2 papers
cs.LG2025
Reliable Active Learning from Unreliable Labels via Neural Collapse Geometry
Atharv Goel, Sharat Agarwal, Saket Anand +1
Active Learning (AL) promises to reduce annotation cost by prioritizing informative samples, yet its reliability is undermined when labels are noisy or when the data distribution s…
cs.CV2025
Just Add Geometry: Gradient-Free Open-Vocabulary 3D Detection Without Human-in-the-Loop
Atharv Goel, Mehar Khurana
Modern 3D object detection datasets are constrained by narrow class taxonomies and costly manual annotations, limiting their ability to scale to open-world settings. In contrast, 2…