paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
WD

Wenlong Deng

ACL 2026×2ICLR 2026×2可解释性多模态对齐与偏好强化学习与后训练理论与学习动力学
新星分新星
87
一作贡献70
核心/参与17
方向广度13
合作网络12
2 一作 · 4 篇 · ACL 2026 / ICLR 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

4
一作ACL 2026Poster· Natural Language Processing

For-Value: Efficient Forward-Only Data Valuation for finetuning LLM s and VLM s

Wenlong Deng · Qi Zeng · Jiaming Zhang · Minghui Chen · Zixin Ding · Christos Thrampoulidis · Boying Gong · Xiaoxiao Li

摘要

Data valuation is essential for enhancing the transparency and accountability of large language models (LLMs) and vision-language models (VLMs). However, existing methods typically rely on gradient computations, making them computationally prohibitive for billion-parameter models and precluding b...

多模态理论与学习动力学对齐与偏好OpenReview 项目页
作者位次 #4/6ACL 2026Poster· ACL Industry Track

Automatic Prompt Engineering for Scalable Prompt Inversion in Text-to-Image Ad Generation

Zixin Ding · Qi Zeng · Boying Gong · Wenlong Deng · Bo Pan · Yuxin Chen

摘要

While prompt engineering offers effective control over Text-to-Image (T2I) generation, it remains labor-intensive for large-scale production. We present PRISM-DUEL, a black-box framework that formalizes prompt optimization as Automatic Prompt Engineering (APE), motivated by advertising workflows...

可解释性多模态对齐与偏好OpenReview 项目页

常见合作者