Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
Paper • 2510.07242 • Published • 30
Hengxiang Zhang
hxiang
AI & ML interests
None yet
Organizations
upvoted 4
papers 8 months ago
Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
Paper • 2509.23050 • Published • 15
Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment
Paper • 2509.23564 • Published • 8
LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals
Paper • 2509.21875 • Published • 10