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
Recent Activity
upvoted
a
paper
about 1 month ago
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
upvoted
a
paper
about 1 month ago
Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
upvoted
a
paper
about 1 month ago
Clean First, Align Later: Benchmarking Preference Data Cleaning for
Reliable LLM Alignment
Organizations
upvoted
4
papers
about 1 month ago
Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
Paper
•
2509.23050
•
Published
•
14
Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment
Paper
•
2509.23564
•
Published
•
7
LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals
Paper
•
2509.21875
•
Published
•
9