6 papers
MoSa: Motion Generation with Scalable Autoregressive Modeling
Mengyuan Liu, Sheng Yan, Yong Wang +3
We introduce MoSa, a novel hierarchical motion generation framework for text-driven 3D human motion generation that enhances the Vector Quantization-guided Generative Transformers…
Declarative Techniques for NL Queries over Heterogeneous Data
Elham Khabiri, Jeffrey O. Kephart, Fenno F. Heath +6
In many industrial settings, users wish to ask questions in natural language, the answers to which require assembling information from diverse structured data sources. With the adv…
Analyzing and Internalizing Complex Policy Documents for LLM Agents
Jiateng Liu, Zhenhailong Wang, Xiaojiang Huang +6
Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules. As requirements grow, these documents expand rapidly, causing…
ZhiFangDanTai: Fine-tuning Graph-based Retrieval-Augmented Generation Model for Traditional Chinese Medicine Formula
ZiXuan Zhang, Bowen Hao, Yingjie Li +1
Traditional Chinese Medicine (TCM) formulas play a significant role in treating epidemics and complex diseases. Existing models for TCM utilize traditional algorithms or deep learn…
A System and Benchmark for LLM-based Q&A on Heterogeneous Data
Achille Fokoue, Srideepika Jayaraman, Elham Khabiri +8
In many industrial settings, users wish to ask questions whose answers may be found in structured data sources such as a spreadsheets, databases, APIs, or combinations thereof. Oft…
Multi-Treatment Multi-Task Uplift Modeling for Enhancing User Growth
Yuxiang Wei, Zhaoxin Qiu, Yingjie Li +2
As a key component in boosting online user growth, uplift modeling aims to measure individual user responses (e.g., whether to play the game) to various treatments, such as gaming…