ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
Paper
• 2603.10160 • Published
• 16
Haruka Takahashi
harukatakahashi
AI & ML interests
None yet
Recent Activity
upvoted a paper about 13 hours ago
ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning upvoted a paper about 13 hours ago
Heterogeneous Agent Collaborative Reinforcement Learning upvoted a paper 9 months ago
Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety
Assurance Organizations
None yet
upvoted 2 papers about 13 hours ago
upvoted 2 papers 9 months ago