English
Related papers

Related papers: Disposition Distillation at Small Scale: A Three-A…

200 papers

Small Language Models (SLMs, under 10B parameters) are attractive for private, on-device deployment, yet they frequently fail on strict constraint-satisfaction problems due to linear, overconfident reasoning traces that do not recover from…

Computation and Language · Computer Science 2026-01-22 Aradhya Dixit , Tianxi Liang , Jai Telang

On-policy distillation is a promising approach for transferring knowledge between language models, where a student learns from dense token-level signals along its own trajectories. This framework typically uses reverse KL divergence,…

Machine Learning · Computer Science 2026-05-25 Woogyeol Jin , Taywon Min , Yongjin Yang , Swanand Ravindra Kadhe , Yi Zhou , Dennis Wei , Nathalie Baracaldo , Kimin Lee

We demonstrate that in knowledge distillation for diffusion models, the teacher network's highly complex denoising process - stemming from its substantially larger capacity - poses a significant challenge for the student model to faithfully…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Hyunsoo Han , Sangyeop Yeo , Jaejun Yoo

R1-style Reinforcement Learning (RL) significantly enhances Large Language Models' reasoning capabilities, yet the mechanism behind rule-based RL remains unclear. We found that small-scale SFT has substantial influence on RL but shows poor…

Machine Learning · Computer Science 2025-08-06 Yutong Chen , Jiandong Gao , Ji Wu

Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To address this, we extend Inverse Distillation, a technique…

Machine Learning · Computer Science 2026-02-24 David Li , Nikita Gushchin , Dmitry Abulkhanov , Eric Moulines , Ivan Oseledets , Maxim Panov , Alexander Korotin

Large Language Models (LLMs) have transformed listwise document reranking by enabling global reasoning over candidate sets, yet single models often struggle to balance fine-grained relevance scoring with holistic cross-document analysis. We…

Computation and Language · Computer Science 2025-08-26 Abdelrahman Abdallah , Jamshid Mozafari , Bhawna Piryani , Adam Jatowt

Distillation has emerged as a practical and effective approach to enhance the reasoning capabilities of open-source language models. In this work, we conduct a large-scale empirical study on reasoning data distillation by collecting…

Computation and Language · Computer Science 2025-05-23 Xiaoyu Tian , Yunjie Ji , Haotian Wang , Shuaiting Chen , Sitong Zhao , Yiping Peng , Han Zhao , Xiangang Li

Knowledge distillation has been shown to be a powerful model compression approach to facilitate the deployment of pre-trained language models in practice. This paper focuses on task-agnostic distillation. It produces a compact pre-trained…

Computation and Language · Computer Science 2023-02-21 Chen Liang , Haoming Jiang , Zheng Li , Xianfeng Tang , Bin Yin , Tuo Zhao

To improve the performance of the dual-encoder retriever, one effective approach is knowledge distillation from the cross-encoder ranker. Existing works construct the candidate passages following the supervised learning setting where a…

Computation and Language · Computer Science 2024-06-07 Chongyang Tao , Chang Liu , Tao Shen , Can Xu , Xiubo Geng , Binxing Jiao , Daxin Jiang

Due to constraints on privacy, cost, and latency, on-premise deployment of small models is increasingly common. However, most practical pipelines stop at supervised fine-tuning (SFT) and fail to reach the reinforcement learning (RL)…

Convolutional neural networks (CNNs) have achieved a great success in face recognition, which unfortunately comes at the cost of massive computation and storage consumption. Many compact face recognition networks are thus proposed to…

Computer Vision and Pattern Recognition · Computer Science 2019-05-21 Yushu Feng , Huan Wang , Daniel T. Yi , Roland Hu

Dataset distillation aims to condense large datasets into a small number of synthetic examples that can be used as drop-in replacements when training new models. It has applications to interpretability, neural architecture search, privacy,…

Machine Learning · Computer Science 2024-06-24 Andrei Lupu , Chris Lu , Jarek Liesen , Robert Tjarko Lange , Jakob Foerster

Adapter-Tuning (AT) method involves freezing a pre-trained model and introducing trainable adapter modules to acquire downstream knowledge, thereby calibrating the model for better adaptation to downstream tasks. This paper proposes a…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Jiacheng Ruan , Jingsheng Gao , Mingye Xie , Daize Dong , Suncheng Xiang , Ting Liu , Yuzhuo Fu

Large Language Models are routinely compressed via post-training quantization to reduce inference costs and memory footprint for cloud and edge deployment, yet the impact of this compression on model quality remains poorly understood.…

Machine Learning · Computer Science 2026-05-18 Plawan Kumar Rath , Rahul Maliakkal

Alignment techniques enable Large Language Models (LLMs) to generate outputs that align with human preferences and play a crucial role in their effectiveness. However, their impact often diminishes when applied to Small Language Models…

Computation and Language · Computer Science 2025-03-06 Shiping Gao , Fanqi Wan , Jiajian Guo , Xiaojun Quan , Qifan Wang

Minimizing prediction uncertainty on unlabeled data is a key factor to achieve good performance in semi-supervised learning (SSL). The prediction uncertainty is typically expressed as the \emph{entropy} computed by the transformed…

Machine Learning · Computer Science 2021-12-16 Jing Li , Yuangang Pan , Ivor W. Tsang

Healthcare providers are increasingly using machine learning to predict patient outcomes to make meaningful interventions. However, despite innovations in this area, deep learning models often struggle to match performance of shallow linear…

Machine Learning · Computer Science 2020-12-18 Rohan S. Kodialam , Rebecca Boiarsky , Justin Lim , Neil Dixit , Aditya Sai , David Sontag

Recently, transformer-based methods have achieved state-of-the-art prediction quality on human pose estimation(HPE). Nonetheless, most of these top-performing transformer-based models are too computation-consuming and storage-demanding to…

Computer Vision and Pattern Recognition · Computer Science 2024-04-05 Sichen Chen , Yingyi Zhang , Siming Huang , Ran Yi , Ke Fan , Ruixin Zhang , Peixian Chen , Jun Wang , Shouhong Ding , Lizhuang Ma

Language models rely on semantic priors to perform in-context learning, which leads to poor performance on tasks involving inductive reasoning. Instruction-tuning methods based on imitation learning can superficially enhance the in-context…

Computation and Language · Computer Science 2025-04-16 Nafis Sadeq , Xin Xu , Zhouhang Xie , Julian McAuley , Byungkyu Kang , Prarit Lamba , Xiang Gao

Large language models are increasingly used as behavioral simulators, but it remains unclear when their outputs reflect human-like cognitive mechanisms rather than prompt-sensitive surface patterns. We study this question through the…

Artificial Intelligence · Computer Science 2026-05-26 Ciarán Walsh , Emilio Barkett