I’m a Ph.D. student in Computer Science at Georgia Tech, where I am fortunate to be advised by Prof. Judy Hoffman.
Recent Projects
- World Models (WFM): Developing VLM-based benchmarks for automatic evaluation of world models.
- 7B Open-Source VLM: Open-vocabulary 3D scene graph generation (under review).
- SkyScenes: Synthetic aerial dataset for real-world segmentation (ECCV 2024).
- Generalist Multimodal LLM: Jointly-trained vision-audio model that reduces cross-modal interference and outperforms larger models.
My research advances vision-language models (VLMs) by extending their capabilities across modalities, spatial reasoning, and evaluation—integrating audio, enhancing spatial understanding, and enabling automatic evaluation of world models for robotic manipulation. I have also worked on syn-to-real transfer and domain generalization.
💼 I'm currently seeking research internships for Summer 2026 — feel free to reach out if you're hiring!
📝 Recent Updates [ 🌟: Highlight | 💡: Research | 📆: Misc ]
- 🌟 Attending CVPR 2025 in Nashville!
- 🌟 Attending ECCV 2024 in Milan, Italy!
Georgia Tech published an article about our work. - 💡 Jul 1, 2024: My first first-author paper — SkyScenes: A Synthetic Dataset for Aerial Scene Understanding — accepted at ECCV 2024!
View more
- 🌟 Apr 1, 2024: Joining Georgia Tech for Ph.D. CS under Prof. Judy Hoffman (Fall 2024).
- 📆 Mar 12, 2024: Serving as a reviewer for ECCV 2024.
- 💡 Oct 24, 2023: My first main-conference paper — LatentDR: Improving Model Generalization Through Sample-Aware Latent Degradation and Restoration — accepted at WACV 2024!
- 🌟 Attended NeurIPS 2022 in New Orleans, LA, USA (my first in-person conference!).
- 🌟 Apr 4, 2022: Admitted to the MS CS program at Georgia Tech for Fall 2022!
📚 Publications
2024
ECCV 2024 (First first-author paper!)
SkyScenes: A Synthetic Dataset for Aerial Scene Understanding
Sahil Khose*, Anisha Pal*, Aayushi Agarwal*, Deepanshi*, Judy Hoffman, Prithvijit Chattopadhyay
Sahil Khose*, Anisha Pal*, Aayushi Agarwal*, Deepanshi*, Judy Hoffman, Prithvijit Chattopadhyay
WACV 2024 (First main-conference paper!)
LatentDR: Improving Model Generalization Through Sample-Aware Latent Degradation and Restoration
Ran Liu, Sahil Khose, Jingyun Xiao, Lakshmi Sathidevi, Keerthan Ramnath, Zsolt Kira, Eva L. Dyer
Ran Liu, Sahil Khose, Jingyun Xiao, Lakshmi Sathidevi, Keerthan Ramnath, Zsolt Kira, Eva L. Dyer
2022
NeurIPS 2022 (First in-person conference!)
- Poster: Continual VQA for Disaster Response Systems at CCAI
ICML 2022 (Best Paper Award 🌟)
ACL 2022
2021
NeurIPS 2021
- Spotlight Paper 🌟: Semi-Supervised Classification and Segmentation on High Resolution Aerial Images at CCAI
- XCI-Sketch: Extraction of Color Information from Images for Generation of Colored Outlines and Sketches
Presented at: New in ML (Oral), CtrlGen, ML4CD, and DGM - Poster: A Studious Approach to Semi-Supervised Learning at ICBINB