3 papers
cs.CV2025
VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference
Shengling Qin, Hao Yu, Chenxin Wu +10
This paper presents VLCache, a cache reuse framework that exploits both Key-Value (KV) cache and encoder cache from prior multimodal inputs to eliminate costly recomputation when t…
cs.CV2025
SplatCo: Structure-View Collaborative Gaussian Splatting for Detail-Preserving Rendering of Large-Scale Unbounded Scenes
Haihong Xiao, Jianan Zou, Yuxin Zhou +2
We present SplatCo, a structure-view collaborative Gaussian splatting framework for high-fidelity rendering of complex outdoor scenes. SplatCo builds upon three novel components: 1…
cs.LG2025
FloE: On-the-Fly MoE Inference on Memory-constrained GPU
Yuxin Zhou, Zheng Li, Jun Zhang +5
With the widespread adoption of Mixture-of-Experts (MoE) models, there is a growing demand for efficient inference on memory-constrained devices. While offloading expert parameters…