Vardaan Pahuja
I am a Ph.D. student in CSE at The Ohio State University. I am fortunate to be advised by Prof. Yu Su. I graduated with M.Sc. (thesis track) in Computer Science from Université de Montréal (affiliated with MILA). Prior to this, I was working as Software Engineer in IBM India Research Lab., Bangalore. I graduated with Bachelor of Technology (Hons.) from IIT Kharagpur, India, and was awarded the prestigious Institute Silver Medal. I spent three wonderful summers as a research intern at Microsoft Research, Google Brain, and Bosch AI Research.
News
- [Jan 2026] One paper accepted to ICLR 2026.
- [Oct 2025] Recognized as top reviewer at NeurIPS 2025.
- [Oct 2025] Presented Explorer at OSU Graduate Engineering Research Symposium.
- [June 2025] Serving as emergency Area Chair for ACL ARR May 2025.
- [May 2025] My internship work Explorer is accepted to ACL (Findings) 2025.
- [Feb 2025] The preprint for my internship project at Microsoft Research is now available on arXiv [Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents].
- [July 2024] Our work Reviving the Context: Camera Trap Species Classification as Link Prediction on Multimodal Knowledge Graphs has been accepted to CIKM'24.
- [April 2024] Interning at Microsoft Research, Redmond this summer.
- [Aug 2023] Our work A Retrieve-and-Read Framework for Knowledge Graph Link Prediction has been accepted to CIKM'23.
- [June 2023] Our work SalsaBot: Towards a Robust and Generalizable Embodied Agent has been accepted to Embodied AI workshop at CVPR 2023.
- [May 2023] My internship work @ Google Brain is accepted to Transformers for Vision (T4V) workshop, CVPR 2023.
- [Feb 2023] Our team Salsabot has qualified to enter the semifinals of Alexa Prize Simbot Challenge.
- [Oct 2022] Attending Automated Knowledge Base Construction (AKBC) at London, UK.
- [April 2022] Interning at Google Brain this summer.
- [May 2021] Long paper accepted to ACL 2021 (Oral).
- [March 2021] Interning at Bosch AI Research this summer.
Research Interests
My research interests lie in LLM agents, multimodal foundation models, and KB reasoning, with a central focus on the role of structure in modern multimodal machine learning. Broadly, I study how leveraging structure, either inherent (e.g., knowledge graphs) or deliberately synthesized (e.g., web interaction trajectories), can make multimodal systems more robust, generalizable, and interpretable. My work integrates visual signals, language, and structured knowledge to enhance representation and reasoning (ACL'21, CIKM'23, CIKM'24) as well as interactive web environments (ACL (Findings)'25). I also work on computer-use agents and LLM interpretability, including the use of sparse autoencoders to analyze salient latent structure in dense image representations (ICLR'26).
Publications
Automatic Image-Level Morphological Trait Annotation for Organismal Images
[pdf] ICLR 2026
Reviving the Context: Camera Trap Species Classification as Link Prediction on Multimodal Knowledge Graphs
[pdf]
[code]
CIKM 24 (Oral)
[poster] Honourable Mention, OSU CSE Graduate Student Research Poster Exhibition 2024
[short version] CV4Animals workshop, CVPR 24 (Oral)
Fine-Tuning is Fine, if Calibrated
[pdf] NeurIPS 2024
Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data
[pdf] NeurIPS 2023
Knowledge Base Question Answering: A Semantic Parsing Perspective
[pdf] AKBC 2022
Learning a Probabilistic Boolean Network Model from Biological Pathways and Time-series Expression Data
[paper] EMBC 16
SalsaBot: Towards a Robust and Generalizable Embodied Agent
[short version]
Embodied AI Workshop at CVPR 2023
[long version]
Alexa Prize SimBot Challenge Proceedings 2023
Learning Sparse Mixture of Experts for Visual Question Answering
[pdf] Visual Question Answering and Dialog Workshop, CVPR 2019
Tooling framework for instantiating natural language querying system
[pdf] VLDB Endowment 2018
Service
- Area Chair: ARR/EMNLP'25
- Program Committee: NeurIPS'25, AAAI'25, ICCV'25, ACL'25, NAACL'25, CVPR'25, WACV'25, COLM'24, CVPR'24, EMNLP'23, ACL'23, NAACL'22, Transactions on Big Data'24
- Workshops: Workshop on Computer-use Agents (ICML'25), CV4Animals (CVPR'24), Knowledge Augmented Methods for NLP (AAAI'23), Structured and Unstructured Knowledge Integration (NAACL'22)
- Secondary Reviewer: BigData-IT'22, EMNLP'21; SIGKDD'21; ACL'21; SIGKDD'20