Ankur Singh — accepted AI-conference papers

2026

ShapeAR: Generating Editable Shape Layers via Autoregressive Diffusion

Souymodip Chakraborty, Ankur Singh, Amit Vikram Singh, Vineet Batra, Ankit Phogat

CVPR 2026

We present ShapeAR, a novel autoregressive latent diffusion framework that decomposes raster images into editable, artist-like vector shape layers. Unlike conventional raster-to-SVG methods that rely on boundary tracing or joint path optimisation, ShapeAR generates non-overlapping RGBA shape layers

Cited by 0 Source ↗Scholar ↗

2024

Interpretable Policy Extraction with Neuro-Symbolic Reinforcement Learning

Rajdeep Dutta, Qincheng Wang, Ankur Singh, Dhruv Kumarjiguda, Xiaoli Li, Senthilnath Jayavelu

ICASSP 2024accepted

This paper presents a novel RL algorithm, S-REINFORCE, designed by leveraging two types of function approximators, namely Neural Network (NN) and Symbolic Regressor (SR), to produce numerical and symbolic policies for dynamic decision-making tasks, respectively. A symbolic policy uncovers functional…

Cited by 0 Source ↗Scholar ↗