"HART-Pruner: A Human-Aligned Token Reduction Method for Interpretable and ..."

Miho Takahashi et al. (2025)

> Home

Details and statistics

DOI: 10.1145/3765766.3765832

access: closed

type: Conference or Workshop Paper

metadata version: 2026-02-03

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - conf/hai/TakahashiHME25
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/hai/TakahashiHME25
Miho Takahashi, Rintaro Harada, Akiko Masaki-Kato, Takeharu Eda:
HART-Pruner: A Human-Aligned Token Reduction Method for Interpretable and Efficient Vision-Language Inference. HAI 2025: 458-460

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.