Amir Yazdanbakhsh
- Papers
- 7
Cite
Notes
Only stored in your browser.
7papers
Authored papers
7ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution
arXiv 2026
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
arXiv 2025
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
arXiv 2024
When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
arXiv 2024
SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs
arXiv 2024
Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
arXiv 2024
Learning Performance-Improving Code Edits
arXiv 2023
Affiliations
No known affiliations.
Frequent co-authors
10from 7 papers