collaborators

10 papers

cs.CV2026

Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate

Soumava Paul, Prakhar Kaushik, Alan Yuille

Multiview 3D evaluation assumes that the images being scored are observations of one static 3D scene. This assumption can fail in NVS and sparse-view reconstruction: inputs or gene…

cs.LG2026

Shared LoRA Subspaces for almost Strict Continual Learning

Prakhar Kaushik, Ankit Vaidya, Shravan Chaudhari +2

Adapting large pretrained models to new tasks efficiently and continually is crucial for real-world deployment but remains challenging due to catastrophic forgetting and the high c…

cs.LG2026

EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference

Prakhar Kaushik, Ankit Vaidya, Shravan Chaudhari +1

The rapid growth of large models has raised concerns about their environmental impact and equity in accessibility due to significant computational costs. Low-Rank Adapters (LoRA) o…

cs.CV2026

Name That Part: 3D Part Segmentation and Naming

Soumava Paul, Prakhar Kaushik, Ankit Vaidya +2

We address semantic 3D part segmentation: decomposing objects into parts with meaningful names. While datasets exist with part annotations, their definitions are inconsistent acros…

cs.LG2025

The Universal Weight Subspace Hypothesis

Prakhar Kaushik, Shravan Chaudhari, Ankit Vaidya +2

We show that deep neural networks trained across diverse tasks exhibit remarkably similar low-dimensional parametric subspaces. We provide the first large-scale empirical evidence…

cs.CV2025

Perceptual Taxonomy: Evaluating and Guiding Hierarchical Scene Reasoning in Vision-Language Models

Jonathan Lee, Xingrui Wang, Jiawei Peng +9

We propose Perceptual Taxonomy, a structured process of scene understanding that first recognizes objects and their spatial configurations, then infers task-relevant properties suc…