α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Zhile Ren
Zhile Ren
1
Affiliations
Affiliations
Apple
3
papers
163
total citations
papers (3)
DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search
ICLR 2025
arXiv
142
citations
MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization
ICLR 2025
arXiv
16
citations
CommVQ: Commutative Vector Quantization for KV Cache Compression
ICML 2025
arXiv
5
citations