Alex Open Research Wiki
Search
Search
Dark mode
Light mode
Explorer
Tag: post-training
4 items with this tag.
Oct 25, 2026
1.5-SPSA: Probe-Space Preconditioning for Fast and Stable Zero-Order Training
zeroth-order
optimization
preconditioning
post-training
benchmark-hygiene
Oct 25, 2026
Evolution Strategies
evolution-strategies
reinforcement-learning
post-training
Jul 17, 2026
DMax: Aggressive Parallel Decoding for dLLMs
diffusion-language-models
parallel-decoding
self-distillation
inference-efficiency
post-training
May 15, 2026
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
evolution-strategies
llm-fine-tuning
reinforcement-learning
post-training