Hi there, this is the original author. I just came across this post 11 years late. Anyways, the papers are almost all publicly accessible now through the link which redirects to Google Scholar or Semantic Scholar. There are also now 30 conferences instead of 11.

Here's the new link (though the old one still works): https://jeffhuang.com/best_paper_awards/

Most of the papers are behind a paywall.

A good link, but the title may be misleading.

11 CS conferences, a marginal fraction of how many CS conferences are out there.

notably all best papers before 2005 are missing for ICML.

in terms of metrics of research quality, not all conferences are equal, and "best" papers are often selected by a relatively small group of people whose decision isn't really validated too much.

A good link, but the title may be misleading.

"Every best paper from CS conferences" does not really sound like what this site does -- list best papers from 11 CS conferences, a marginal fraction of how many CS conferences are out there.

the title is wrong. it's not every "best paper": notably all best papers before 2005 are missing for ICML.

in terms of metrics of research quality, not all conferences are equal, and "best" papers are often selected by a relatively small group of people whose decision isn't really validated too much.

A good link, but the title may be misleading.

"Every best paper from CS conferences" does not really sound like what this site does -- list best papers from 11 CS conferences, a marginal fraction of how many CS conferences are out there.

the title is wrong. it's not every "best paper": notably all best papers before 2005 are missing for ICML. In terms of metrics of research quality, not all conferences are equal, and "best" papers are often selected by a relatively small group of people whose decision isn't really validated too much.