Scaling Textual Gradients via Sampling-Based Momentum

Ding, Zixin (ORCID:0009000722271046); Hong, Junyuan (ORCID:0000000257185187); Shi, Zhan (ORCID:0009000217953409); Wang, Tianhao (ORCID:0000000179443418); Lin, Zinan (ORCID:0000000284212662); Yin, Li (ORCID:0000000310630682); Liu, Meng (ORCID:0000000294203874); Wang, Zhangyang (ORCID:0000000220505693); Chen, Yuxin (ORCID:000000032133140X)

doi:10.1145/3786335.3813168

skip to main content

An official website of the United States government Here's how you know

Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 5:00 PM ET until 8:00 PM ET on Friday, September 11 due to maintenance. We apologize for the inconvenience.

Citation Details

This content will become publicly available on May 26, 2027

Scaling Textual Gradients via Sampling-Based Momentum

Award ID(s):: 2313131

PAR ID:: 10702535

Author(s) / Creator(s):: Ding, Zixin; Hong, Junyuan; Shi, Zhan; Wang, Tianhao; Lin, Zinan; Yin, Li; Liu, Meng; Wang, Zhangyang; Chen, Yuxin

Publisher / Repository:: ACM

Date Published:: 2026-05-26

ISBN:: 9798400724152

Page Range / eLocation ID:: 917 to 952

Format(s):: Medium: X

Location:: San Jose CA USA

Sponsoring Org:: National Science Foundation

Free Publicly Accessible Full Text
This content will become publicly available on May 26, 2027
Conference Paper:
https://doi.org/10.1145/3786335.3813168

More Like this