PACED: Distillation at the Frontier of Student Competence
Paper
• 2603.11178 • Published
• 3
XYX
xuyd16
AI & ML interests
None yet
Recent Activity
submitted
a paper
about 5 hours ago
PACED: Distillation at the Frontier of Student Competence authored
a paper
about 9 hours ago
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning authored
a paper
about 9 hours ago
On-Policy Self-Distillation for Reasoning Compression Organizations
None yet
submitted a paper to Daily Papers about 5 hours ago
authored 4 papers about 9 hours ago
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
Paper
• 2602.21420 • Published
• 6
On-Policy Self-Distillation for Reasoning Compression
Paper
• 2603.05433 • Published
• 5
Not all tokens are needed(NAT): token efficient reinforcement learning
Paper
• 2603.06619 • Published
PACED: Distillation at the Frontier of Student Competence
Paper
• 2603.11178 • Published
• 3