Reza Shirkavand

Catalog-Native LLM: Speaking Item-ID dialect with Less Entanglement for Recommendation

Pruning Without Fine-Tuning: Dynamic Pruning of Autoregressive Image Generation Models to Mixtures of Experts

Cost-Aware Contrastive Routing for LLMs

Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training

Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models

Bilevel ZOFO: Bridging Parameter-Efficient and Zeroth-Order Techniques for Efficient LLM Fine-Tuning and Meta-Training

From Pixels to Prose: A Large Dataset of Dense Image Captions