Skip to content

[ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

active 2024-06-192025-11-04 (UTC)

Complete coverage26,748 / 26,748 hourly files (100%) · 2 absent upstream2023-08-152026-09-02 (UTC)
Events
59
Pushes
2
Pull requests
0
Issues
10
Stars
42
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 504 days from 2024-06-19 to 2025-11-04. Pushes: 2 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 10 total, peak 2 in a day. Comments: 3 total, peak 2 in a day. Stars: 42 total, peak 2 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
Yuzz10206202
184100806313001
queng123223000
zhangbaijin1000
FanshuoZeng1000
keepsimpler1000

Recent activity

Latest issues, pull requests and releases

  • Issue#5184100806312024-11-21 07:19
    mistakes in the code
  • Issue comment#6184100806312024-11-20 09:26
    Questions about SQuADv1/v2
  • Issue#6queng123222024-11-20 07:59
    Questions about SQuADv1/v2
  • Issue#5184100806312024-11-20 07:21
    mistakes in the code
  • Issue#4FanshuoZeng2024-11-05 17:31
    Could you please tell me where the core code for this work is?
  • Issue#3queng123222024-11-01 03:05
    Questions about Transformer
  • Issue#1Yuzz10202024-10-21 04:00
    Nice work!Can it apply to VLMs?
  • Issue#3queng123222024-10-12 08:26
    Questions about Transformer
  • Issue comment#1Yuzz10202024-09-22 16:06
    Nice work!Can it apply to VLMs?
  • Issue#2Yuzz10202024-09-22 16:04
    Cool! Is the source code of visualizing the attention maps available? I can not find it. Thanks!
  • Issue comment#2Yuzz10202024-09-22 16:04
    Cool! Is the source code of visualizing the attention maps available? I can not find it. Thanks!
  • Issue#2keepsimpler2024-09-18 21:28
    Cool! Is the source code of visualizing the attention maps available? I can not find it. Thanks!
  • Issue#1zhangbaijin2024-09-12 08:04
    Nice work!Can it apply to VLMs?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 42 stars here means stars gained during the window, not the repo's star count.