| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://yangalan123.github.io/xlog/
access-control-allow-origin: *
expires: Mon, 29 Dec 2025 22:44:23 GMT
cache-control: max-age=600
x-proxy-cache: MISS
x-github-request-id: 74D4:2118F1:94DE02:A73066:695301E2
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 22:34:23 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210054-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767047664.637449,VS0,VE201
vary: Accept-Encoding
x-fastly-request-id: a1c6071f13d9217539b6c18fcd917baaa6ba3b56
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Wed, 15 Oct 2025 00:29:02 GMT
access-control-allow-origin: *
etag: W/"68eeeace-296d"
expires: Mon, 29 Dec 2025 22:44:23 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 2D15:3A7A40:955D2F:A7B14A:695301EF
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 22:34:24 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210054-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767047664.852636,VS0,VE213
vary: Accept-Encoding
x-fastly-request-id: 0d6f77f7563dcb9593a8138a2b7437863694855d
content-length: 3293
Blog (Slides)
The best way to learn is to teach.
Blog (Slides)
The best way to learn is to teach.
- Tutorial for Inference-Time Compute
- By “Alignment”, what are we aligning LLMs to?
- (NAACL 2024) Self-Reflection/Self-Correct May Not Work
- Tutorial for Mechanistic Interpretability (RASP)
- Distributed Training and Inference in Academia Environment (co-teach w/ Marziyeh Movahedi at TTIC seminar)
- External Tools + LLM (WebGPT, Toolformer)
- GPT-4 TechReport 100-Page Walkthrough
- Emergent Ability of LLM
- Unified View of Pattern Efficient Tuning
- Open-Retrieval QA Pretraining: Explained (co-teach w/ Zhengping Jiang at Columbia and IBM)
- Tutorial on Certified Robustness in NLP