#qwen3
8 briefs tagged #qwen3.
OPD² improves multilingual math reasoning in Qwen3 tests
The arXiv study reports gains over OPD in English, Korean and Japanese math reasoning.
OPD2 improves multilingual math reasoning in Qwen3 tests
The distillation method beat OPD in English, Korean and Japanese math reasoning experiments.
Researchers refine on-policy distillation for smaller models
New arXiv papers propose capacity- and outcome-aware ways to guide student models.
Researchers refine on-policy distillation for AI agents
Three arXiv papers propose ways to make teacher guidance depend on downstream outcomes.
New papers probe self-distillation for LLM reinforcement learning
ArXiv reports propose ICE and OCSD while warning that privileged-information teachers can fail.
Researchers probe on-policy distillation for multilingual LLMs
New papers test OPD variants for math, ASR and low-resource reasoning across languages.
ARCHead targets LLM output-head compression
The method compresses LM-head storage without keeping a dense BF16 head, according to a new arXiv paper.
New papers test self-distillation for LLM reinforcement learning
Studies propose ICE and OCSD while warning that privileged-information teachers can fail on harder tasks.