This paper proposes a new approach to fine-tuning models, focusing on the direction of updates rather than the magnitude of changes, to improve performance without introducing behavioral drift. Practitioners can benefit from this method by optimizing their fine-tuning process to achieve better results while preserving existing capabilities.
Firehose
Filtered to tagged “direction-selection problem” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives
Browse by tag
artificial intelligence 89continual learning 27AI 23AI safety 13reinforcement learning 13agentic coding 12open-weight models 12AI agents 10machine learning 9AI ethics 8cybersecurity 8existential risk 8language models 8natural language processing 8ethics 7Reinforcement learning 6Diffusion models 5large language models 5multi-agent systems 5open-source 5recursive self-improvement 5robotics 5security 5software development 5Agentic AI 4artificial general intelligence 4mathematics 4Recursive self-improvement 4agents 3AI infrastructure 3