Picture for Kun Qian

Kun Qian

Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts

Add code
Apr 19, 2025
Viaarxiv icon

Evaluation and Incident Prevention in an Enterprise AI Assistant

Add code
Apr 11, 2025
Viaarxiv icon

Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning

Add code
Mar 31, 2025
Viaarxiv icon

Contrastive Speaker-Aware Learning for Multi-party Dialogue Generation with LLMs

Add code
Mar 11, 2025
Viaarxiv icon

Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotation

Add code
Feb 21, 2025
Viaarxiv icon

MAD-UV: The 1st INTERSPEECH Mice Autism Detection via Ultrasound Vocalization Challenge

Add code
Jan 08, 2025
Figure 1 for MAD-UV: The 1st INTERSPEECH Mice Autism Detection via Ultrasound Vocalization Challenge
Figure 2 for MAD-UV: The 1st INTERSPEECH Mice Autism Detection via Ultrasound Vocalization Challenge
Figure 3 for MAD-UV: The 1st INTERSPEECH Mice Autism Detection via Ultrasound Vocalization Challenge
Viaarxiv icon

Bridging the Data Provenance Gap Across Text, Speech and Video

Add code
Dec 19, 2024
Figure 1 for Bridging the Data Provenance Gap Across Text, Speech and Video
Figure 2 for Bridging the Data Provenance Gap Across Text, Speech and Video
Figure 3 for Bridging the Data Provenance Gap Across Text, Speech and Video
Figure 4 for Bridging the Data Provenance Gap Across Text, Speech and Video
Viaarxiv icon

Exploring Large Vision-Language Models for Robust and Efficient Industrial Anomaly Detection

Add code
Dec 01, 2024
Viaarxiv icon

Radio Frequency Ray Tracing with Neural Object Representation

Add code
Nov 16, 2024
Viaarxiv icon

Unleashing the Power of LLMs as Multi-Modal Encoders for Text and Graph-Structured Data

Add code
Oct 15, 2024
Figure 1 for Unleashing the Power of LLMs as Multi-Modal Encoders for Text and Graph-Structured Data
Figure 2 for Unleashing the Power of LLMs as Multi-Modal Encoders for Text and Graph-Structured Data
Figure 3 for Unleashing the Power of LLMs as Multi-Modal Encoders for Text and Graph-Structured Data
Figure 4 for Unleashing the Power of LLMs as Multi-Modal Encoders for Text and Graph-Structured Data
Viaarxiv icon