collaborators

5 papers

cs.CL2026

NüshuVoice: Reviving the Voice of Endangered Nüshu with Pitch-Aware Text-to-Speech

Hongkun Yang, Xinhui Yi, Xiyan Zhao +13

Nüshu is an endangered phonetic script historically used by women in Jiangyong County, southern Hunan, China. While existing computational studies of Nüshu mainly focus on textua…

cs.CY2026

AppellateGen: A Benchmark for Appellate Legal Judgment Generation

Hongkun Yang, Lionel Z. Wang, Wei Fan +10

Legal judgment generation is a critical task in legal intelligence. However, existing research in legal judgment generation has predominantly focused on first-instance trials, rely…

cs.LG2026

From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models

Zhuofan Li, Hongkun Yang, Zhenyang Chen +4

Vision-Language-Action (VLA) models have recently enabled embodied agents to perform increasingly complex tasks by jointly reasoning over visual, linguistic, and motor modalities.…

cs.CV2026

DeAR: Fine-Grained VLM Adaptation by Decomposing Attention Head Roles

Yiming Ma, Hongkun Yang, Lionel Z. Wang +3

Prompt learning is a dominant paradigm for adapting pre-trained Vision-Language Models (VLMs) to downstream tasks. However, existing methods often rely on a simplistic, layer-centr…

cs.LG2026

How Implicit Bias Accumulates and Propagates in LLM Long-term Memory

Yiming Ma, Lixu Wang, Lionel Z. Wang +6

Long-term memory mechanisms enable Large Language Models (LLMs) to maintain continuity and personalization across extended interaction lifecycles, but they also introduce new and u…