Nithin Sivakumaran

Nithin Sivakumaran

I am a 4th year undergraduate student majoring in Computer Science and Economics with a minor in Statistics at UNC Chapel Hill. I work in the MURGe Lab where I am mentored by Prof. Mohit Bansal and Prof. Elias Stengel-Eskin. I am currently seeking PhD programs for Fall 2026.

My research focuses on building collaborative multimodal AI systems for monitorable LLM reasoning. Additionally, I am interested in using post-training methods for LLMs to improve interpretability.

🔥 News

  • 2026.04:  🎉🎉 Honored to receive the NSF Graduate Research Fellowship!
  • 2026.02:  🎉🎉 New preprint “Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution” on a new training framework to improve faithfulness within LLMs.
  • 2026.01:  🎉🎉 Our paper “DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning” was accepted to EACL 2026 main!
  • 2025.12:  🎉🎉 Honored to receive an Honorable Mention for the CRA Outstanding Undergraduate Research Award.
  • 2025.12:  🎉🎉 New preprint “Movie Facts and Fibs (MF^2): A Benchmark for Long Movie Understanding” introducing a benchmark for narrative understanding of long open-domain movies.

📝 Publications

Preprint
sym

Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution

Nithin Sivakumaran, Shoubin Yu, Hyunji Lee, Yue Zhang, Ali Payani, Mohit Bansal, Elias Stengel-Eskin.

Code

  • We propose REMuL, a training framework that improves faithfulness by incentivizing a speaker model to produce reasoning that is executable by a set of listener models
EACL 2026
sym

DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning

Nithin Sivakumaran, Justin Chih-Yao Chen, David Wan, Yue Zhang, Jaehong Yoon, Elias Stengel-Eskin, Mohit Bansal.

Code

  • We propose DART, a multi-agent multimodal debate framework that uses disagreement between VLM agents to address visual uncertainty
ICMI 2025
sym

A Multimodal Classroom Video Question-Answering Framework for Automated Understanding of Collaborative Learning

Nithin Sivakumaran, Chia-Yu Yang, Abhay Zala*, Shoubin Yu, Daeun Hong, Xiaotian Zou, Elias Stengel-Eskin, Dan Carpenter, Wookhee Min, Cindy Hmelo-Silver, Jonathan Rowe, James Lester, Mohit Bansal.

Code

  • We propose EngageVP, a new mutimodal video QA framework for stronger understanding of student engagement and behavior in classroom videos
Preprint
sym

Movie Facts and Fibs (MF^2): A Benchmark for Long Movie Understanding

Emmanouil Zaranis, António Farinhas, Saul Santos, Beatriz Canaverde,…Nithin Sivakumaran, et al.

Code

  • We propose MF2, a new benchmark for evaluating whether models can comprehend, consolidate, and recall key narrative information from full-length movies

💻 Experience