Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
Paper • 2509.24372 • Published • 16
Kajetan Schweighofer
kschweig
AI & ML interests
Uncertainty Estimation, Reinforcement Learning
Recent Activity
upvoted a paper about 1 month ago
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement
Learning upvoted a paper 4 months ago
Effective Distillation to Hybrid xLSTM Architectures upvoted an article about 1 year ago
xLSTM-based time series model TiRex significantly outperforms competing models in forecasting accuracyOrganizations
upvoted a paper about 1 month ago
upvoted a paper 4 months ago
upvoted an article about 1 year ago
Article
xLSTM-based time series model TiRex significantly outperforms competing models in forecasting accuracy
BobWue
• • 12 liked a
model over 1 year ago
upvoted 4
papers over 1 year ago
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
Paper • 2410.22391 • Published • 22
LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content
Paper • 2410.10783 • Published • 26
GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models
Paper • 2410.06154 • Published • 16
One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation
Paper • 2410.07170 • Published • 16