7592 papers
This paper proposes a bimanual manipulation framework that leverages a pre-trained 3D geometric foundation model to fuse RGB-based 3D latents, 2D semantics, and proprioception within a diffusion policy, enabling the joint prediction of actions and future 3D scene evolution to achieve state-of-the-art performance without relying on explicit point clouds.
This paper introduces an exemplar-free continual learning framework for histopathology report generation that prevents catastrophic forgetting by using compact domain footprints to synthesize pseudo-WSI representations and distill linguistic styles, enabling effective adaptation to evolving clinical data without storing raw slides.
This paper proposes CPN-YOLO, a robust SAR ship detection framework that enhances YOLOv8 through a learnable large-kernel denoising module, a PPA-based feature extraction strategy, and a Gaussian similarity loss, achieving superior precision and recall on HRSID and SSDD datasets.
This paper proposes a robust end-to-end multimodal framework for DICOM series classification that leverages bi-directional cross-attention and a sparse, missingness-aware dictionary learning encoder to effectively handle heterogeneous image content, variable series lengths, and incomplete metadata without requiring imputation, thereby outperforming existing baselines in both in-domain and out-of-domain settings.
This paper proposes a Polarization Uncertainty-Guided Diffusion Model that leverages image diffusion priors and explicitly models polarization uncertainty to accurately reconstruct high-fidelity color polarization images, effectively overcoming the limitations of existing network-based methods in recovering polarization characteristics due to data scarcity.
The NAU-QMUL team proposed a multi-modal multi-task model leveraging pre-trained BERT and CLIP encoders with cross-modal fusion and pseudo-labeling data augmentation to achieve fifth place in both detection and source identification tasks of the CT2 AI-Generated Image Detection competition.
This paper introduces ReSeg-CLIP, a training-free open-vocabulary semantic segmentation method for remote sensing that achieves state-of-the-art performance by combining hierarchical attention masking with SAM-generated masks and a novel model composition strategy that averages multiple RS-specific CLIP variants.
This paper proposes a bandwidth-adaptive, cloud-assisted framework for autonomous vehicles that dynamically splits transformer-based 360-degree 3D perception tasks between the vehicle and the cloud using feature compression and quantization, achieving a 72% latency reduction and up to 20% accuracy improvement over static methods under fluctuating network conditions.
This paper proposes a hardware-free, vision-only approach for aerial visual place recognition that estimates relative altitude through ground feature density analysis to generate canonical images, significantly improving localization accuracy and robustness across diverse terrains and large altitude variations compared to traditional sensor-dependent or depth estimation methods.
This paper proposes DACESR, a real-world image super-resolution framework that enhances degraded image recognition via a Real Embedding Extractor (REE) and integrates these high-level features into a Mamba-based network using a Conditional Feature Modulator (CFM) to achieve superior fidelity and perceptual quality.
The paper proposes SelfOccFlow, a self-supervised method for end-to-end 3D occupancy flow prediction that eliminates the need for human annotations or external flow supervision by disentangling static and dynamic scenes and leveraging temporal aggregation with a cosine similarity-based flow cue.
This paper introduces Ref-Adv, a challenging benchmark for Referring Expression Comprehension designed to eliminate shortcut solutions and expose significant gaps in visual reasoning and grounding capabilities of current multimodal LLMs.
The paper proposes BUSD-Agent, an experience-guided self-adaptive cascaded multi-agent framework for breast ultrasound screening and diagnosis that leverages a memory bank of historical decision trajectories to dynamically adjust escalation thresholds, significantly reducing unnecessary biopsy referrals and improving specificity without requiring model parameter updates.
ABPolicy is an asynchronous flow-matching framework that utilizes B-spline control points and bidirectional prediction with refitting to generate smooth, continuous, and real-time robotic manipulation trajectories, effectively eliminating the jitter and discontinuities common in synchronous action-space policies.
SegMate is an efficient, open-source 2.5D framework that leverages asymmetric attention and multi-scale fusion to achieve state-of-the-art multi-organ segmentation accuracy while significantly reducing computational costs and memory usage across diverse medical datasets.
This paper identifies and addresses the "half-truth" vulnerability in CLIP-style models, where adding plausible but incorrect details to a description erroneously increases similarity scores, by proposing CS-CLIP, a component-supervised training approach that decomposes captions into entities and relations to enforce finer-grained grounding and significantly improve compositional understanding.
This paper proposes a novel training-free Topology-Driven Transferability Estimation framework that leverages global and local topological metrics to accurately rank medical foundation models for segmentation tasks, significantly outperforming existing classification-based methods on the OpenMind benchmark.
The paper proposes GPU-SDF, a neural implicit framework for high-fidelity indoor surface reconstruction that explicitly estimates geometric prior uncertainty to modulate prior influence and incorporates complementary edge and multi-view constraints to recover fine details and complex geometries.
This paper proposes STE-VLN, a novel approach that enhances Vision-Language Navigation in unseen environments by constructing the YE-KG, a large-scale multimodal spatiotemporal knowledge graph derived from real-world indoor videos, and integrating it via a Coarse-to-Fine Hierarchical Retrieval mechanism to improve long-horizon reasoning and handle coarse-grained instructions.
This paper introduces PointCoT, a novel framework and large-scale benchmark (Point-Reason-Instruct) that enhances Multimodal Large Language Models' 3D point cloud understanding by enforcing an explicit "Look, Think, then Answer" Chain-of-Thought reasoning paradigm to mitigate geometric hallucinations and achieve state-of-the-art performance.