A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networksby Biswadeep Chakraborty, Harshit…
Fully Open Source Moxin-7B Technical Reportby Pu Zhao, Xuan Shen, Zhenglun Kong, Yixin Shen, Sung-En…
GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language modelby Haotong Yang, Xiyuan…
Stock Type Prediction Model Based on Hierarchical Graph Neural Networkby Jianhua Yao, Yuxin Dong, Jiajing…
Guidance is All You Need: Temperature-Guided Reasoning in Large Language Modelsby Eyad Gomaa, Gomaa SalahFirst…
Understanding Factual Recall in Transformers via Associative Memoriesby Eshaan Nichani, Jason D. Lee, Alberto BiettiFirst…
Optimizing Multi-Task Learning for Enhanced Performance in Large Language Modelsby Zhen Qi, Jiajing Chen, Shuo…
Normalizing Flows are Capable Generative Modelsby Shuangfei Zhai, Ruixiang Zhang, Preetum Nakkiran, David Berthelot, Jiatao…
Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series…
Enhanced Computationally Efficient Long LoRA Inspired Perceiver Architectures for Auto-Regressive Language Modelingby Kaleel Mahmood, Shaoyi…