Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/6CVPR 2026Poster· Computer Vision & Pattern Recognition

SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokens

Anindita Ghosh · Vladislav Golyanik · Taku Komura · Philipp Slusallek · Christian Theobalt · Rishabh Dabral

推理多模态社会与人本OpenReview 项目页

作者位次 #4/5ACL 2026Findings· Findings of ACL

Bridging the Culture Gap: A Framework for LLM -Driven Socio-Cultural Localization of Math Word Problems in Low-Resource Languages

Israel Abebe Azime · Tadesse Destaw Belay · Dietrich Klakow · Philipp Slusallek · Anshuman Chhabra

摘要

Large language models (LLMs) have demonstrated significant capabilities in solving mathematical problems expressed in natural language. However, multilingual and culturally-grounded mathematical reasoning in low-resource languages lags behind English due to the scarcity of socio-cultural task dat...

多语言与语言学社会与人本推理OpenReview 项目页

作者位次 #3/5SIGGRAPH 2026Oral· Computer Graphics (Conference Track)

Beyond Positional Encoding: A 5D Spatio-Directional Hash Encoding

Philippe Weier · Lukas Bode · Philipp Slusallek · Adrián Jarabo · Sébastien Speierer

代码长上下文与架构OpenReview

Philipp Slusallek

获取完整研究档案

联系方式

2026 顶会论文

SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokens

Bridging the Culture Gap: A Framework for LLM -Driven Socio-Cultural Localization of Math Word Problems in Low-Resource Languages

Beyond Positional Encoding: A 5D Spatio-Directional Hash Encoding

常见合作者