PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling
ulab
university
AI & ML interests
None defined yet.
Recent Activity
-
ulab-ai/ResearchArcade-openreview-paragraphs
Viewer • Updated • 14.2k • 31 -
ulab-ai/ResearchArcade-openreview-papers-revisions
Viewer • Updated • 54.5k • 20 -
ulab-ai/ResearchArcade-openreview-reviews
Viewer • Updated • 472k • 41 • 1 -
ulab-ai/ResearchArcade-openreview-arxiv
Viewer • Updated • 28.6k • 30
Sotopia-RL: Reward Design for Social Intelligence
IRanker: Towards Ranking Foundation Model
Time-R1: Framework and resources for endowing LLMs with comprehensive temporal reasoning (understanding, prediction, creative generation).
Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning
-
Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning
Paper • 2506.09033 • Published • 7 -
ulab-ai/Router-R1-Qwen2.5-3B-Instruct
3B • Updated • 28 • 2 -
ulab-ai/Router-R1-Qwen2.5-3B-Instruct-Alpha0.9
3B • Updated • 6 -
ulab-ai/Router-R1-Llama-3.2-3B-Instruct
4B • Updated • 5
PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling
-
ulab-ai/ResearchArcade-openreview-paragraphs
Viewer • Updated • 14.2k • 31 -
ulab-ai/ResearchArcade-openreview-papers-revisions
Viewer • Updated • 54.5k • 20 -
ulab-ai/ResearchArcade-openreview-reviews
Viewer • Updated • 472k • 41 • 1 -
ulab-ai/ResearchArcade-openreview-arxiv
Viewer • Updated • 28.6k • 30
Sotopia-RL: Reward Design for Social Intelligence
IRanker: Towards Ranking Foundation Model
Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning
-
Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning
Paper • 2506.09033 • Published • 7 -
ulab-ai/Router-R1-Qwen2.5-3B-Instruct
3B • Updated • 28 • 2 -
ulab-ai/Router-R1-Qwen2.5-3B-Instruct-Alpha0.9
3B • Updated • 6 -
ulab-ai/Router-R1-Llama-3.2-3B-Instruct
4B • Updated • 5
Time-R1: Framework and resources for endowing LLMs with comprehensive temporal reasoning (understanding, prediction, creative generation).