Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
Paper • 2609.36585 • Published • 42
Darren R. Wang
DarrenWangvep
·
AI & ML interests
Working on AI safety research
Recent Activity
updated a model 14 days ago
DarrenWangvep/deit-checkpoint published a model 14 days ago
DarrenWangvep/deit-checkpoint upvoted a paper 21 days ago
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes ItOrganizations
None yet