menu

Aditya Ganeshan

CS PhD Student
Brown University
Graphics / Vision / Mathematics / Machine Learning / Music
Most recent update: 16 October 2023.

What I am doing now:

I am contributing towards four research directions: a) Semi-supervised program synthesis with approximate gradients, b) neural program rewriting, c) 3D Shape Editing with LLMs and d) 3D Scene generation with LLMs. Apart from that, I spend some time trying to make music and understanding different graphics/vision/pl problems/ideas.

Short Bio: Aditya Ganeshan is a third-year Ph.D. student at the Brown Visual Computing group, advised by Professor Daniel Ritchie. He is interested in developing techniques for inferring and using structured representations for 3D data (Shapes and Scenes). Previously, he worked on vision for autonomous driving at Preferred Networks Inc., Japan, and adversarial robustness at IISc, India. He completed his Bachelor’s in Applied Mathematics from IIT Roorkee, India.

Recent Research:

Improving Unsupervised Visual Program Inference with Code Rewriting Families

A. Ganeshan, R. Kenny Jones and Daniel Ritchie

Oral (1.8%) IEEE / CVF International Conference on Computer Vision (ICCV), 2023

Skill Generalization with Verbs

R. Ma, L. Lam, B. A. Spiegel, A. Ganeshan, B. Abbatematteo, R. Patel, D. Paulius, S. Tellex, G. Konidaris.

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023

Warp-Refine Propagation Semi-Supervised Auto-labeling via Cycle-consistency

A. Ganeshan , Alexis Vallet, Yasunori Kudo, Shin-ichi Maeda, Tommi Kerola, Rares Ambrus, Dennis Park, Adrien Gaidon

IEEE / CVF International Conference on Computer Vision (ICCV), 2021

Phonetroller - Visual Representations of Fingers for Precise Touch Input with Mobile Phones in VR

Fabrice Matulic, A. Ganeshan, Hiroshi Fujiwara, Daniel Vogel

Conference on Human Factors in Computing Systems, CHI 21

Meta-Learning Extractors for Music Source Separation

David Samuel, A. Ganeshan, Jason Naradowsky

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-2020)

Recent highlights and news:

  • 19 December 2023 : Finished my fifth semester with no courses. Most of the time spent in research - coding clean versions of old packages, and pushing forth with new ideas!
  • 9 December 2023 : I released the code for GeoLIPI: A DSL for Implicit Geometric Modelling. Its my attempt at putting together different code pieces I deal with constantly into one place. The code is still in its infancy, and I will be adding more features to it as I go along.
  • 15 October 2023 : I released the code for Branching BAD, Neural Volumetric Primitives, and Pack Poly. Also, a config parser wacky and a minor tool ProcXD. Code for GeoLIPI (meta langauge for shape languages) and CoReF (code rewriting families) to be released soon.
  • 1 October 2023 : Thanks to Yiming Qian for selecting our ICCV 2023 paper for a student paper talk at the 3D Vision and Modeling Challenges in eCommerce Workshop at ICCV 2023 (of course thanks to Daniel for suggesting the paper when asked for it).
  • 1 October 2023 : Thanks to Daniel for sponsoring my trip to paris for present our paper at ICCV 2023! Quite an experience! Good to see people take interest in “structured representations” of objects. Also, the GenAI deluge is morphing into a tsunami.
  • See all news ...