activity
20242026
collaborators

16 papers

cs.SD2026

Whisper-AuT: Domain-Adapted Audio Encoder for Efficient Audio-LLM Training

Jielin Qiu, Ming Zhu, Wenting Zhao +11

Audio-native large language models (audio-LLMs) commonly use Whisper as their audio encoder. However, Whisper was trained exclusively on speech data, producing weak representations…

cs.HC2026

RealUserSim: Bridging the Reality Gap in Agent Benchmarking via Grounded User Simulation

Ming Zhu, Juntao Tan, Rithesh Murthy +6

LLM-based user simulation is the primary mechanism for end-to-end agent evaluation, yet simulated users are poor proxies for real humans: unconstrained LLM defaults produce a Forma…

cs.SD2026

Enterprise Sales Copilot: Enabling Real-Time AI Support with Automatic Information Retrieval in Live Sales Calls

Jielin Qiu, Liangwei Yang, Ming Zhu +11

During live sales calls, customers frequently ask detailed product questions that require representatives to manually search internal databases and CRM systems. This process typica…

cs.SD2026

Building Enterprise Realtime Voice Agents from Scratch: A Technical Tutorial

Jielin Qiu, Zixiang Chen, Liangwei Yang +11

We present a technical tutorial for building enterprise-grade realtime voice agents from first principles. While end-to-end speech-to-speech models may ultimately provide the best…

cs.CL2026

Position: Vector Prompt Interfaces Should Be Exposed to Enable Customization of Large Language Models

Liangwei Yang, Shiyu Wang, Haolin Chen +12

As large language models (LLMs) transition from research prototypes to real-world systems, customization has emerged as a central bottleneck. While text prompts can already customi…

cs.SD2026

VoiceAgentRAG: Solving the RAG Latency Bottleneck in Real-Time Voice Agents Using Dual-Agent Architectures

Jielin Qiu, Jianguo Zhang, Zixiang Chen +12

We present VoiceAgentRAG, an open-source dual-agent memory router that decouples retrieval from response generation. A background Slow Thinker agent continuously monitors the conve…