Publications (62)
StyleDGPT: Stylized Response Generation with Pre-trained Language Models
Ze Yang, Wei Wu, Can Xu +5
Generating responses following a desired style has great potentials to extend applications of open-domain dialogue systems, yet is refrained by lacking of parallel data for trainin…
Recovering and Simulating Pedestrians in the Wild
Ze Yang, Siva Manivasagam, Ming Liang +3
Sensor simulation is a key component for testing the performance of self-driving vehicles and for data augmentation to better train perception systems. Typical approaches rely on a…
GenAssets: Generating in-the-wild 3D Assets in Latent Space
Ze Yang, Jingkang Wang, Haowei Zhang +3
High-quality 3D assets for traffic participants are critical for multi-sensor simulation, which is essential for the safe end-to-end development of autonomy. Building assets from i…
Research on Large Language Model Cross-Cloud Privacy Protection and Collaborative Training based on Federated Learning
Ze Yang, Yihong Jin, Yihan Zhang +2
The fast development of large language models (LLMs) and popularization of cloud computing have led to increasing concerns on privacy safeguarding and data security of cross-cloud…
Model Compression with Multi-Task Knowledge Distillation for Web-scale Question Answering System
Ze Yang, Linjun Shou, Ming Gong +2
Deep pre-training and fine-tuning models (like BERT, OpenAI GPT) have demonstrated excellent results in question answering areas. However, due to the sheer amount of model paramete…
Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model
Emre Can Acikgoz, Jeremiah Greer, Akul Datta +6
Large Language Models (LLMs) with API-calling capabilities enabled building effective Language Agents (LA), while also revolutionizing the conventional task-oriented dialogue (TOD)…