3 papers
cs.RO2026
Reflex: Real-Time VLA Control through Streaming Inference
Yuanchun Guo, Bingyan Liu
Flow matching Vision-Language-Action (VLA) models promise precise continuous control, but their iterative denoising nature introduces fundamental incompatibilities with real-time r…
cs.LG2025
PracMHBench: Re-evaluating Model-Heterogeneous Federated Learning Based on Practical Edge Device Constraints
Yuanchun Guo, Bingyan Liu, Yulong Sha +1
Federating heterogeneous models on edge devices with diverse resource constraints has been a notable trend in recent years. Compared to traditional federated learning (FL) that ass…
cs.LG2023
Recent Advances on Federated Learning: A Systematic Survey
Bingyan Liu, Nuoyan Lv, Yuanchun Guo +1
Federated learning has emerged as an effective paradigm to achieve privacy-preserving collaborative learning among different parties. Compared to traditional centralized learning t…