10 papers
One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence
Bowen Jiang, Taiwei Shi, Ryo Kamoi +5
This paper introduces OMAR: One Model, All Roles, a reinforcement learning framework that enables AI to develop social intelligence through multi-turn, multi-agent conversational s…
Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
Bowen Jiang, Zhuoqun Hao, Young-Min Cho +6
Large Language Models (LLMs) have emerged as personalized assistants for users across a wide range of tasks -- from offering writing support to delivering tailored recommendations…
ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations
Bowen Jiang, Yuan Yuan, Xinyi Bai +6
This work demonstrates that diffusion models can achieve font-controllable multilingual text rendering using just raw images without font label annotations.Visual text rendering re…
GeoGrid-Bench: Can Foundation Models Understand Multimodal Gridded Geo-Spatial Data?
Bowen Jiang, Yangxinyu Xie, Xiaomeng Wang +6
We present GeoGrid-Bench, a benchmark designed to evaluate the ability of foundation models to understand geo-spatial data in the grid structure. Geo-spatial datasets pose distinct…
Vysics: Object Reconstruction Under Occlusion by Fusing Vision and Contact-Rich Physics
Bibit Bianchini, Minghan Zhu, Mengti Sun +3
We introduce Vysics, a vision-and-physics framework for a robot to build an expressive geometry and dynamics model of a single rigid body, using a seconds-long RGBD video and the r…
A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation
Yangxinyu Xie, Bowen Jiang, Tanwi Mallick +10
Large language models (LLMs) are a transformational capability at the frontier of artificial intelligence and machine learning that can support decision-makers in addressing pressi…