Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation
Sharath Turuvekere Sreenivas, Adithyakrishna Venkatesh Hanasoge, Mingyu Yang +4
Cross-tokenizer knowledge distillation allows a student model to learn from teachers with incompatible vocabularies. Prior work operates on hidden states or logits; the latter is p…
cs.LG2026
DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off
Xiaofan Li, Ming Yang, Zhiyuan Ma +9
Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed significant advances in the reasoning capabilities of Large Language Models (LLMs). However, effectively managin…