Summary of Torchtitan: One-stop Pytorch Native Solution For Production Ready Llm Pre-training, by Wanchao Liang et al.
TorchTitan: One-stop PyTorch native solution for production ready LLM pre-trainingby Wanchao Liang, Tianyu Liu, Less…
TorchTitan: One-stop PyTorch native solution for production ready LLM pre-trainingby Wanchao Liang, Tianyu Liu, Less…
DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detectorby Jinghan Li, Yuan Gao, Jinda Lu, Junfeng Fang,…
Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRAby Maharshi Gor,…
Harnessing the Power of Noise: A Survey of Techniques and Applicationsby Reyhaneh Abdolazimi, Shengmin Jin,…
Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptationby Tianyi Zhang, Junda Su, Aditya Desai,…
Communication-Efficient Federated Group Distributionally Robust Optimizationby Zhishuai Guo, Tianbao YangFirst submitted to arxiv on: 8…
Physics-Informed Regularization for Domain-Agnostic Dynamical System Modelingby Zijie Huang, Wanjia Zhao, Jingdong Gao, Ziniu Hu,…
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learningby Siyuan Li, Juanxi Tian, Zedong Wang,…
HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aidby Hemank Lamba, Anton Abilov,…
Covering Numbers for Deep ReLU Networks with Applications to Function Approximation and Nonparametric Regressionby Weigutian…