Get started
Author

Hossein Entezari Zarch

Observed names: Zarch, Hossein, Zarch, Hossein Entezari
Observed institution: University of Southern California
ORCID: 0000-0002-1976-1534
Observed ORCID: 0000-0002-1976-1534
OpenAlex ID: A5104435472
KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation
2025 · Chaoyi Jiang, Lei Gao, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 4
PDF
PACT: NVFP4 Data-Flow LoRA Fine-Tuning on Consumer GPUs
2026 · Gao, Lei, Zarch, Hossein Entezari, et al. · arXiv (Cornell University)
PDF
ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference
2026 · Ziashahabi, Amir, Zarch, Hossein Entezari, et al. · arXiv (Cornell University)
PDF
HuffmanEmbed: Using Huffman Coding for Embedding Table Compression in Deep Learning Recommendation Models
2026 · Chaoyi Jiang, Abdulla Alshabanah, et al. · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)
DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning
2026 · Association for Computational Linguistics 2026, Annavaram, Murali, et al. · Underline Science Inc.
MARché: Fast Masked Autoregressive Image Generation with Cache-Aware Attention
2026 · Chaoyi Jiang, Sungwoo Kim, et al. · Lecture notes in computer science
PDF
DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning
2026 · Hossein Entezari Zarch, Lei Gao, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
Striking the Right Balance between Compute and Copy: Improving LLM Inferencing Under Speculative Decoding
2025 · Ramachandran, Arun, Govindarajan, Ramaswamy, et al. · arXiv (Cornell University)
PDF
DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing
2025 · Gao, Lei, Jiang, Chaoyi, et al. · arXiv (Cornell University)
PDF
DEL: Context-Aware Dynamic Exit Layer for Efficient Self-Speculative Decoding
2025 · Zarch, Hossein Entezari, Gao, Lei, et al. · arXiv (Cornell University)
PDF
CADC: Encoding User-Item Interactions for Compressing Recommendation Model Training Data
2024 · Zarch, Hossein Entezari, Alshabanah, Abdulla, et al. · arXiv (Cornell University)
PDF
Works count: 12
Citation count: 4
H-index: 1
I10-index:
Year
Topic
Type