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

Santosh T.Y.S.S

ACL 2026×2社会与人本智能体与工具多模态对齐与偏好安全
新星分新星
63
一作贡献30
核心/参与12
方向广度10
合作网络3
1 一作 · 2 篇 · ACL 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

2
一作ACL 2026Poster· Natural Language Processing

From Naturalness to Norms: Interactional Cultural Competence for S peech LM s

Santosh T.Y.S.S

摘要

Spoken language models (SpeechLMs) are increasingly real-time conversational actors. Yet many culturally consequential aspects of spoken interaction are not primarily lexical. Across sociolinguistics, linguistic anthropology, and conversation analysis, meaning emerges through how talk is produced...

社会与人本智能体与工具多模态OpenReview 项目页
作者位次 #2/3ACL 2026Findings· Findings of ACL

Position: From Noise to Signal to Selbstzweck - Reframing Human Label Variation in the Era of Post-training in NLP

Shanshan Xu · Santosh T.Y.S.S · Barbara Plank

摘要

Human Label Variation (HLV) refers to legitimate disagreement in annotation that reflects the diversity of human perspectives rather than mere error. Long treated in NLP as \textit{noise} to be eliminated, HLV has only recently been reframed as a \textit{signal} for improving model robustness. Wi...

对齐与偏好安全强化学习与后训练OpenReview 项目页

常见合作者