14 papers
When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding
Ke Li, Jiayu Chen, Maoliang Li +5
Efficient long-video understanding requires vision--language models (VLMs) to reason over a small number of frames selected as sparse visual evidence. Existing relevance-based meth…
PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud
Chenghua Wang, Daliang Xu, Dongqi Cai +24
Physical AI policies require inference throughout their lifecycle, including model evaluation, cloud reinforcement learning rollout, edge GPU serving, and onboard deployment. Altho…
EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics
Jiayu Chen, Hengyi Zhang, Maoliang Li +5
DiT video generation is latency-intensive due to iterative full-frame denoising, while prior cloud-edge methods largely rely on static inter-step decoupling and cannot leverage int…
WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving
Chiheng Lou, Sheng Qi, Rui Kang +5
Deploying multiple models within shared GPU clusters is a key strategy to improve resource efficiency in large language model (LLM) serving. Existing multi-LLM serving systems impr…
VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness
Zihao Zheng, Zhihao Mao, Xingyue Zhou +9
Vision-and-Language Navigation (VLN) increasingly relies on large vision-language models, but their inference cost conflicts with real-time deployment. Token caching is a promising…
HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness
Zihao Zheng, Zhihao Mao, Sicheng Tian +8
Vision-Language-Action (VLA) Models have become the mainstream solution for robot control, but suffer from slow inference speeds. Speculative Decoding (SD) is a promising accelerat…