Sanket Kalwar

I am currently working as a graduate research assistant at the Robotics Research Center at IIIT Hyderabad, under the guidance of Prof. K Madhava from IIIT Hyderabad and external advisor Dr. Sourav Garg from The University of Adelaide, and Prof. Srinath Sridhar from Brown University .

At RRC, I have actively contributed to projects focused on enhancing 2D scene and video understanding along with 3D robotics perception. My work encompasses areas such as object detection, segmentation, and tracking. I am dedicated to advancing the field by infusing machines with visual intelligence, a goal that inspires my research endeavors.

Email / CV / Scholar / Twitter / Github

Research

I'm interested in computer vision, robotic perception, deep-learning and representation-learning.

	AMT-Hyp : Adversarial Multi-Task Reinforcement Learning Framework for Policy Generation using Hypernetworks Sanket Kalwar, Jayaram Reddy, Brojeshwar Bhowmick, Arun Singh, K Madhava Krishna project page / code Under Review!
	DiffPrompter: Differentiable Implicit Visual Prompts for Object-Segmentation in Adverse Conditions Sanket Kalwar, Mihir Ungarala, Shruti Jain, Aaron Monis, Krishna Reddy Konda, Sourav Garg, K Madhava Krishna* project page / code IROS 2024, Abu Dhabi (Oral Pitch!)
	Constrained 6-DoF Grasp Generation on Complex Shapes for Improved Dual-Arm Manipulation Gaurav Singh, Sanket Kalwar, Md Faizal Karim, Bipasha Sen, Nagamanikandan Govindan, Srinath Sridhar, K Madhava Krishna project page / code IROS 2024, Abu Dhabi (Oral Pitch!)
	GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions Sanket Kalwar, Dhruv Patel, Aakash Aanegola, Krishna Reddy Konda, Sourav Garg, K Madhava Krishna project page/ code ICRA 2023, London
	LatentGAN Autoencoder: Learning Disentangled Latent Distribution Sanket Kalwar, Animikh Aich, Tanay Dixit arXiv, 2022

Projects

Prompt-to-Binary Executable: End-to-End Neural Compilation
Sanket Kalwar
project page / code
An experimental framework that fine-tunes large language models to act as direct prompt-to-binary compilers. It synthesizes stripped, executable ELF64 machine code directly as raw hexadecimal strings under strict -nostdlib constraints, bypassing the traditional high-level code, assembly, and linking toolchain.

Education

	International Institute of Information Technology, Hyderabad MS student in Computer Science 2022-present*
	Savitribai Phule Pune University B.Eng. in Computer Science and Engineering 2014-2018

Work Experience

	Robotics Research Center at IIIT, Hyderabad Research Assistant 2022-2023
	Wobot Intelligence (Wobot.ai), New Delhi, India Senior Computer Vision Engineer 2020-2022
	Jekson Vision, Gujarat Deep-learning Lead 2019-2020
	Yantra AI Tech, Pune Computer Vision Engineer 2018-2019