BAFNet: Bilateral Attention Fusion Network for Lightweight Semantic Segmentation of Urban Remote Sensing Imagesby Wentao…
Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformersby Siyu Chen, Heejune Sheen,…
Dynamic Fraud Detection: Integrating Reinforcement Learning into Graph Neural Networksby Yuxin Dong, Jianhua Yao, Jiajing…
Planning Transformer: Long-Horizon Offline Reinforcement Learning with Planning Tokensby Joseph Clinton, Robert LieckFirst submitted to…
Language Models “Grok” to Copyby Ang Lv, Ruobing Xie, Xingwu Sun, Zhanhui Kang, Rui YanFirst…
Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPUby Zhenyu Ning,…
Y-Drop: A Conductance based Dropout for fully connected layersby Efthymios Georgiou, Georgios Paraskevopoulos, Alexandros PotamianosFirst…
Transformer with Controlled Attention for Synchronous Motion Captioningby Karim Radouane, Sylvie Ranwez, Julien Lagarde, Andon…
SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexityby Qitian Wu, Kai Yang, Hengrui Zhang, David…
Sub-graph Based Diffusion Model for Link Predictionby Hang Li, Wei Jin, Geri Skenderi, Harry Shomer,…