Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspectiveby Qishuai Wen, Chun-Guang LiFirst submitted to…
Pretrained transformer efficiently learns low-dimensional target functions in-contextby Kazusato Oko, Yujin Song, Taiji Suzuki, Denny…
Enhancing Risk Assessment in Transformers with Loss-at-Risk Functionsby Jinghan Zhang, Henry Xie, Xinhao Zhang, Kunpeng…
Grouped Discrete Representation for Object-Centric Learningby Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni PajarinenFirst submitted…
Sparsing Law: Towards Large Language Models with Greater Activation Sparsityby Yuqi Luo, Chenyang Song, Xu…
SIRA: Scalable Inter-frame Relation and Association for Radar Perceptionby Ryoma Yataka, Pu Perry Wang, Petros…
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learningby Dake Bu, Wei Huang, Andi…
Amortized Bayesian Experimental Design for Decision-Makingby Daolang Huang, Yujia Guo, Luigi Acerbi, Samuel KaskiFirst submitted…
Training Compute-Optimal Protein Language Modelsby Xingyi Cheng, Bo Chen, Pan Li, Jing Gong, Jie Tang,…
Ask, and it shall be given: On the Turing completeness of promptingby Ruizhong Qiu, Zhe…