papers

Publications (7)

cs.CL2026

EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models

Li Zhou, Lutong Yu, You Lyu +6

Speech Language Models (SLMs) have made significant progress in spoken language understanding. Yet it remains unclear whether they can fully perceive non lexical vocal cues alongsi…

cs.SE2026

Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents

Chenyu Zhao, Shenglin Zhang, Yihang Lin +7

Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose t…

cs.CL2026

GrowLoop: Self-Evolving Conversation Evaluation Seeded by Human

Yihang Lin, Yunze Gao, Zeyang Lin +3

With the rapid advancement of large language models, evaluating human-likeness in open-ended conversation has become increasingly important. However, human-likeness is a form of ta…

cs.SD2026

PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis

Bowen Li, Shaotong Guo, Zhen Wang +11

Building state-of-the-art text-to-speech (TTS) systems typically demands millions of hours of proprietary data and complex multi-stage architectures, creating substantial barriers…

cs.CV2026

TKN: Transformer-based Keypoint Prediction Network For Real-time Video Prediction

Haoran Li, XiaoLu Li, Yihang Lin +4

Video prediction is a complex time-series forecasting task with great potential in many use cases. However, traditional methods prioritize accuracy and overlook slow prediction spe…

cs.SD2026

Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-Speech

Yihang Lin, Li Zhou, Congwei Cao +4

Large language model (LLM)-based text-to-speech (TTS) systems enable prompt-conditioned emotional control but struggle with fine-grained emotion intensity due to the semantic -- ac…

cs.LG2023

Mitigating Backdoors in Federated Learning with FLD

Yihang Lin, Pengyuan Zhou, Zhiqian Wu +1

Federated learning allows clients to collaboratively train a global model without uploading raw data for privacy preservation. This feature, i.e., the inability to review participa…