Akshay Raman
MSc in Computer Science | New York University, Courant Institute
Hi! I’m Akshay, a computer science graduate from New York University and a researcher at the AI4VS Lab at Columbia University, working under the supervision of Prof. Kaveri Thakoor.
My research focuses on multimodal learning approaches that integrate eye-tracking data to improve predictive performance. My broader interests include reinforcement learning, representation learning, and scientific applications of AI.
I have also collaborated with researchers at the DICE Lab at NYU and the AI4Science Group at the University of Ottawa. You can find my full CV here.
In my spare time, I enjoy music, running, and reading.
News
| May 15, 2025 | 🎓 Graduated from New York University with a Master’s degree in Computer Science (AI Specialization). |
|---|---|
| Aug 18, 2023 | 🎓 Graduated from Vellore Institute of Technology with a Bachelor’s degree in Computer Science and Engineering. |
| Dec 20, 2022 |  Launched this website! |
Selected Projects
Fine-Tuning Video Diffusion Models for 3D-Consistent Multi-view Generation
Fine-tuned a video diffusion model (SVD) to generate geometrically consistent, multi-view renderings from a single input image. Demonstrated that a curated high-quality 1% subset (10K objects) of the Objaverse dataset achieved performance comparable to full-scale training (1M+ objects).
Canvas - A Modular Deep Learning Project Template Using Pytorch and Hydra
Designed a flexible, modular deep learning project template using pytorch and hydra. Canvas aims to provide a unified template for all kinds of machine learning projects.
Scalable CLIP-based Geolocation via Hierarchical Embedding Search
Developed a CLIP-based geolocation model trained on over 4M+ images from the MediaEval-16 dataset, achieving 70% country-level prediction accuracy. Engineered a novel hierarchical clustering algorithm to accelerate model inference by ~100x, reducing the search space from 100k+ GPS points to ~1k while maintaining competitive accuracy.
Continual Credit Assignment with Eligibility Traces
Masters Capstone Project
Developed an online reinforcement learning algorithm by adapting Generalized Advantage Estimation (GAE) with eligibility traces, eliminating memory-intensive data buffers. Proposed a clipped traces regularization method to solve training instability in the online setting, and applied on MuJoCo and Atari environments.
Solving Optimal Transport using Deep Neural Networks
Project under Prof. Augusto Gerolin, Undergraduate Thesis
Prototyped a deep neural network solver for amortized Wasserstein OT in TensorFlow, accelerating the Sinkhorn algorithm by 2x on MNIST. Simulated atomic dissociation for N-electron systems using an OT solver, predicting potential energy curves within 5% of theoretical values.