Establishing Task Scaling Laws via Compute-Efficient Model Ladders
Paper
•
2412.04403
•
Published
•
2
Jiacheng Liu
liujch1998
AI & ML interests
NLP
Recent Activity
authored
a paper
6 days ago
Don't throw away your value model! Making PPO even better via
Value-Guided Monte-Carlo Tree Search decoding
authored
a paper
6 days ago
MathVista: Evaluating Mathematical Reasoning of Foundation Models in
Visual Contexts
authored
a paper
6 days ago
Crystal: Introspective Reasoners Reinforced with Self-Feedback
Organizations
