arXiv AI

DASH: Dual-Branch Score Distillation for Guidance-Calibrated Compact Diffusion Models

arXiv:2606. 00798v1 Announce Type: cross Abstract: Parameter compression of class-conditional diffusion models reveals an underexplored limitation in output-level distillation: the unconditional score branch remains unsupervised, leaving the classifier-free guidance gap underdetermined in the student.

arXiv AI

Jul 20

When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models

arXiv:2603. 26556v2 Announce Type: replace-cross Abstract: Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising approach to reducing inference costs.

By Juan Gabriel Kostelec, Qinghai Guo

llms efficiency benchmarks

arXiv AI

Jul 28

Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation

arXiv:2607. 24731v1 Announce Type: cross Abstract: On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guidance (CFG), a default component of modern diffusion systems, remains poorly understood.

By Bingnan Li, Haozhe Wang, Haozhong Xiong, Fangtai Wu, Jinpeng Yu, Yang Shi, Jiaming Liu, Ruihua Huang

diffusion efficiency

arXiv AI

Jun 9

Trajectory-Refined Distillation

arXiv:2606. 08432v1 Announce Type: new Abstract: On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision along the student's own rollouts.

By Li Jiang, Haoran Xu, Yichuan Ding, Amy Zhang

llms efficiency benchmarks

arXiv AI

5d ago

Rethinking Normalization Placement for LLMs: Post-Norm under Curriculum Depth Growing

arXiv:2608. 13156v1 Announce Type: new Abstract: Pre-norm is the standard normalization placement in modern Transformers because it facilitates joint optimization of full-depth models.

By Sheng Ren, Yadong Wang, Naiqiang Tan, Jiangang Kong, Jun Fang, Rui Liu, Jun Wang, Kai Chen, Lipeng Liang, Xiang Chen

llms efficiency

arXiv Machine Learning

Jun 2

Single-Channel Tissue Segmentation via Cross-Modal Distillation from Foundation Models

arXiv:2606. 00928v1 Announce Type: cross Abstract: Multiplexed fluorescence microscopy improves tissue segmentation by providing complementary channels including nuclear (DAPI) and membrane (E-cadherin), that together encode richer spatial context than single-channel imaging alone.

By Sakib Mohammad, Jarin Ritu, Md Sakhawat Hossain

computer-vision efficiency multimodal

arXiv Machine Learning

Jul 7

Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe

arXiv:2605. 03677v2 Announce Type: replace Abstract: On-policy distillation (OPD) has recently emerged as an effective post-training paradigm for consolidating the capabilities of specialized expert models into a single student model.

By Wenjin Hou, Shangpin Peng, Weinong Wang, Zheng Ruan, Yue Zhang, Zhenglin Zhou, Mingqi Gao, Yifei Chen, Kaiqi Wang, Hongming Yang, Chengquan Zhang, Zhuotao Tian, Han Hu, Yi Yang, Fei Wu, Hehe Fan

llms efficiency multimodal benchmarks

arXiv AI

Aug 11

WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training

arXiv:2608. 09447v1 Announce Type: cross Abstract: On-policy distillation (OPD) aligns a student with a teacher on trajectories sampled from the student itself, reducing the train-test state mismatch of offline distillation.

By Zehao Chen, Gongxun Li, Tianxiang Ai, Yifei Li, Zixuan Huang, Wang Zhou, Tao Huang, Fuzhen Zhuang, Xianglong Liu, Jianxin Li, Deqing Wang, Yikun Ban

efficiency

arXiv AI

1d ago

Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning

arXiv:2608. 16333v1 Announce Type: cross Abstract: On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories.

By Changhui Sun, Lanbo Liu, Hang Lei, Tong Ling, Jiahang Xie, Zhiyong Zheng, Yujia Wang, Hao Liu, Feng Xiao, Lu Liu, Yanlong Du, Zifeng Cheng, Ziwei Jiang, Qing Gu

agents fine-tuning efficiency

arXiv Machine Learning

Aug 11

Adaptive Supervised Anchoring for On-Policy Self-Distillation

arXiv:2608. 07935v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) adapts a language model by distilling guidance from a frozen teacher on trajectories sampled from the student.

By Meilin Yang (Renmin University of China, Beijing, China), Zixuan Ding (Renmin University of China, Beijing, China), Jianhao Nie (Renmin University of China, Beijing, China), Weite Zhang (Renmin University of China, Beijing, China), Yuxin Zhang (Renmin University of China, Beijing, China), Zhiming Shao (Renmin University of China, Beijing, China), Li Yu (Renmin University of China, Beijing, China), Zhe Fu (Renmin University of China, Beijing, China)

llms efficiency benchmarks safety

arXiv AI

Jun 2

SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting

arXiv:2604. 10688v2 Announce Type: replace-cross Abstract: On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewards make token-level credit assignment notoriously difficult.

By Binbin Zheng, Xing Ma, Yiheng Liang, Jingqing Ruan, Xiaoliang Fu, Kepeng Lin, Benchang Zhu, Ke Zeng, Xunliang Cai

llms reinforcement-learning efficiency benchmarks safety

arXiv AI

Jun 24

ARIA: Adaptive Region-Based Importance Allocation for Conditional Diffusion Distillation

arXiv:2606. 23898v1 Announce Type: cross Abstract: Distilling conditional diffusion models aims to transfer the behavior of a large teacher to a smaller student while preserving alignment across conditioning inputs.

By Loay Mualem, Vinh Tong, Samir Darouich, Mathias Niepert

diffusion efficiency safety

arXiv Machine Learning

Aug 4

Prefix-Guided On-Policy Distillation: Mining Golden Trajectories from Rollouts

arXiv:2606. 21994v2 Announce Type: replace Abstract: On-policy distillation (OPD) improves reasoning models by applying dense teacher supervision on student-sampled trajectories.

By Qingfei Zhao, Huan Song, Shuyu Tian, Jiawei Shao, Xuelong Li

efficiency benchmarks

Related stories