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

Kaustubh Shivshankar Shejole

ACL 2026×2ICML 2026效率与系统社会与人本理论与学习动力学对齐与偏好推理
新星分新星
72
一作贡献30
核心/参与24
方向广度13
合作网络3
1 一作 · 3 篇 · ACL 2026 / ICML 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

3
作者位次 #2/3ICML 2026Poster· Probabilistic Methods / Everything Else

An Efficient Joint Learning Approach for Item Response Theory

Tanish Agarwal · Kaustubh Shivshankar Shejole · Arpit Agarwal

效率与系统理论与学习动力学OpenReview
作者位次 #2/3ACL 2026Poster· Natural Language Processing

Looking at Radiology Report Generation through a Causal Lens: A Survey

Satyam Kumar · Kaustubh Shivshankar Shejole · Pushpak Bhattacharyya

摘要

Automatic radiology report generation (RRG) has emerged as a promising approach to reduce clinicians’ workload, yet existing systems are vulnerable to biases induced by spurious correlations across data, models, and evaluation pipelines. Such biases raise serious fairness concerns and may adverse...

社会与人本对齐与偏好效率与系统OpenReview 项目页
一作ACL 2026Findings· Findings of ACL

Rethinking Research on Stereotypes: An Analysis through Social Psychological and Computational Perspectives

Kaustubh Shivshankar Shejole · Pushpak Bhattacharyya

摘要

Stereotypes are social constructs shaping human perception and behavior that can produce harmful outcomes under specific conditions. Recent work shows that large language models (LLMs) may inherit and amplify such social harms. However, most existing research often focuses only upon stereotypical...

社会与人本推理安全OpenReview 项目页

常见合作者