会员服务
Rethinking the Teacher-Student Framework for Test-Time Adaptation
Arxiv
0+阅读 · 9月2日
Beyond Magnitude: Contrastive Routing for Modular Mixture-of-Experts
Arxiv
0+阅读 · 9月1日
Momentum as Residual-Driven Multiplier Correction for Deep Learning Optimization
Arxiv
0+阅读 · 8月30日
EMAG: Self-Rectifying Diffusion Sampling with Exponential Moving Average Guidance
Arxiv
0+阅读 · 8月31日
Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models
Arxiv
0+阅读 · 6月23日
Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models
Arxiv
0+阅读 · 6月30日
Forecasting the Evolving Composition of Inbound Tourism Demand: A Bayesian Compositional Time Series Approach Using Platform Booking Data
Arxiv
0+阅读 · 6月27日
Momentum as Residual-Driven Multiplier Correction for Deep Learning Optimization
Arxiv
0+阅读 · 8月13日
Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average
Arxiv
0+阅读 · 7月4日
EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games
Arxiv
0+阅读 · 6月22日
Heterogeneous Knowledge Distillation via Geometry Decoupling and Momentum-Aware Gradient Regulation
Heterogeneous Knowledge Distillation via Geometry Decoupling and Momentum-Aware Gradient Regulation
Arxiv
0+阅读 · 6月23日
Spectral Retrieval-Augmented Time-Series Forecasting
Arxiv
0+阅读 · 6月17日
OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality
Arxiv
0+阅读 · 6月15日
Quantile autoregressive moving average models for ratio-based bounded time series
Arxiv
0+阅读 · 5月25日
What is the Long-Term Value of Reliability?
Arxiv
0+阅读 · 6月10日
参考链接
微信扫码咨询专知VIP会员
Top