Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
Paper
•
2503.07572
•
Published
•
17
Lei Wang
demolei
AI & ML interests
LLMs
Recent Activity
upvoted
a
paper
about 15 hours ago
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
upvoted
a
paper
about 15 hours ago
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through
Two-Stage Rule-Based RL
Organizations
demolei's activity
upvoted
2
papers
about 15 hours ago
upvoted
a
paper
1 day ago
upvoted
a
collection
6 days ago
upvoted
5
papers
6 days ago
Efficient Test-Time Scaling via Self-Calibration
Paper
•
2503.00031
•
Published
•
13
Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
Paper
•
2503.01307
•
Published
•
31
Visual-RFT: Visual Reinforcement Fine-Tuning
Paper
•
2503.01785
•
Published
•
64
Process-based Self-Rewarding Language Models
Paper
•
2503.03746
•
Published
•
35
START: Self-taught Reasoner with Tools
Paper
•
2503.04625
•
Published
•
83
upvoted
2
papers
9 days ago
upvoted
a
paper
13 days ago
upvoted
5
papers
15 days ago
OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning
Paper
•
2502.11271
•
Published
•
16
Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
Paper
•
2502.12215
•
Published
•
16
Small Models Struggle to Learn from Strong Reasoners
Paper
•
2502.12143
•
Published
•
28
S^2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
Paper
•
2502.12853
•
Published
•
28
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
Paper
•
2502.14768
•
Published
•
45
upvoted
a
paper
17 days ago
upvoted
2
papers
19 days ago