Sahil Khose

AI Researcher

Atlanta, Georgia, United States12 yrs 3 mos experience

Most Likely To SwitchAI Enabled

Key Highlights

Developed a 7B open-source VLM for 3D scene graph generation.
Designed a vision-audio model outperforming larger systems.
Mentored 50 students in advanced machine learning techniques.

Stackforce AI infers this person is a Computer Vision and AI Researcher with a focus on multimodal models.

Contact

sahil.khose@gatech.edu LinkedIn

Skills

Other Skills

Artificial Intelligence (AI)C (Programming Language)Deep LearningMachine LearningNatural Language Processing (NLP)PyTorchPython (Programming Language)

About

I'm a Ph.D. student in Computer Science at Georgia Tech, where I'm fortunate to be advised by Prof. Judy Hoffman. My research focuses on developing multimodal vision-language models that integrate spatial, semantic, and temporal reasoning with minimal supervision. Recent work includes: 1. A 7B open-source VLM for open-vocabulary 3D scene graph generation. 2. SkyScenes, a synthetic aerial dataset for improving real-world segmentation, accepted at ECCV 2024. 3. A generalist multimodal LLM, where I designed a jointly-trained vision-audio model that outperforms larger generalist systems by reducing cross-modal interference. I bring prior experience in domain generalization, zero-shot learning, and synthetic-to-real adaptation, focusing on making models robust to diversity, correlation, and semantic shifts in real-world environments. My goal is to build generalizable systems that require minimal labeled data yet remain reliable under distribution shifts. I also review for top conferences (NeurIPS, CVPR, ECCV) and have published across both vision and language communities. 💼 I'm currently looking for research internships for Summer 2026 — feel free to reach out if you're hiring! Website: https://sahilkhose.github.io/

Experience

Georgia institute of technology

3 roles

Doctoral Student

Aug 2024 – Present · 1 yr 7 mos

Advised by Prof. Judy Hoffman

Graduate Teaching Assistant

Aug 2023 – Dec 2023 · 4 mos

Instructor: Prof. Judy Hoffman
Course: CS 7647 Machine Learning with Limited Supervision
Mentored 50 students to apply and advance state-of-the-art techniques for learning from visual data with limited human supervision, overseeing 12 research projects.

Graduate Research Assistant

Jan 2023 – Present · 3 yrs 2 mos

Advisor: Prof. Judy Hoffman
Research
📝 [ECCV 2024] SkyScenes: A Synthetic Dataset for Aerial Scene Understanding
Addressing the syn-to-real gap and developing DG/DA algorithms for aerial imagery and exploring the impact of viewpoint variability on syn-to-real performance a facet of aerial imagery research that is unexplored.
Spearheaded the generation of a synthetic aerial imagery dataset with varying weather, daytime, height, and pitch variations using the CARLA simulator and studying the effects of domain shift due to varying semantic conditions.

Fruitpunch ai hyderabad

AI Expertise Head

Aug 2021 – Jul 2022 · 11 mos · Hyderabad, Telangana, India

Established the first international chapter of FruitPunch AI, a non-profit organization headquartered in Europe. Engaged in building the community and promoting AI for social good initiatives

Indian institute of science (iisc)

Research Intern

Jul 2021 – Jul 2022 · 1 yr · Bengaluru, Karnataka, India

Advisors: Prof. Suresh Sundaram and Dr. Chandan Gautam
Conducted my BTech thesis.
Worked under Prof. Suresh Sundaram and Dr. Chandan Gautam in the domain of Continual Zero-Shot Learning at the Artificial Intelligence and Robotics Lab

Research society mit manipal

2 roles

Research Mentor

Promoted

Jun 2021 – Jan 2023 · 1 yr 7 mos

Actively involved in the mentorship and guidance of undergraduate students to work on research projects in the various domains of computer science, primarily in artificial intelligence and computer vision.
Research
📝 [🏆 Spotlight Paper, NeurIPS-W 2021] Semi-Supervised Classification & Segmentation on High Resolution Aerial Images
📝 [📢 Oral | NeurIPS-W 2021] XCI-Sketch: Extraction of Color Information from Images for Generation of Colored Outlines and Sketches
📝 [NeurIPS-W 2021] A Studious Approach to Semi-Supervised Learning

AI Division Member

Nov 2020 – Jun 2021 · 7 mos

Manipal institute of technology

Medical AI Research Assistant

Apr 2021 – Oct 2022 · 1 yr 6 mos

Advisor: Prof. Harish Kumar J. R.
Research
📝 [IEEE INDICON 2023] Explainable Classification of Macular Degeneration Using Deep Learning
📝 [IEEE INDICON 2023] Fovea Segmentation Using Semi-Supervised Learning
Worked under the supervision of Prof. Harish Kumar J. R. on deep learning approaches to solve problem statements in the field of ophthalmology and health care.

Project manas

AI Perception Developer

Feb 2019 – Apr 2021 · 2 yrs 2 mos

Part of the Perception subdivision under Project MANAS, Manipal.
📝 [🏆 Top Performer Award | NAACL-W 2021] BERT based Transformers lead the way in Extraction of Health Information from Social Media
Achievements
🏆 World Rank 1 at the 27th Intelligent Ground Vehicle Competition 2019 (IGVC 2019)
Emerged as the International Grand Champions of IGVC 2019 which was held at the University of Maryland, USA. Beat prestigious universities such as Georgia Tech, IIT Madras, etc.
🏆 Won the Mahindra $1 Million Mahindra Rise Prize Autonomous Car Challenge
One of the top 13 (out of 153) teams in India to receive an electric car from Mahindra to participate in their 1 million dollar Rize Prize competition. One of the few undergraduate teams to have been selected for the competition.