1863 papers
The paper proposes SurgFed, a language-guided multi-task federated learning framework that utilizes Language-guided Channel Selection and Language-guided Hyper Aggregation to overcome tissue and task diversity challenges, thereby improving surgical video segmentation and depth estimation across heterogeneous clinical environments.
The paper presents Context-Nav, a training-free framework for text-goal instance navigation that combines caption-driven frontier ranking for global exploration with viewpoint-aware 3D spatial verification to accurately disambiguate target objects in cluttered environments, achieving state-of-the-art performance on InstanceNav and CoIN-Bench.
This paper investigates the reliability of Vision-Language Models (VLMs) in autonomous driving by exposing their tendencies toward response inconsistency and weak temporal reasoning, and subsequently proposes the FutureVQA benchmark and a self-supervised chain-of-thought tuning method to enhance grounded future scene reasoning without requiring temporal labels.
The paper introduces RESBev, a plug-and-play framework that enhances the robustness of Bird's-eye-view (BEV) perception systems against sensor degradation and adversarial attacks by reframing the problem as latent semantic prediction to reconstruct clean features from corrupted observations.
This paper proposes DCAU-Net, a novel medical image segmentation framework that combines Differential Cross Attention to efficiently model long-range dependencies while reducing computational complexity, and a Channel-Spatial Feature Fusion strategy to adaptively integrate semantic and spatial details, thereby achieving enhanced segmentation accuracy and robustness.
This study demonstrates that the longitudinal progression of radiologic pleuroparenchymal fibroelastosis (PPFE), quantified via automated analysis of low-dose CT scans, independently predicts increased mortality and adverse respiratory outcomes in large lung cancer screening cohorts.
This paper proposes a reinforcement learning-based post-training strategy that extends Group Relative Policy Optimization (GRPO) with hybrid and process-level rewards to enable existing unified vision-language models to generate high-quality multimodal interleaved outputs without relying on large-scale interleaved datasets.
This paper introduces DynHiL-EQA, a new dataset for dynamic human-in-the-loop Embodied Question Answering, and proposes DIVRR, a training-free framework that enhances robustness and inference efficiency by refining ambiguous views and selectively managing memory in dynamic environments.
This paper presents a comprehensive study of Time-of-Flight non-line-of-sight imaging methods by unifying their theoretical formulations and hardware implementations to establish a common framework for analysis and demonstrate that, under equal constraints, existing techniques share similar performance limitations despite method-specific differences.
The paper introduces GeoSolver, a framework that enhances remote sensing reasoning by leveraging a large-scale process supervision dataset (Geo-PRM-2M) and a novel Process-Aware Tree-GRPO algorithm to train a token-level reward model (GeoPRM), thereby enabling verifiable, step-by-step reasoning and robust test-time scaling for both specialized and general-purpose Vision-Language Models.
The paper introduces GeoAlignCLIP, a unified framework that enhances fine-grained vision-language alignment in remote sensing by leveraging multi-granular semantic learning and intra-modal consistency, supported by a newly constructed hierarchical dataset (RSFG-100k) to outperform existing methods on diverse benchmarks.
This paper introduces the Panorama-Language Modeling (PLM) paradigm and the PanoVQA dataset to enable holistic $360^\circ$ vision-language reasoning in adverse omni-scenes, demonstrating that a unified panoramic approach yields superior understanding compared to stitching multiple narrow-field-of-view inputs.
This paper introduces BinaryAttention, a theoretically grounded method that replaces floating-point dot products with 1-bit sign-based operations and learnable biases to achieve over 2x speedup over FlashAttention2 while matching or exceeding full-precision accuracy in vision and diffusion transformers.
The paper proposes ParTY, a novel framework that improves text-to-motion synthesis by introducing part-guided networks, part-aware text grounding, and holistic-part fusion to overcome the limitations of existing methods in aligning specific body part actions with text while maintaining full-body motion coherence.
This paper proposes a saccade-inspired image classification method that leverages DINO's Vision Transformer attention maps to selectively focus processing on task-relevant regions, achieving performance comparable to or better than full-image analysis while offering a biologically plausible approach to efficient visual processing.
This paper proposes a zero-shot MRI super-resolution framework that leverages explicit, physics-driven 3D Gaussian representations and parallel brick-based rasterization to achieve high-quality, efficient reconstruction without relying on costly paired training data.
This paper introduces Quantization-aware Distilled Restoration (QDR), a novel framework that employs Decoder-Free Distillation and Learnable Magnitude Reweighting to overcome bottlenecks in quantization-aware training, enabling high-performance, edge-deployed image restoration models that achieve near-FP32 accuracy and significant speedups.
This paper proposes a vision-language grounded framework for interpretable synthetic data generation and evaluation in remote sensing, introducing the ARAS400k dataset which demonstrates that augmenting real data with synthetic images consistently outperforms real-data-only baselines in semantic segmentation and image captioning tasks.
This paper introduces X-GS, an extensible open framework that unifies 3D Gaussian Splatting with downstream multimodal models through a real-time, semantically enriched pipeline capable of processing unposed video streams for tasks like object detection and zero-shot captioning.
This paper presents OTPL-VIO, a robust stereo visual-inertial odometry system that enhances performance in low-texture and illumination-challenging environments by employing a training-free deep descriptor with entropy-regularized optimal transport for line association and introducing adaptive uncertainty weighting to stabilize estimation.