-
MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
Imperial College London unveils MASt3R-SLAM: a cutting-edge monocular dense SLAM system built on the revolutionary MASt3R two-view 3D reconstruction prior, delivering unmatched real-time accuracy and global consistency. Key Highlights: Two-View 3D Priors: Leverages MASt3R’s pointmap predictions and per-pixel feature confidences, addressing key challenges in pose estimation and dense geometry reconstruction from video frames. Real-Time Performance:… →
-
CVPR 2025-Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
Fast3R breaks the pairwise bottleneck in multi-view 3D reconstruction. Building on DUSt3R, it introduces a transformer-based architecture that directly regresses dense 3D pointmaps from unposed, unordered RGB images-processing 1000+ views in a single forward pass. Key Highlights: Feedforward Multi-View Reconstruction – Eliminates the need for pairwise processing and global alignment. Predicts local and global 3D… →
-
AirSLAM: An Efficient and Illumination-Robust Point-Line Visual SLAM System
AirSLAM introduces a hybrid visual SLAM approach that integrates deep learning for feature detection with traditional backend optimization. Key highlights: Unified Feature Extraction: Employs a convolutional neural network (CNN) to simultaneously extract keypoints and structural lines, enhancing feature richness. Coupled Feature Optimization: Associates, matches, triangulates, and optimizes point and line features in a unified framework,… →
-
Patient-reported outcomes from the MIRASOL trial evaluating mirvetuximab soravtansine versus chemotherapy in patients with folate receptor alpha-positive, platinum-resistant ovarian cancer: a randomised, open-label, phase 3 trial
BACKGROUND: Mirvetuximab soravtansine-gynx (MIRV) is a first-in-class antibody-drug conjugate targeting folate receptor α (FRα), approved by the US Food and Drug Administration for the treatment of platinum-resistant ovarian cancer in the USA. Here, we report patient-reported outcomes for participants treated with MIRV compared with investigator’s choice of chemotherapy from the phase 3 MIRASOL trial, which… →
-
First-line talazoparib plus enzalutamide versus placebo plus enzalutamide in men with metastatic castration-resistant prostate cancer and homologous recombination repair gene alterations: patient-reported outcomes from the randomised, double-blind, placebo-controlled, phase 3 TALAPRO-2 trial
BACKGROUND: In the phase 3 TALAPRO-2 trial, talazoparib plus enzalutamide significantly improved radiographic progression-free survival compared with placebo plus enzalutamide in men with metastatic castration-resistant prostate cancer harbouring alterations in genes involved in homologous recombination repair (HRR). We aimed to assess patient-reported outcomes in patients with HRR-deficient metastatic castration-resistant prostate cancer in TALAPRO-2. →
-
First-line talazoparib plus enzalutamide versus placebo plus enzalutamide for metastatic castration-resistant prostate cancer: patient-reported outcomes from the randomised, double-blind, placebo-controlled, phase 3 TALAPRO-2 trial
BACKGROUND: Patients with metastatic castration-resistant prostate cancer have poor prognoses, underscoring the need for novel therapeutic strategies. First-line talazoparib plus enzalutamide significantly improved radiographic progression-free survival compared with placebo plus enzalutamide in men with metastatic castration-resistant prostate cancer in the phase 3 TALAPRO-2 study. We aimed to evaluate patient-reported outcomes in the all-comers cohort of… →
-
-
Meet Open-Qwen2VL: A Fully Open and Compute-Efficient Multimodal Large Language Model
Meet Open-Qwen2VL: A Fully Open and Compute-Efficient Multimodal Large Language Model Multimodal Large Language Models (MLLMs) have advanced the integration of visual and textual modalities, enabling progress in tasks such as image captioning, visual question answering, and document interpretation. However, the replication and further development of these models are often hindered by a lack of… →
-
-
Researchers from Dataocean AI and Tsinghua University Introduces Dolphin: A Multilingual Automatic Speech Recognition ASR Model …
Researchers from Dataocean AI and Tsinghua University Introduces Dolphin: A Multilingual Automatic Speech Recognition ASR Model Optimized for Eastern Languages and Dialects Automatic speech recognition (ASR) technologies have advanced significantly, yet notable disparities remain in their ability to accurately recognize diverse languages. Prominent ASR systems, such as OpenAI& Whisper, exhibit pronounced performance gaps when processing… →
