activity
20242026
most citedAsteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices

1 citations · 2 across the 9 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference

Junjie Liu, Shengyuan Ye, Xu Chen

Vision-Language Models (VLMs) demonstrate exceptional visual reasoning capabilities, yet their inference costs escalate rapidly with the proliferation of visual tokens. Existing vi…