影响力指数

13.58/100

超过 41.8%

全站排名 #37,497

发表论文7 篇

平均评分4.7

年均产出2.3 篇/年

Prakhar Kaushik

PhD student@Johns Hopkins University·美国·OpenReview

研究方向

3d part segmentation · 3d vlm · model merging · information removal · model efficiency · 3D pose estimation · 3D scene reconstruction · unsupervised learning · domain adaptation · vision-language models · text-to-image · text-to-3D · image-to-3D · continual learning · lifelong learning

Do Neural Networks Learn Similar Subspaces? An Empirical Exploration of Joint Parametric Subspaces in Deep Neural Networks

ICLR 2026Rejected

EigenLoRAx: Efficient Low Rank Adaptation Using Recycled Principal Subspaces

ICLR 2026Withdrawn

DSPart: A Large-scale Diffusion-generated Synthetic Dataset with Annotations from 3D Parts

ICLR 2025Rejected

EigenLoRA: Recycle trained Adapters for Resource Efficient Adaptation and Inference

ICLR 2025Rejected

Scaling 3D Compositional Models for Robust Classification and Pose Estimation

ICLR 2025Withdrawn

CIDA3D: Conformal Inference aided unsupervised Domain Adaptation for 3D-Aware Classification

ICLR 2025Withdrawn

合作者 (20)

博士导师7 篇

Adam Kortylewski

Shravan S Chaudhari