Publications
My current research focuses on LLM reasoning, self-improvement, and post-training. Over the years, I have also worked on generative recommender systems, geometric deep learning, bio-inspired optimization, and autonomous agents. Below is a selection of my publications organized by research area.
LLM Reasoning & Alignment
 | Credit Assignment with Resets in Language Model Reasoning |
 | Imbalanced Gradients in RL Post-Training of Multi-Task LLMs |
 | How to Make LLMs Strong Node Classifiers? |
 | Structure Enables Effective Self-Localization of Errors in LLMs |
 | Self-Improvement of Language Models by Post-Training on Multi-Agent Debate |
Generative Recommender Systems
 | Multimodal Generative Recommendation for Fusing Semantic and Collaborative Signals |
 | Generating Long Semantic IDs in Parallel for Recommendation |
 | Billion-Scale Graph Deep Learning Framework for Ads Recommendation |
 | Preference Discerning with LLM-Enhanced Generative Retrieval |
 | Unifying Generative and Dense Retrieval for Sequential Recommendation |
 | Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale |
Geometric Deep Learning
Bio-Inspired Optimization & Control Theory
 | Simulating Collective Intelligence of Bio-Inspired Competing Agents |
 | Multi-Objective Design of State Feedback Controllers Using Reinforced Particle Swarm Optimization |
 | A Case Study on Collective Intelligence Based on Energy Flow |
 | An Incremental Framework for Classification of EEG Signals Using Quantum Particle Swarm Optimization |
 | Optimal Tuning of Linear Quadratic Regulators using Quantum Particle Swarm Optimization |
 | An Incremental Parallel Particle Swarm Approach for Classification Rule Discovery from Dynamic Data |
