English
Related papers

Related papers: HAD: Hybrid Architecture Distillation Outperforms …

200 papers

Adversarial training is a widely adopted strategy to bolster the robustness of neural network models against adversarial attacks. This paper revisits the fundamental assumptions underlying image classification and suggests that representing…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Erh-Chung Chen , Che-Rung Lee

Distilling vision-language models into faster hybrid architectures, such as 3:1 Mamba-2/attention mixes, is now standard practice for making inference efficient. Aggregate benchmarks suggest that this works but they hide selective failures.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yihao Liang , Niraj K. Jha

Self-supervised pre-trained models such as HuBERT and WavLM leverage unlabeled speech data for representation learning and offer significantly improve for numerous downstream tasks. Despite the success of these methods, their large memory…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-23 Yingying Gao , Shilei Zhang , Zihao Cui , Yanhan Xu , Chao Deng , Junlan Feng

Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising approach to reducing inference costs. However, achieving high-quality generation in distilled models requires careful joint…

Computation and Language · Computer Science 2026-03-30 Juan Gabriel Kostelec , Xiang Wang , Axel Laborieux , Christos Sourmpis , Qinghai Guo

Knowledge distillation has been applied to various tasks successfully. The current distillation algorithm usually improves students' performance by imitating the output of the teacher. This paper shows that teachers can also improve…

Computer Vision and Pattern Recognition · Computer Science 2022-07-06 Zhendong Yang , Zhe Li , Mingqi Shao , Dachuan Shi , Zehuan Yuan , Chun Yuan

Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-11 Cheng Cui , Ruoyu Guo , Yuning Du , Dongliang He , Fu Li , Zewu Wu , Qiwen Liu , Shilei Wen , Jizhou Huang , Xiaoguang Hu , Dianhai Yu , Errui Ding , Yanjun Ma

There have been numerous attempts to distill quadratic attention-based large language models (LLMs) into sub-quadratic linearized architectures. However, despite extensive research, such distilled models often fail to match the performance…

Transformer-based architectures have become the de-facto standard models for diverse vision tasks owing to their superior performance. As the size of the models continues to scale up, model distillation becomes extremely important in…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Cheng Han , Qifan Wang , Sohail A. Dianat , Majid Rabbani , Raghuveer M. Rao , Yi Fang , Qiang Guan , Lifu Huang , Dongfang Liu

Distillation has shown remarkable success in transferring knowledge from a Large Language Model (LLM) teacher to a student LLM. However, current distillation methods require similar tokenizers between the teacher and the student,…

Computation and Language · Computer Science 2025-10-27 Benjamin Minixhofer , Ivan Vulić , Edoardo Maria Ponti

Large pretrained language models have achieved state-of-the-art results on a variety of downstream tasks. Knowledge Distillation (KD) into a smaller student model addresses their inefficiency, allowing for deployment in resource-constrained…

Computation and Language · Computer Science 2023-10-17 Aashka Trivedi , Takuma Udagawa , Michele Merler , Rameswar Panda , Yousef El-Kurdi , Bishwaranjan Bhattacharjee

This paper studies the problem of pre-training for small models, which is essential for many mobile devices. Current state-of-the-art methods on this problem transfer the representational knowledge of a large network (as a Teacher) into a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Mingsheng Li , Lin Zhang , Mingzhen Zhu , Zilong Huang , Gang Yu , Jiayuan Fan , Tao Chen

Knowledge distillation (KD) is a powerful paradigm for compressing large language models (LLMs), whose effectiveness depends on intertwined choices of divergence direction, optimization strategy, and data regime. We break down the design of…

Computation and Language · Computer Science 2026-04-23 Wenhong Zhu , Ruobing Xie , Rui Wang , Pengfei Liu

Heterogeneous distillation is an effective way to transfer knowledge from cross-architecture teacher models to student models. However, existing heterogeneous distillation methods do not take full advantage of the dark knowledge hidden in…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Yaoxin Yang , Peng Ye , Weihao Lin , Kangcong Li , Yan Wen , Jia Hao , Tao Chen

Vision foundation models trained via multi-teacher distillation offer a promising path toward unified visual representations, yet the learning dynamics and data efficiency of such approaches remain underexplored. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Sofian Chaybouti , Sanath Narayan , Yasser Dahou , Phúc H. Lê Khac , Ankit Singh , Ngoc Dung Huynh , Wamiq Reyaz Para , Hilde Kuehne , Hakim Hacid

Recently, non-autoregressive (NAT) models predict outputs in parallel, achieving substantial improvements in generation speed compared to autoregressive (AT) models. While performing worse on raw data, most NAT models are trained as student…

Computation and Language · Computer Science 2021-12-23 Jiaxin Guo , Minghan Wang , Daimeng Wei , Hengchao Shang , Yuxia Wang , Zongyao Li , Zhengzhe Yu , Zhanglin Wu , Yimeng Chen , Chang Su , Min Zhang , Lizhi Lei , shimin tao , Hao Yang

The deployment and application of Large Language Models (LLMs) is hindered by their memory inefficiency, computational demands, and the high costs of API inferences. Traditional distillation methods, which transfer the capabilities of LLMs…

Computation and Language · Computer Science 2024-11-21 Yifei Zhang , Bo Pan , Chen Ling , Yuntong Hu , Liang Zhao

Large Language models (LLMs) have demonstrated impressive in-context learning (ICL) capabilities, where a LLM makes predictions for a given test input together with a few input-output pairs (demonstrations). Nevertheless, the inclusion of…

Computation and Language · Computer Science 2024-03-13 Yichuan Li , Xiyao Ma , Sixing Lu , Kyumin Lee , Xiaohu Liu , Chenlei Guo

Pre-trained speech language models such as HuBERT and WavLM leverage unlabeled speech data for self-supervised learning and offer powerful representations for numerous downstream tasks. Despite the success of these models, their high…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-24 Yingying Gao , Shilei Zhang , Chao Deng , Junlan Feng

Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. Meanwhile, the great need for capable aritificial intelligence on mobile devices also arises, such as the AI assistant software. Some…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Qianhan Feng , Wenshuo Li , Tong Lin , Xinghao Chen

The advent of large pre-trained language models has given rise to rapid progress in the field of Natural Language Processing (NLP). While the performance of these models on standard benchmarks has scaled with size, compression techniques…

Computation and Language · Computer Science 2021-05-14 Ahmad Rashid , Vasileios Lioutas , Mehdi Rezagholizadeh