Summary of Moe-infinity: Efficient Moe Inference on Personal Machines with Sparsity-aware Expert Cache, by Leyang Xue et al.
MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cacheby Leyang Xue, Yao Fu,…
MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cacheby Leyang Xue, Yao Fu,…
ServerlessLLM: Low-Latency Serverless Inference for Large Language Modelsby Yao Fu, Leyang Xue, Yeqi Huang, Andrei-Octavian…
Genie: Achieving Human Parity in Content-Grounded Datasets Generationby Asaf Yehudai, Boaz Carmeli, Yosi Mass, Ofir…
Manifold GCN: Diffusion-based Convolutional Neural Network for Manifold-valued Graphsby Martin Hanik, Gabriele Steidl, Christoph von…
UrbanGenAI: Reconstructing Urban Landscapes using Panoptic Segmentation and Diffusion Modelsby Timo KapsalisFirst submitted to arxiv…
Smooth Ranking SVM via Cutting-Plane Methodby Erhan Can Ozcan, Berk Görgülü, Mustafa G. Baydogan, Ioannis…
pix2gestalt: Amodal Segmentation by Synthesizing Wholesby Ege Ozguroglu, Ruoshi Liu, Dídac Surís, Dian Chen, Achal…
Deconstructing Denoising Diffusion Models for Self-Supervised Learningby Xinlei Chen, Zhuang Liu, Saining Xie, Kaiming HeFirst…
Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalitiesby Yiyuan Zhang, Xiaohan Ding, Kaixiong…
Precision Mars Entry Navigation with Atmospheric Density Adaptation via Neural Networksby Felipe Giraldo-Grueso, Andrey A.…