Tag: LLM post-training
Browse our exclusive articles!
Self-Conditioning Boosts Masked Diffusion Models Performance
Discover how Self-Conditioning adaptation improves masked diffusion models, enhancing data generation and image synthesis with minimal changes.
Optimizing Llama-3 70B Post-Training with Language Mixture Ratio
Discover how optimal additional language mixture ratios enhance Llama-3 70B post-training, boosting multilingual and domain-specific AI performance.
StateX: Boost RNN Recall with Post-training State Expansion
Enhance RNN recall and in-context learning efficiently with StateX, a post-training framework expanding recurrent states without costly retraining.
EVPO: Adaptive Policy Optimization for LLM Post-Training
Discover EVPO, an adaptive policy optimization method that improves LLM post-training by balancing critic use to reduce variance and boost performance.