Publications
Highlight: Shaded entries are A or A* venues (prestigious and highly selective), per the CORE Computer Science Conference Rankings.
Google Scholar (as of Sep 2026): 288 citations · h-index 8 · i10-index 6.
Peer-Reviewed International Conference Papers
ProofBridge: Auto-Formalization of Natural Language Proofs in Lean via Joint Embeddings
14th International Conference on Learning Representations, Rio de Janeiro, Brazil, 2026. (Acceptance rate: 28%)
Also accepted for presentation (non-archival) at the 9th International Symposium on AI Verification (SAIV 2026) and the Workshop on AI for Mathematics & Computer Science Research (AIMACS), both at the Federated Logic Conference (FLoC 2026), Lisbon, Portugal, 2026, a quadrennial event that brings together leading researchers in logic and computer science.
NeuroSymbolic LLM for Mathematical Reasoning and Software Engineering
33rd International Joint Conference on Artificial Intelligence, Doctoral Consortium, pp. 8492โ93, 2024. (Acceptance rate: 17%)
TENCON 2021
ICDC 2021
CALCON 2020
PReMI 2019
TENSYMP 2019
CALCON 2017
ICAPR 2017
Invited Papers
CICM 2026
Semantic Alignment Models: A Bridge Between Informal and Formal Mathematics
19th Conference on Intelligent Computer Mathematics, Invited Paper, Ljubljana, Slovenia, 2026.
Peer-Reviewed Workshop Papers
NeurIPS 2026
Learning Flexible Context Management Unlocks Test-Time Scaling
Workshop on Long Context Foundation Models (LCFM) @ NeurIPS, Atlanta, USA, 2026.
NeurIPS 2026
On the Off-Policy Teacher in On-Policy Distillation
6th Workshop on Mathematical Reasoning and AI (MATH-AI) @ NeurIPS, Atlanta, USA, 2026.
& Workshop on Transitioning from Pre-Training to Post-Training (Pre-to-Post) @ NeurIPS, Sydney, Australia, 2026.
Journal Papers / Book Chapters
IJCISIM 2022
River Publishers 2022
Springer Nature 2021
Preprints / Under Submission
arXiv 2026
MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution
Preprint · arXiv:2609.38349, 2026.
arXiv 2025
Abstractions-of-Thought: Intermediate Representations for LLM Reasoning in Hardware Design
Preprint ยท arXiv:2505.15873, 2025.
arXiv 2023
Reducing Opinion Echo-Chambers by Intelligent Placement of Moderate-Minded Agents
Preprint ยท arXiv:2304.10745, 2023.