activity
20162026
most citedTowards Transfer Learning for End-to-End Speech Synthesis from Deep Pre-Trained Language Models

26 citations · 42 across the 10 of their papers we have counts for

collaborators
Showing 2026Show all

2 papers · 1 filter

cs.CL2026

Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning

Wei Fang, James Glass

LLM agents operating over massive, dynamic tool libraries rely on effective retrieval, yet standard single-shot dense retrievers struggle with complex requests. These failures prim…

cs.CL2026★ 1 cited

MedDialogRubrics: A Comprehensive Benchmark and Evaluation Framework for Multi-turn Medical Consultations in Large Language Models

Lecheng Gong, Weimin Fang, Ting Yang +9

Medical conversational AI (AI) plays a pivotal role in the development of safer and more effective medical dialogue systems. However, existing benchmarks and evaluation frameworks…