DFQI transfers knowledge for offline Q-learning
The method integrates source data via L1 penalty in target Q-function updates to improve policy learning with limited target data in marketing and healthcare.
Stories per day · 30 days
1 RSS
Relatedfitted-iteration1image-generation1multimodal-models1offline-reinforcement-learning1q-learning1question-answering1
5 stories, newest first · one card per story
Stories tagged #knowledge-transfer
Paper tests whether image generation expands model knowledge
Across seven knowledge categories and three unified models, visual supervision transferred unevenly into text-only question answering.
On-Policy Distillation Teaches New Skills but Not New Knowledge
On-policy distillation transfers compositional reasoning skill but little new factual knowledge under reverse KL.
MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code
MetaKernelBench measures whether GPU kernel skills transfer across CuTe and TIRx on 74 problems.
Coupled Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward Feedback
CCL couples teacher calibration with student updates via token-level branching, provably removing teacher bias in LLM distillation.