On-policy distillation (OPD) trains a student on its own responses using token-level feedback from a teacher. As responses grow longer, the student's prefix can depart from the teacher's own reasoning, weakening its feedback on later tokens. Updates based on this feedback can reinforce the same deviations in later resp...
Jian-Nan Guan, You-Xin Jiang, Yu-Tai Hou et al.· 0 citations
CUE-Mem provides a testbed for memory systems that selectively retain, retrieve, and use subtle multimodal evidence, and provides a testbed for memory systems that selectively retain, retrieve, and use subtle multimodal evidence.
Yu-Lin Hu, Yan-Yan Zhao, Zi-Mo Long et al.· 0 citations
MIFS mitigates the generalization trade-offs typical of SFT, preserving core visual capabilities while significantly boosting instruction-following precision, and introduces a generative constraint protocol to synthesize diverse raw samples.
Yi-Rong Zeng, Sai Zhang, Yu-Xian Wang et al.· 1 citation
EnvCraft is introduced, an automated framework for synthesizing executable environments and scalable training data that confirms that synthesized executable environments provide robust and generalizable learning signals for training.
Yi-Rong Zeng, Shen You, Jin-Hang Feng et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
