1863 papers
This paper introduces IGLU, a novel parametric activation function derived from a scale mixture of GELU gates that utilizes a Cauchy CDF to provide heavy-tailed gradient properties and robustness against vanishing gradients, alongside a computationally efficient rational approximation (IGLU-Approx) that achieves competitive or superior performance across vision and language tasks compared to standard baselines like ReLU and GELU.
This paper proposes a hardware-efficient trajectory prediction framework that integrates environmental priors with a Dual-Transformer-Cascaded (DTC) architecture to accurately predict the landing points of flying objects, such as tennis balls, by outperforming existing methods in complex real-world scenarios.
The paper introduces PICS, a self-supervised framework that improves pairwise image compositing by employing an Interaction Transformer with mask-guided Mixture-of-Experts and adaptive blending to explicitly model spatial interactions and preserve physical consistency between objects and backgrounds.
This paper introduces OPTED, an open-source preprocessed trachoma eye dataset derived from 2,832 images using a zero-shot SAM 3 pipeline to automatically extract and standardize regions of interest, thereby addressing the scarcity of high-quality data for automated trachoma classification in Sub-Saharan Africa.
This paper proposes a novel data augmentation paradigm that leverages Large Language Models to generate diverse, industry-resembling CAD programs by conditioning them on reference surfaces and modeling procedures, thereby addressing the scarcity of complex, spline-based geometric data in existing training sets.
PaQ-DETR is a unified object detection framework that addresses query utilization imbalance by dynamically generating image-specific queries from shared latent patterns and employing a quality-aware one-to-many assignment strategy, resulting in consistent mAP improvements across various DETR backbones.
The paper proposes DLRMamba, a novel framework for edge-based multispectral object detection that combines a Low-Rank SS2D module to reduce parameter redundancy with a Structure-Aware Distillation strategy to preserve feature fidelity, achieving superior efficiency and accuracy on resource-constrained hardware.
This paper introduces ESM-YOLO+, a lightweight visible-infrared fusion network that employs a Mask-Enhanced Attention Fusion module and training-time Structural Representation enhancement to achieve high-precision small-target detection in complex remote sensing scenes while significantly reducing model complexity compared to baselines.
This paper proposes HIERAMP, a method that leverages the coarse-to-fine generation capability of Vision Autoregressive (VAR) models to amplify hierarchical semantics through dynamic class token injection, thereby improving dataset distillation performance by better capturing object structures and details without explicitly optimizing global proximity.
This study presents a 3D histomorphometric analysis pipeline using nnU-Net segmentation on optically cleared prostatectomy specimens to extract features related to perineural and lymphovascular invasion, demonstrating that 3D perineural invasion features significantly outperform their 2D counterparts in predicting 5-year biochemical recurrence in prostate cancer.
This paper introduces Virtual Intraoperative CT (viCT), a method that sequentially updates preoperative CT scans during endoscopic sinus surgery by integrating monocular endoscopic video-derived 3D reconstructions to visualize evolving tissue resection boundaries with submillimeter accuracy, thereby addressing the limitations of static image guidance.
SurgCUT3R is a novel framework that addresses the challenges of data scarcity and pose drift in monocular endoscopic video reconstruction by leveraging a synthetic data generation pipeline, hybrid supervision, and a hierarchical inference strategy to achieve robust, accurate, and efficient 3D surgical scene understanding.
This paper introduces Conditional Unbalanced Optimal Transport Maps (CUOTM), a robust conditional generative framework that mitigates the outlier sensitivity of classical Conditional Optimal Transport by relaxing distribution-matching constraints via Csiszár divergence penalties while preserving conditioning marginals through a theoretically justified triangular -transform parameterization.
The paper proposes T2SGrid, a novel framework that reformulates video temporal grounding as a spatial understanding task by arranging video frames into composite grid images via overlapping sliding windows, thereby overcoming the limitations of existing temporal encoding methods and achieving superior performance on standard benchmarks.
This paper proposes a novel approach to image-based shape retrieval that leverages pre-aligned multi-modal encoders and a hard contrastive learning loss to achieve state-of-the-art performance in both zero-shot and supervised settings, eliminating the need for explicit view-based supervision or view synthesis.
This paper proposes a perception-aware multimodal reasoning framework that enhances Vision-Language Models' spatial understanding in monocular driving scenarios by representing objects with Visual Reference Tokens and utilizing a Multimodal Chain-of-Thought dataset, achieving significant performance gains on the SURDS benchmark through standard supervised fine-tuning.
This paper introduces ADAS-TO, the first large-scale naturalistic multimodal dataset of 15,659 ADAS-to-manual takeover events from 327 drivers, which combines kinematic and vision-language analysis to characterize safety-critical scenarios and demonstrate that actionable visual cues often precede takeovers by over three seconds.
MipSLAM is a novel 3D Gaussian Splatting SLAM framework that achieves high-fidelity anti-aliased rendering and robust pose estimation by integrating an Elliptical Adaptive Anti-aliasing algorithm, a Spectral-Aware Pose Graph Optimization module, and a local frequency-domain perceptual loss to overcome aliasing artifacts and trajectory drift.
AdaGen introduces a general, learnable framework that employs reinforcement learning with an adversarial reward to dynamically adapt step-specific parameters during iterative image synthesis, thereby overcoming the limitations of static, manually-designed schedules and achieving superior performance across diverse generative models with reduced inference costs.
TrajPred is a novel framework that enhances surgical instrument-tissue interaction recognition in vision-language models by encoding instrument trajectories to capture temporal motion cues and generating fine-grained visual semantic embeddings, thereby significantly improving performance and vision-text alignment on the CholecT50 benchmark.