine-grained visual discrepancies, and proposes OddGrid-GRPO, a reinforcement learning framework that effectively enhances this sensitivity through curriculum learning and distance-aware rewards.
This paper introduces the Strategic Tactical Agent Reasoning (STAR) benchmark, a multi-agent framework for evaluating LLMs in zero-sum environments, which reveals a critical trade-off where reasoning-intensive models excel in turn-based settings but often underperform in real-time scenarios due to latency, highlighting the need to balance strategic depth with rapid execution.
This paper proposes Predictive Spectral Calibration (PSC), a simple and model-agnostic source-free framework that enhances test-time adaptation for image regression by extending subspace alignment to block spectral matching, thereby achieving consistent performance improvements over strong baselines, especially under severe distribution shifts.
This paper proposes a robust and provably secure image steganography framework that utilizes latent-space iterative optimization to significantly enhance message extraction accuracy under various compression and processing scenarios while maintaining security guarantees.
This paper introduces Evidential Perfusion Physics-Informed Neural Networks (EPPINN), a novel framework that integrates evidential deep learning with physics-informed modeling to quantify both aleatoric and epistemic uncertainties in CT perfusion imaging, thereby achieving superior accuracy and reliability in acute ischemic stroke assessment compared to existing deterministic methods.
This paper proposes M3GCLR, a game-theoretic contrastive learning framework that addresses limitations in existing skeleton-based action recognition methods by establishing an Infinite Skeleton-data Game model with a mini-max optimization strategy and dual-loss equilibrium optimizer to effectively handle view discrepancies, adversarial mechanisms, and augmentation perturbations, achieving state-of-the-art performance on multiple benchmarks.
The paper proposes MIL-PF, a scalable framework that combines frozen foundation model encoders with a lightweight attention-based Multiple Instance Learning head to achieve state-of-the-art mammography classification while significantly reducing computational costs and training complexity.
SinGeo is a novel framework that achieves robust cross-view geo-localization using a single model by employing a dual discriminative learning architecture and a curriculum learning strategy, thereby overcoming the limitations of existing methods that struggle with unseen fields of view and orientations.
EventVGGT is a novel framework that addresses the scarcity of depth annotations and temporal inconsistency in event-based monocular depth estimation by treating event streams as coherent video sequences and distilling spatio-temporal and multi-view geometric priors from the Visual Geometry Grounded Transformer (VGGT) through a tri-level distillation strategy, achieving state-of-the-art performance and robust zero-shot generalization.
The paper proposes MIDAS, a training-free diffusion-based framework that enables coverless multi-image steganography with user-specific access control through latent-level fusion, demonstrating superior performance in image quality, robustness, and security compared to existing methods.
This paper presents the ICDAR 2025 competition on end-to-end document image machine translation, detailing its dual-track structure for small and large models, participation statistics, and findings that highlight large-model approaches as a promising paradigm for handling complex document layouts.
This paper introduces YOLO-NAS-Bench, the first surrogate benchmark for YOLO-style object detectors, which employs a self-evolving mechanism to iteratively refine a LightGBM predictor, enabling efficient and accurate discovery of high-performing architectures that surpass official YOLO baselines.
This paper introduces the Fully Convolutional Diffusion Model (FCDM), a ConvNeXt-based architecture that achieves competitive generative performance with significantly fewer computational resources and training steps than Transformer-based counterparts, demonstrating that modern convolutional designs remain a highly efficient alternative for scaling diffusion models.
RiO-DETR is the first real-time oriented object detection transformer that addresses challenges in angle estimation, periodicity, and convergence through novel designs like Content-Driven Angle Estimation and Decoupled Periodic Refinement, achieving a new speed-accuracy trade-off on benchmark datasets.
This paper introduces PromptDLA, a domain-aware framework that leverages descriptive knowledge as cues to customize prompts for integrating domain priors, thereby overcoming the limitations of directly merging diverse datasets and achieving state-of-the-art performance in Document Layout Analysis across multiple benchmarks.
CIGPose introduces a Causal Intervention Graph Neural Network framework that enhances whole-body pose estimation robustness by using a Structural Causal Model to identify and replace context-confounded keypoint representations with invariant embeddings, thereby achieving state-of-the-art performance on COCO-WholeBody without relying on extra training data.
The paper proposes MetaDAT, a trajectory prediction framework that combines meta-learning pre-training with a data-adaptive test-time updating mechanism to achieve robust, fast, and accurate online adaptation under distribution shifts by dynamically adjusting learning rates and focusing on informative hard samples.
This paper introduces "Open-World Motion Forecasting," an end-to-end class-incremental framework that predicts future trajectories directly from camera images while mitigating catastrophic forgetting through pseudo-labeling with vision-language models and a novel query feature variance-based replay strategy, enabling continual adaptation to evolving object taxonomies in real-world autonomous driving.
The paper proposes GIIM, a novel graph-based framework that enhances multi-view medical image diagnosis by simultaneously modeling intra-view relationships and inter-view dynamics while effectively handling missing data to improve predictive accuracy and robustness.
This paper introduces OncoAgent, a novel guideline-aware AI agent that achieves zero-shot, training-free auto-delineation of clinical target volumes by converting textual clinical guidelines into 3D contours, demonstrating superior adaptability and physician preference over traditional supervised deep learning models.