会员服务
Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression
Arxiv
0+阅读 · 2月19日
3D Scene Rendering with Multimodal Gaussian Splatting
Arxiv
0+阅读 · 2月19日
FoundationPose-Initialized 3D-2D Liver Registration for Surgical Augmented Reality
FoundationPose-Initialized 3D-2D Liver Registration for Surgical Augmented Reality
Arxiv
0+阅读 · 2月19日
Heterogeneous Federated Fine-Tuning with Parallel One-Rank Adaptation
Arxiv
0+阅读 · 2月18日
Amber-Image: Efficient Compression of Large-Scale Diffusion Transformers
Arxiv
0+阅读 · 2月19日
PredMapNet: Future and Historical Reasoning for Consistent Online HD Vectorized Map Construction
PredMapNet: Future and Historical Reasoning for Consistent Online HD Vectorized Map Construction
Arxiv
0+阅读 · 2月18日
Efficient Knowledge Transfer for Jump-Starting Control Policy Learning of Multirotors through Physics-Aware Neural Architectures
Arxiv
0+阅读 · 2月17日
$μ$pscaling small models: Principled warm starts and hyperparameter transfer
Arxiv
0+阅读 · 2月11日
Gradient Descent with Large Step Sizes: Chaos and Fractal Convergence Region
Arxiv
0+阅读 · 2月8日
Overcoming Barren Plateaus in Variational Quantum Circuits using a Two-Step Least Squares Approach
Arxiv
0+阅读 · 2月16日
EDGS: Eliminating Densification for Efficient Convergence of 3DGS
Arxiv
0+阅读 · 2月12日
Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation
Arxiv
0+阅读 · 2月13日
Default Machine Learning Hyperparameters Do Not Provide Informative Initialization for Bayesian Optimization
Arxiv
0+阅读 · 2月9日
A Theoretical Framework for LLM Fine-tuning Using Early Stopping for Non-random Initialization
Arxiv
0+阅读 · 2月15日
Optimal Estimation in Orthogonally Invariant Generalized Linear Models: Spectral Initialization and Approximate Message Passing
Arxiv
0+阅读 · 2月9日
参考链接
微信扫码咨询专知VIP会员
Top