会员服务
Flatter Tokens are More Valuable for Speculative Draft Model Training
Arxiv
0+阅读 · 2月18日
ARO: A New Lens On Matrix Optimization For Large Models
Arxiv
0+阅读 · 2月9日
Supercharging Packet-level Network Simulation of Large Model Training via Memoization and Fast-Forwarding
Arxiv
0+阅读 · 2月11日
R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training
Arxiv
0+阅读 · 2月13日
Evolutionary Generative Optimization: Towards Fully Data-Driven Evolutionary Optimization via Generative Learning
Arxiv
0+阅读 · 2月13日
AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models
Arxiv
0+阅读 · 2月11日
AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models
Arxiv
0+阅读 · 2月10日
Provable Training Data Identification for Large Language Models
Arxiv
0+阅读 · 2月13日
Context Forcing: Consistent Autoregressive Video Generation with Long Context
Arxiv
0+阅读 · 2月5日
Horizon-LM: A RAM-Centric Architecture for LLM Training
Arxiv
0+阅读 · 2月5日
Horizon-LM: A RAM-Centric Architecture for LLM Training
Arxiv
0+阅读 · 2月4日
Reshaping Action Error Distributions for Reliable Vision-Language-Action Models
Arxiv
0+阅读 · 2月4日
Mano: Restriking Manifold Optimization for LLM Training
Arxiv
0+阅读 · 1月30日
Mixtera: A Data Plane for Foundation Model Training
Arxiv
0+阅读 · 2月1日
Why Inference in Large Models Becomes Decomposable After Training
Arxiv
0+阅读 · 2月2日
参考链接
微信扫码咨询专知VIP会员
Top