← Search

Subhojyoti Khastagir

3 accepted papers

2025

LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation

NeurIPS 2025poster

Recent advances in generative modeling have shown significant promise in designing novel periodic crystal structures. Existing approaches typically rely on either large language models (LLMs) or equivariant denoising models, each with complementary strengths: LLMs excel at handling discrete atomic t…

Cited by 0SourcecodeScholar
2025

Periodic Materials Generation using Text-Guided Joint Diffusion Model

ICLR 2025poster

Equivariant diffusion models have emerged as the prevailing approach for generat- ing novel crystal materials due to their ability to leverage the physical symmetries of periodic material structures. However, current models do not effectively learn the joint distribution of atom types, fractional co…

2023

Off-Policy Average Reward Actor-Critic with Deterministic Policy Search

ICML 2023poster

The average reward criterion is relatively less studied as most existing works in the Reinforcement Learning literature consider the discounted reward criterion. There are few recent works that present on-policy average reward actor-critic algorithms, but average reward off-policy actor-critic is re…

Cited by 11SourcePDFScholar