English
Related papers

Related papers: From Fact Overwriting to Knowledge Evolution: Caus…

200 papers

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive…

Computation and Language · Computer Science 2024-07-04 Jongwoo Ko , Sungnyun Kim , Tianyi Chen , Se-Young Yun

Knowledge distillation is a method of transferring the knowledge from a pretrained complex teacher model to a student model, so a smaller network can replace a large teacher network at the deployment stage. To reduce the necessity of…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Mingi Ji , Seungjae Shin , Seunghyun Hwang , Gibeom Park , Il-Chul Moon

Edge computation offloading allows mobile end devices to put execution of compute-intensive task on the edge servers. End devices can decide whether offload the tasks to edge servers, cloud servers or execute locally according to current…

Networking and Internet Architecture · Computer Science 2020-04-10 Haowei Chen , Liekang Zeng , Shuai Yu , Xu Chen

Modern Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks by employing search-augmented reasoning to incorporate external knowledge into long chains of thought. However, we identify a critical yet…

Computation and Language · Computer Science 2026-02-11 Sangwon Yu , Ik-hwan Kim , Donghun Kang , Bongkyu Hwang , Junhwa Choi , Suk-hoon Jung , Seungki Hong , Taehee Lee , Sungroh Yoon

In-context learning (ICL) allows large language models (LLMs) to solve novel tasks without weight updates. Despite its empirical success, the mechanism behind ICL remains poorly understood, limiting our ability to interpret, improve, and…

Machine Learning · Computer Science 2025-06-16 Chengye Li , Haiyun Liu , Yuanxi Li

On-policy distillation (OPD) is an increasingly important paradigm for post-training language models. However, we identify a pervasive Scaling Law of Miscalibration: while OPD effectively improves task accuracy, it systematically traps…

Machine Learning · Computer Science 2026-04-21 Jiaxin Zhang , Xiangyu Peng , Qinglin Chen , Qinyuan Ye , Caiming Xiong , Chien-Sheng Wu

Collaborative learning of large language models (LLMs) has emerged as a new paradigm for utilizing private data from different parties to guarantee efficiency and privacy. Meanwhile, Knowledge Editing (KE) for LLMs has also garnered…

Computation and Language · Computer Science 2025-02-25 Jiamu Zheng , Jinghuai Zhang , Tianyu Du , Xuhong Zhang , Jianwei Yin , Tao Lin

Knowledge distillation (KD) improves the performance of a low-complexity student model with the help of a more powerful teacher. The teacher in KD is a black-box model, imparting knowledge to the student only through its predictions. This…

Machine Learning · Computer Science 2023-10-05 Sayantan Chowdhury , Ben Liang , Ali Tizghadam , Ilijc Albanese

Knowledge Distillation (KD) is increasingly adopted to transfer capabilities from large language models to smaller ones, offering significant improvements in efficiency and utility while often surpassing standard fine-tuning. Beyond…

Dataset distillation aims to synthesize a compact dataset from the original large-scale one, enabling highly efficient learning while preserving competitive model performance. However, traditional techniques primarily capture low-level…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Qianxin Xia , Jiawei Du , Guoming Lu , Zhiyong Shu , Jielei Wang

Enabling artificial intelligence systems, particularly large language models, to integrate new knowledge and flexibly apply it during reasoning remains a central challenge. Existing knowledge editing approaches emphasize atomic facts,…

Artificial Intelligence · Computer Science 2026-02-03 Ya Gao , Kalle Kujanpää , Pekka Marttinen , Harri Valpola , Alexander Ilin

Large Language Models (LLMs) have demonstrated impressive capability in different tasks and are bringing transformative changes to many domains. However, keeping the knowledge in LLMs up-to-date remains a challenge once pretraining is…

Computation and Language · Computer Science 2024-07-24 Xiou Ge , Ali Mousavi , Edouard Grave , Armand Joulin , Kun Qian , Benjamin Han , Mostafa Arefiyan , Yunyao Li

Knowledge distillation is typically realized by transferring a teacher model's knowledge into a student's parameters through supervised or reinforcement-based optimization. While effective, such approaches require repeated parameter updates…

Machine Learning · Computer Science 2026-03-31 Shuozhi Yuan , Jinqing Wang , Zihao Liu , Miaomiao Yuan , Haoran Peng , Jin Zhao , Bingwen Wang , Haoyi Wang

Large language models (LLMs) excel at factual recall yet still propagate stale or incorrect knowledge. In-context knowledge editing offers a gradient-free remedy suitable for black-box APIs, but current editors rely on static demonstration…

Computation and Language · Computer Science 2025-10-28 Mahmud Wasif Nafee , Maiqi Jiang , Haipeng Chen , Yanfu Zhang

Data-free knowledge distillation (DFKD) has emerged as a pivotal technique in the domain of model compression, substantially reducing the dependency on the original training data. Nonetheless, conventional DFKD methods that employ…

Computer Vision and Pattern Recognition · Computer Science 2024-10-24 Muquan Li , Dongyang Zhang , Tao He , Xiurui Xie , Yuan-Fang Li , Ke Qin

Knowledge distillation (KD) is a substantial strategy for transferring learned knowledge from one neural network model to another. A vast number of methods have been developed for this strategy. While most method designs a more efficient…

Machine Learning · Computer Science 2022-03-22 Yen-Chang Hsu , James Smith , Yilin Shen , Zsolt Kira , Hongxia Jin

Many applications of reinforcement learning can be formalized as goal-conditioned environments, where, in each episode, there is a "goal" that affects the rewards obtained during that episode but does not affect the dynamics. Various…

Machine Learning · Computer Science 2023-03-09 Alexander Levine , Soheil Feizi

Knowledge Editing (KE) for modifying factual knowledge in Large Language Models (LLMs) has been receiving increasing attention. However, existing knowledge editing methods are entity-centric, and it is unclear whether this approach is…

Computation and Language · Computer Science 2023-11-16 Yifan Wei , Xiaoyan Yu , Huanhuan Ma , Fangyu Lei , Yixuan Weng , Ran Song , Kang Liu

Originally proposed as a method for knowledge transfer from one model to another, some recent studies have suggested that knowledge distillation (KD) is in fact a form of regularization. Perhaps the strongest argument of all for this new…

Machine Learning · Computer Science 2023-10-26 Md Arafat Sultan

Conditioning image generation facilitates seamless editing and the creation of photorealistic images. However, conditioning on noisy or Out-of-Distribution (OoD) images poses significant challenges, particularly in balancing fidelity to the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-23 Bastien van Delft , Tommaso Martorella , Alexandre Alahi