| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Sat, 13 Sep 2025 14:31:46 GMT
access-control-allow-origin: *
etag: W/"68c58052-23a3"
expires: Mon, 29 Dec 2025 20:24:34 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: BD54:21D6A4:95C5AE:A7D80A:6952E12A
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 20:14:35 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210098-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767039275.844737,VS0,VE202
vary: Accept-Encoding
x-fastly-request-id: b5858d23020419aeed5dd0c8d74b6609a798c65e
content-length: 2521
Marcos Treviso
Marcos Treviso
Assistant Professor at Instituto Superior Técnico, University of Lisbon.
I work on Machine Learning ∩ Natural Language Processing with interests in efficiency and explainability.
Publications
For an up-to-date list, please see my Google Scholar profile.
Some Projects
Linear-chain CRF in PyTorch
Reference implementation and tutorial.
entmax-demo
Interactive demos of α-entmax.
arr-report-generator
Generate reports from ARR data.
cluster-scope
Utilities for cluster exploration.
PyTorch Lecture (Tensor Puzzles)
With Sasha Rush — puzzles and notebooks.
triton-tutorial
Hands-on Triton kernels for efficiency.