Generative AI & Large Language Models

Making language models more reliable and more data-efficient — from agentic systems and memory management for multi-agent setups, to alignment that needs less human feedback, to retrieval and multimodal reasoning over text, image, and tabular data.

Related Publications

ICLR 2026 Open source QAFD-RAG: Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees
Accepted at the International Conference on Learning Representations (ICLR), 2026

The first principled flow diffusion for graph-based retrieval-augmented generation, with online query-aware edge reweighting, exponential convergence guarantees, and state-of-the-art results across multiple benchmarks. Open sourced, with code and models released.

BigData 2025 PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning
IEEE International Conference on Big Data (BigData), 2025

Combines partial-match rewards with verbal reinforcement learning so text-to-SQL models get useful learning signal from near-correct queries rather than only exact matches.

ICML 2024 Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation
International Conference on Machine Learning (ICML), 2024

Defines an Uncertainty-aware Reward Model (URM) for preference training of LLMs, using a Bayesian approximation to quantify the uncertainty of paired responses. URM-based fine-tuning boosts instruction-following capability and policy optimization objectives, surpassing existing methods by a large margin on benchmarks such as Vicuna and MT-Bench.

Full publication list on Google Scholar →

Project Highlights

Agentic Models & Multi-Agent Systems

Agent design and memory management for multi-agent systems (MAS), addressing how agents retain, share, and retrieve context across long-running collaborative tasks.

Data-Efficient LLM Alignment

Alignment and fine-tuning techniques that reach strong instruction-following performance with substantially less human feedback, built on uncertainty-aware reward modeling.

Retrieval-Augmented Generation

RAG architectures for knowledge-intensive tasks, including graph-based retrieval with formal guarantees on which evidence a query recovers.

Text-to-SQL Generation

Reinforcement learning for structured query generation, using partial-match rewards and verbal feedback to make training signal denser and more informative.

Multimodal LLMs

Language models tailored to text, image, and tabular data, supporting business and engineering workflows where the inputs are rarely text alone.