Scholar

Kurt Keutzer

Google Scholar ID: ID9QePIAAAAJ

Professor of the Graduate School, EECS, University of California, Berkeley

artificial intelligence systemsdeep learningefficient computation

Homepage↗Google Scholar↗

Citations & Impact

All-time

Citations

44,253

H-index

i10-index

203

Publications

Co-authors

list available

Contact

No contact links provided.

Publications

55 items

LLM Inference in a Flash!

2026

Cited

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

2026

Cited

SEED: Targeted Data Selection by Weighted Independent Set

2026

Cited

Building Interactive Real-Time Agents with Asynchronous I/O and Speculative Tool Calling

2026

Cited

Learning, Fast and Slow: Towards LLMs That Adapt Continually

2026

Cited

Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment

2026

Cited

LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models

2026

Cited

Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution

2026

Cited

Resume (English only)

Co-authors

46 total

Amir Gholami

Research Scientist, University of California, Berkeley

Srinivas Devadas

Edwin Sibley Webster Professor of Electrical Engineering and Computer Science, MIT

Michael Mahoney

Professor of Statistics, UC Berkeley

Zhen Dong

NVIDIA Nemotron, AP at UCSB, Berkeley AI PhD