Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentationby Daniel Kienzle, Marco Kantonis, Robin Schön, Rainer…
Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Modelsby Yongxin Guo, Zhenglin Cheng,…
MiniCache: KV Cache Compression in Depth Dimension for Large Language Modelsby Akide Liu, Jing Liu,…
Minimum number of neurons in fully connected layers of a given neural network (the first…
A Structure-Aware Framework for Learning Device Placements on Computation Graphsby Shukai Duan, Heng Ping, Nikos…
Variational Delayed Policy Optimizationby Qingyuan Wu, Simon Sinong Zhan, Yixuan Wang, Yuhui Wang, Chung-Wei Lin,…
Bayesian Inverse Problems with Conditional Sinkhorn Generative Adversarial Networks in Least Volume Latent Spacesby Qiuyi…
Probabilistic Inference in the Era of Tensor Networks and Differential Programmingby Martin Roa-Villescas, Xuanzhao Gao,…
Attention as an RNNby Leo Feng, Frederick Tung, Hossein Hajimirsadeghi, Mohamed Osama Ahmed, Yoshua Bengio,…
Leader Reward for POMO-Based Neural Combinatorial Optimizationby Chaoyang Wang, Pengzhi Cheng, Jingze Li, Weiwei SunFirst…