5 papers
Decentralized Federated Learning for Heterogeneous Multi-Task Semantic Communication
Lin Yin, Tiejun Lv, Weicai Li +2
Collaborative training in distributed semantic communication (DSC) networks typically relies on decentralized federated learning (DFL). However, pushing topology-agnostic aggregati…
Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data
Linqi Yin, Shiduo Zhang, Shenling Qiu +11
Vision-language models (VLMs) are powerful general-purpose reasoners, yet converting them into robot control policies (VLAs) is surprisingly difficult. The root cause is a two-fold…
Adaptive Dual-Path Framework for Covert Semantic Communication
Xi Yu, Weicai Li, Lin Yin +1
This paper proposes a novel adaptive dual-path framework for covert semantic communication (SemCom), which integrates covert information transmission with task-oriented semantic co…
WESR: Scaling and Evaluating Word-level Event-Speech Recognition
Chenchen Yang, Kexin Huang, Liwei Fan +8
Speech conveys not only linguistic information but also rich non-verbal vocal events such as laughing and crying. While semantic transcription is well-studied, the precise localiza…
FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization
Yicheng Liu, Shiduo Zhang, Zibin Dong +12
Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often…