Akshay Manglik

Bio

I am a senior at Columbia University, majoring in Computer Science and Economics and minoring in Math. I am a Laidlaw Scholar and a Data Science Institute Scholar.

I am interested in studying reasoning, robustness, and grounding in language models, especially through expanding test-time compute, devising alternative metrics and training objectives, and integrating symbolic systems.

My past research experiences have spanned natural language processing, computer vision, neuroimaging, computational genomics, and protein structure prediction. I have conducted research at:

• the Dynamic Perception and Memory Lab at Columbia, under Prof. Chris Baldassano and Jiawen Huang;
• the AlQuraishi Lab at Columbia under Prof. Mohammed AlQuraishi and Dr. Nazim Bouatta;
• the Johns Hopkins Applied Physics Lab, under Dr. Vince Pulido and Dr. Benjamin Skerritt-Davis;
• the Schrauwen Lab at Columbia Medical Center, under Prof. Isabelle Schrauwen;
• the Quantitative Imaging and AI Lab at Stanford, under Prof. Daniel Rubin and Dr. Hersh Sagreiya.

Research Interests

I aim to develop AI systems that reason reliably and ground their knowledge, particularly in novel situations. While large language models (LLMs) memorize vast amounts during pretraining, they struggle to apply knowledge in novel, "long tail" scenarios and lack mechanisms for factuality. These challenges of reasoning and grounding are deeply interconnected: better reasoning improves factuality, while better grounding enables reasoning with less information. I am interested in how multi-agent dynamics can encourage reliable reasoning, especially under limited information, drawing on my background in economics, debate, and philosophy. My research interests span three areas:

1. Test-Time Exploration: Developing sample-efficient, scalable techniques beyond sampling and search, like injecting schema, finetuning at test time, and incorporating cooperative and competitive multi-agent dynamics into decoding.
2. Learning from Rich Feedback: Creating robust metrics for assessing factuality and causality in reasoning, and developing sample-efficient training objectives for sparsely-observed tasks.
3. Neuro-symbolic Integration: Incorporating symbolic reasoning and tool use to ground model outputs and ensure robustness in novel, sample-constrained situations.

CV

Full CV in PDF.

Publications

Most recent publications on Google Scholar.
^‡ denotes equal contribution.

• All

Website Design