Author

Ali Hashemi

Observed name: Hashemi, Ali

Institutions: Multiverse Computing (Spain), Berlin Institute for the Foundations of Learning and Data, Technische Universität Berlin

Observed institutions: Multiverse Computing (Spain), Berlin Institute for the Foundations of Learning and Data, Technische Universität Berlin

OpenAlex ID: A5144412958

LLM Compression by Block Removal with Constrained Binary Optimization

2026 · Jansen, David, Rausch, Roman, et al. · arXiv (Cornell University) · 5

Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss

2026 · Ryskulov, Bakbergen, García-Ferrero, Iker, et al. · arXiv (Cornell University) · 4

Distilling Lightweight Domain Experts from Large ML Models by Identifying Relevant Subspaces

2026 · Chormai, Pattarawat, Hashemi, Ali, et al. · arXiv (Cornell University) · 1

Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs

2026 · Ryskulov, Bakbergen, García-Ferrero, Iker, et al. · arXiv (Cornell University)

Block removal for large language models through constrained binary optimization

2026 · Jansen, David, Rausch, Roman, et al. · Zenodo (CERN European Organization for Nuclear Research)

Works count: 5

Citation count: 10

H-index: 2

I10-index: