Persistent 'Rock Tokens' in on-policy distillation resist teacher corrections, consume large gradient norms, yet add negligible value to reasoning, allowing targeted bypassing to streamline alignment.
Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Training student models on synthetic data generated by strong teacher models is a promising way to distilling the capabilities of teachers. However, recent studies show that stronger models are not always optimal teachers, revealing a mismatch between teacher outputs and student learnability. To address this issue, we propose PerSyn (Personalized data Synthesis), a novel synthesis strategy that operates under a new ``Route then Generate'' paradigm to create data tailored to each student model, enabling it to learn more effectively. Specifically, PerSyn first assigns each prompt to its optimal teacher via a query-level router that jointly considers student learnability and teacher response quality. Each teacher then synthesizes data only for its assigned prompts, making the process more efficient than the conventional ``Generate then Select'' paradigm, where all teachers must generate parallel responses for the entire prompt set before constructing the final dataset. Extensive experiments across different model families and scales demonstrate that PerSyn consistently achieves superior or comparable performance to all baselines in instruct tuning and math reasoning settings. Further analysis verifies the effectiveness of PerSyn and offers extra insights to propel future research.
years
2026 3verdicts
UNVERDICTED 3representative citing papers
MUSE decouples reconstruction and semantic learning in visual tokenization via topological orthogonality, yielding SOTA generation quality and improved semantic performance over its teacher model.
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.
citing papers explorer
-
Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation
Persistent 'Rock Tokens' in on-policy distillation resist teacher corrections, consume large gradient norms, yet add negligible value to reasoning, allowing targeted bypassing to streamline alignment.
-
MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality
MUSE decouples reconstruction and semantic learning in visual tokenization via topological orthogonality, yielding SOTA generation quality and improved semantic performance over its teacher model.
-
Reinforcement Learning for Scalable and Trustworthy Intelligent Systems
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.