Vedant Khandelwal

Vedant Khandelwal

Ph.D. candidate in Computer Science at the University of South Carolina

Posts by Collection

portfolio

publications

“Is depression related to cannabis?”: A knowledge-infused model for entity and relation extraction with limited Supervision

Published in AAAI 2021 Spring Symposium on Combining Machine Learning and Knowledge Engineering (AAAI-MAKE), 2021

A knowledge-infused relation extraction model combining ontology guidance, GPT-3 embeddings, and contrastive learning under limited supervision.

Recommended citation: Kaushik Roy, Usha Lokala, Vedant Khandelwal, and Amit Sheth. (2021). "Is depression related to cannabis?: A knowledge-infused model for entity and relation extraction with limited Supervision." Proceedings of the AAAI 2021 Spring Symposium on Combining Machine Learning and Knowledge Engineering (AAAI-MAKE 2021).
Download Paper

Explainable Pathfinding for Inscrutable Planners with Inductive Logic Programming

Published in ICAPS 2022 Workshop on Explainable AI Planning, 2022

An ILP-driven explainable pathfinding framework that summarizes solutions across all problem instances using an explainable pathfinding graph.

Recommended citation: Forest Agostinelli, Rojina Panta, Vedant Khandelwal, Biplav Srivastava, Bharath Chandra Muppasani, Kausik Lakkaraju, and Dezhi Wu. (2022). "Explainable Pathfinding for Inscrutable Planners with Inductive Logic Programming." ICAPS 2022 Workshop on Explainable AI Planning.
Download Paper

ALLURE: A Multi-Modal Guided Environment for Helping Children Learn to Solve a Rubik’s Cube with Automatic Solving and Interactive Explanations

Published in Proceedings of the AAAI Conference on Artificial Intelligence, 2022

ALLURE combines automatic Rubik’s Cube solving with interactive, human-understandable explanations for child-centered learning.

Recommended citation: Kausik Lakkaraju, Thahimum Hassan, Vedant Khandelwal, Prathamjeet Singh, Cassidy Bradley, Ronak Shah, Forest Agostinelli, Biplav Srivastava, and Dezhi Wu. (2022). "ALLURE: A Multi-Modal Guided Environment for Helping Children Learn to Solve a Rubik's Cube with Automatic Solving and Interactive Explanations." Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 11, pp. 13185-13187.
Download Paper

Demo Alleviate: Demonstrating Artificial Intelligence Enabled Virtual Assistance for Telehealth: The Mental Health Case

Published in Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-23 Demo Track), 2023

Alleviate is a safety-constrained telehealth mental-health assistant that combines personalized patient knowledge graphs with explainable feedback loops.

Recommended citation: Kaushik Roy, Vedant Khandelwal, Raxit Goswami, Nathan Dolbir, Jinendra Malekar, and Amit Sheth. (2023). "Demo Alleviate: Demonstrating Artificial Intelligence Enabled Virtual Assistance for Telehealth: The Mental Health Case." Proceedings of the AAAI Conference on Artificial Intelligence 37(13): 16289-16290.
Download Paper

GEAR-Up: Generative AI and External Knowledge-based Retrieval Upgrading Scholarly Article Searches for Systematic Reviews

Published in Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

A modular pipeline that combines generative AI and external knowledge retrieval to improve systematic review query construction.

Recommended citation: Kaushik Roy, Vedant Khandelwal, Harshul Surana, Valerie Vera, Amit Sheth, and Heather Heckman. (2024). "GEAR-Up: Generative AI and External Knowledge-based Retrieval Upgrading Scholarly Article Searches for Systematic Reviews." Proceedings of the AAAI Conference on Artificial Intelligence.
Download Paper

Specifying goals to deep neural networks with answer set programming

Published in International Conference on Automated Planning and Scheduling (ICAPS), 2024

Goal-conditioned planning with ASP specifications allows a trained DNN heuristic to solve diverse target goals without retraining.

Recommended citation: Forest Agostinelli, Rojina Panta, and Vedant Khandelwal. (2024). "Specifying goals to deep neural networks with answer set programming." Proceedings of the ICAPS, vol. 34, pp. 2-10.
Download Paper

A Domain-Agnostic Neurosymbolic Approach for Big Social Data Analysis: Evaluating Mental Health Sentiment on Social Media during COVID-19

Published in IEEE International Conference on Big Data, 2024

A domain-agnostic neurosymbolic pipeline for large-scale COVID-era mental health sentiment analysis across depression, addiction, and anxiety.

Recommended citation: Vedant Khandelwal, Manas Gaur, Ugur Kursuncu, Valerie Shalin, and Amit Sheth. (2024). "A Domain-Agnostic Neurosymbolic Approach for Big Social Data Analysis: Evaluating Mental Health Sentiment on Social Media during COVID-19." Proceedings of the IEEE International Conference on Big Data.
Download Paper | Download Slides

A Neurosymbolic Fast and Slow Architecture for Graph Coloring

Published in Twelfth Annual Conference on Advances in Cognitive Systems (ACS), 2025

SOFAI-v2 combines fast LLM proposals with metacognitive verification and symbolic fallback for reliable graph coloring.

Recommended citation: Vedant Khandelwal, Vishal Pallagani, Biplav Srivastava, and Francesca Rossi. (2025). "A Neurosymbolic Fast and Slow Architecture for Graph Coloring." Twelfth Annual Conference on Advances in Cognitive Systems (ACS).
Download Paper | Download Slides

AI-Augmented Search for Systematic Reviews: A Comparative Analysis

Published in Proceedings of the Association for Information Science and Technology (ASIS&T), 2025

A comparative analysis of AI-augmented search methods for systematic reviews published in ASIS&T proceedings.

Recommended citation: Valerie Vera*, Vedant Khandelwal*, Kaushik Roy, Ritvik Garimella, Harshul Surana, and Amit Sheth. (2025). "AI-Augmented Search for Systematic Reviews: A Comparative Analysis." Proceedings of the Association for Information Science and Technology 62, no. 1: 705-717. (* Equal contribution)
Download Paper

NeuroSymbolic Knowledge-Grounded Planning and Reasoning in Artificial Intelligence Systems

Published in IEEE Intelligent Systems, 2025

A neurosymbolic framework for knowledge-grounded, constraint-aware planning and reasoning in high-stakes AI decision support.

Recommended citation: Amit Sheth, Vedant Khandelwal, Kaushik Roy, Vishal Pallagani, and Megha Chakraborty. (2025). "NeuroSymbolic Knowledge-Grounded Planning and Reasoning in Artificial Intelligence Systems." IEEE Intelligent Systems, pp. 27-34.
Download Paper

PDDLFuse: A Tool for Generating Diverse Planning Domains

Published in GenPlan Workshop, AAAI 2025, 2025

Generating solvable and structurally diverse planning domains with probabilistic PDDL fusion.

Recommended citation: Vedant Khandelwal, Amit Sheth, and Forest Agostinelli. (2025). "PDDLFuse: A Tool for Generating Diverse Planning Domains." GenPlan Workshop, AAAI 2025.
Download Paper

NeuroLit Navigator: A Neurosymbolic Approach to Scholarly Article Searches for Systematic Reviews

Published in arXiv preprint arXiv:2503.00278, 2025

A neurosymbolic retrieval pipeline for faster, reproducible first-iteration search in systematic reviews.

Recommended citation: Vedant Khandelwal, Kaushik Roy, Valerie Lookingbill, Ritvik Garimella, Harshul Surana, Heather Heckman, and Amit Sheth. (2025). "NeuroLit Navigator: A Neurosymbolic Approach to Scholarly Article Searches for Systematic Reviews." arXiv preprint arXiv:2503.00278.
Download Paper

Inductive Logic Programming for Heuristic Search

Published in Accepted at both IJCLR 2025 (5th International Joint Conference on Learning & Reasoning) and the ICAPS 2025 Workshop on Planning and Reinforcement Learning (PRL), 2025

Learning explainable cost-to-go heuristics directly as logic programs for efficient A* search.

Recommended citation: Rojina Panta*, Vedant Khandelwal*, Celeste Veronese, Amit Sheth, Daniele Meli, and Forest Agostinelli. (2025). "Inductive Logic Programming for Heuristic Search." Accepted at both IJCLR 2025 (5th International Joint Conference on Learning & Reasoning) and the ICAPS 2025 Workshop on Planning and Reinforcement Learning (PRL). (* Equal contribution)
Download Paper | Download Slides

Language Models Coupled with Metacognition Can Outperform Reasoning Models

Published in arXiv preprint arXiv:2508.17959 (under review at ICML 2026), 2025

Demonstrating that language models enhanced with metacognitive capabilities can outperform traditional reasoning models.

Recommended citation: Vedant Khandelwal, Francesca Rossi, Keerthiram Murugesan, Erik Miehling, Murray Campbell, Karthikeyan Natesan Ramamurthy, and Lior Horesh. (2025). "Language Models Coupled with Metacognition Can Outperform Reasoning Models." arXiv preprint arXiv:2508.17959 (under review at ICML 2026).
Download Paper

Top-K Gated Macro-Actions for Neural Heuristic Search

Published in Under review at SOCS 2026, 2026

Top-K gating bounds macro branching in neural heuristic search while preserving completeness and reducing node expansions.

Recommended citation: Vedant Khandelwal et al. (2026). "Top-K Gated Macro-Actions for Neural Heuristic Search." Under review at SOCS 2026.

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.