Akshay Raman

I’m a researcher at Columbia University’s AI4VS Lab, working under the supervision of Prof. Kaveri Thakoor. I received my master’s from NYU Courant and bachelor’s from VIT, India.

My research focuses on self-supervised and multimodal approaches for longitudinal and video data. My broader interests include representation learning, multimodality, and AI4Science.

Previously, I have 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.

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).

Easel - 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.