cv
Education
- 2024 - 2026 (Expected)
MS in Computer Science
University of California San Diego
- Specialization: Artificial Intelligence and Machine Learning
- GPA: 4.0/4.0
- 2019 - 2023
B.Tech in Aerospace Engineering, Minor in Machine Learning
Indian Institute of Technology Kanpur
- CPI: 8.9/10
Research Experience
- Jan 2025 - Present
Research Intern
Professor Zhuowen Tu
- Developing a novel curriculum learning strategy to enforce layout-based controllability in diffusion models enabling developement of controlled generative models.
- June 2024 - Dec 2024
Research Intern
Professor Hao Su
- Introduced a dual-encoder VLA architecture with a language-aligned action tokenizer that preserves pretrained VLM features, boosting generalization and increasing task success by 40% over SOTA baselines.
- Feb 2024 - June 2024
Research Intern
Professor Yogesh Rawat and Vibhav Vineet
- Created the CosPlan benchmark for corrective sequential planning and proposed the Scene Graph Incremental (SGI) update method, a novel training-free technique that improves error correction by 5.2%.
- July 2023 - Feb 2024
Research Intern
Professor Yogesh Rawat and Vibhav Vineet
- Proposed the Dream of Thoughts (DoT) prompting technique, a novel multi-step reasoning approach that navigates model hallucinations to significantly improve the understanding of activity transitions.
- July 2023 - Feb 2024
Research Intern
Professor Yogesh Rawat and Vibhav Vineet
- Designed the CTx-Net compositional architecture for robust video understanding and introduced three benchmark datasets to systematically study and evaluate model performance under occlusion.
Publications
- Under Review
Enhancing Generalization in VLA Models by Preserving Pretrained Representations
- S. Grover, A. Gopalkrishnan, B. Ai, H. I. Christensen, H. Su, X. Li
- Under Review
Navigating Hallucinations for Reasoning of Unintentional Activities
- S. Grover, V. Vineet, Y. S. Rawat
- Under Review
CosPlan: A Benchmark for Corrective Sequential Planning
- S. Grover, V. Vineet, Y. S. Rawat
- NeurIPS 2023
Revealing the Unseen: Benchmarking Video Action Recognition under Occlusion
- S. Grover, V. Vineet, Y. S. Rawat
Skills
-
Languages
- Python (Advanced)
- C++ (Proficient)
- Julia (Familiar)
- SQL
-
Libraries
- PyTorch
- JAX
- NumPy
- Pandas
- TensorFlow
- Scikit-learn
-
HPC/Distributed
- CUDA
- PyTorch FSDP
- Kubernetes
- Docker
- Slurm
Honors and Awards
- 2023
- B.Tech Degree with Distinction (Mathematics & Computing), IIT Kanpur
- 2022
- Academic Excellence Award, IIT Kanpur
Academic Service
- Reviewer: NeurIPS 2025