Bilge Acun
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4Gecko: An Efficient Neural Architecture Inherently Processing Sequences with Arbitrary Lengths
arXiv 2026
CHAI: Clustered Head Attention for Efficient LLM Inference
arXiv 2024
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
arXiv 2024
DataPerf: Benchmarks for Data-Centric AI Development
dataperf-benchmarks-for-data-centric-ai
Affiliations
No known affiliations.
Frequent co-authors
10from 4 papers