FLORO is a multimodal geospatial foundation model that learns transferable remote sensing representations from a small, diverse corpus, achieving strong performance across various sensor types and res…

The paper proposes Energy-Aware NECO, a single-pass hybrid detector that combines geometric ratio and logit-based energy scores to achieve superior pixel-wise out-of-distribution detection for semanti…

The paper advocates for a paradigm shift toward joint Spatial Representation Learning (SRL) that unifies raster imagery and structured vector data into a single embedding space for developing more sem…

This paper introduces a novel cloud-removal framework using Denoising Diffusion Probabilistic Models and a Masked Diffusion Transformer to generate cloud-free multispectral flood imagery, significantl…

The paper analyzes token reduction for efficient unified VLM training, finding that while task-specific acceleration saves computation, it destroys the mutual performance gains achieved through joint…

This paper investigates the application of Parameter-Efficient Fine-Tuning (PEFT) methods, specifically adapters and LoRA, to large pretrained models for instance segmentation, demonstrating that thes…

CIPER proposes a unified transformer framework to simultaneously perform cross-view image retrieval and precise 3-DoF pose estimation, overcoming the limitations of cascaded, separate methods.

The paper proposes Locality-Aware Redundancy Pruning (LoRP), a training-free method that prunes LLM layers by exploiting localized inter-layer redundancy, leading to improved efficiency while maintain…

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quali…

The paper proposes a unified framework to systematically redefine instance matching for Panoptic Quality evaluation, moving beyond the standard One-to-One matching to accommodate complex scenarios lik…

The paper proposes an attention-enhanced deep learning framework using EfficientNet and CBAM to achieve high accuracy (93.3%) in classifying peach leaf damage, demonstrating improved robustness under…

The paper proposes xModel-KD, a cross-modal knowledge distillation framework, to improve 3D point cloud segmentation by effectively transferring rich appearance cues from 2D images to sparse 3D geomet…

The paper introduces MLLM-Microscope, a system that analyzes the internal structure of multimodal large language models (MLLMs), finding that modality fusion significantly impacts the linearity and di…

PARCEL introduces a novel visual tokenization architecture that combines spatial pooling anchors with conditioned elastic queries, efficiently reducing the computational cost of large Vision-Language…

肖代替了视觉令牌的永久删除，通过可恢复的路由来改进视觉语言模型的性能

The paper proposes a novel Global Context-aware Squeeze and Excite Residual UNet (GCSER-UNet) network, which significantly enhances brain tumor segmentation accuracy on benchmark MRI datasets.

The paper shows that simple, non-architectural enhancements, such as adding semantic pseudo-labels and visibility information, can significantly boost Lidar Semantic Scene Completion performance.

The paper introduces Multi-temporal Referring Segmentation (MTRS), a new task requiring models to segment language-described temporal changes, and proposes MTRefSeg-R1, a specialized framework that ac…

CIVIC is a path-consistent compact visual inference framework that achieves genuine hardware efficiency in Vision-Language Models by maintaining contiguous sequence representations across all inferenc…