-
Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement
Paper • 2501.12273 • Published • 14 -
CritiQ: Mining Data Quality Criteria from Human Preferences
Paper • 2502.19279 • Published • 10 -
Instruction Pre-Training: Language Models are Supervised Multitask Learners
Paper • 2406.14491 • Published • 95
Eric NG
Eric108
AI & ML interests
NLP
Recent Activity
upvoted
a
paper
about 1 month ago
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains
RLVR
upvoted
a
paper
about 1 month ago
AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs
upvoted
a
paper
about 1 month ago
Deep Think with Confidence
Organizations
None yet