English
Related papers

Related papers: Adaptive Teacher Exposure for Self-Distillation in…

200 papers

Large Language Models (LLMs) have exhibited impressive capabilities in various tasks, yet their vast parameter sizes restrict their applicability in resource-constrained settings. Knowledge distillation (KD) offers a viable solution by…

Computation and Language · Computer Science 2024-06-07 Rongzhi Zhang , Jiaming Shen , Tianqi Liu , Haorui Wang , Zhen Qin , Feng Han , Jialu Liu , Simon Baumgartner , Michael Bendersky , Chao Zhang

Reinforcement learning (RL) has emerged as a promising paradigm for inducing explicit reasoning behaviors in large language and vision-language models. However, reasoning-oriented RL post-training remains fundamentally challenging due to…

Artificial Intelligence · Computer Science 2026-05-13 Fan Yang , Rui Meng , Trudi Di Qi , Ali Ezzati , Yuxin Wen

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

Knowledge Distillation (KD) has been considered as a key solution in model compression and acceleration in recent years. In KD, a small student model is generally trained from a large teacher model by minimizing the divergence between the…

Machine Learning · Computer Science 2021-11-16 Raed Alharbi , Minh N. Vu , My T. Thai

Post-training of language models (LMs) increasingly relies on the following two stages: (i) knowledge distillation, where the LM is trained to imitate a larger teacher LM, and (ii) reinforcement learning from human feedback (RLHF), where…

Machine Learning · Computer Science 2025-02-06 Daniil Tiapkin , Daniele Calandriello , Johan Ferret , Sarah Perrin , Nino Vieillard , Alexandre Ramé , Mathieu Blondel

We introduce a novel approach to large language model (LLM) distillation by formulating it as a constrained reinforcement learning problem. While recent work has begun exploring the integration of task-specific rewards into distillation…

Machine Learning · Computer Science 2025-09-30 Matthieu Zimmer , Xiaotong Ji , Tu Nguyen , Haitham Bou Ammar

Knowledge distillation (KD) compresses the network capacity by transferring knowledge from a large (teacher) network to a smaller one (student). It has been mainstream that the teacher directly transfers knowledge to the student with its…

In this work, we investigate the implicit regularization induced by teacher-student learning dynamics in self-distillation. To isolate its effect, we describe a simple experiment where we consider teachers at random initialization instead…

Machine Learning · Computer Science 2023-07-06 Felix Sarnthein , Gregor Bachmann , Sotiris Anagnostidis , Thomas Hofmann

Knowledge distillation is central to LLM post-training, yet its design space remains poorly understood, especially alongside reinforcement learning (RL). We show that the prevailing paradigms, off-policy distillation and on-policy…

Machine Learning · Computer Science 2026-05-19 Anhao Zhao , Haoran Xin , Yingqi Fan , Junlong Tong , Wenjie Li , Xiaoyu Shen

Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, have been proposed to acquire powerful and general representations from unlabeled data. However, these models are commonly pretrained…

Computer Vision and Pattern Recognition · Computer Science 2023-12-20 Yuang Liu , Jing Wang , Qiang Zhou , Fan Wang , Jun Wang , Wei Zhang

In learning-to-rank problems, a privileged feature is one that is available during model training, but not available at test time. Such features naturally arise in merchandised recommendation systems; for instance, "user clicked this item"…

Machine Learning · Computer Science 2022-09-20 Shuo Yang , Sujay Sanghavi , Holakou Rahmanian , Jan Bakus , S. V. N. Vishwanathan

While neural end-to-end text-to-speech (TTS) is superior to conventional statistical methods in many ways, the exposure bias problem in the autoregressive models remains an issue to be resolved. The exposure bias problem arises from the…

Computation and Language · Computer Science 2020-02-21 Rui Liu , Berrak Sisman , Jingdong Li , Feilong Bao , Guanglai Gao , Haizhou Li

Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent methods have shown promising gains, they typically rely on static teacher-student hierarchies…

Machine Learning · Computer Science 2026-05-12 Khouloud Saadi , Di Wang

Adversarial Distillation aims to enhance student robustness by guiding the student with a robust teacher's soft labels within the min-max adversarial training framework, yet its success is notoriously inconsistent: a more robust teacher…

Machine Learning · Computer Science 2026-05-22 Hongsin Lee , Hye Won Chung

Representation-based retrieval models, so-called bi-encoders, estimate the relevance of a document to a query by calculating the similarity of their respective embeddings. Current state-of-the-art bi-encoders are trained using an expensive…

Information Retrieval · Computer Science 2025-06-24 Lukas Gienapp , Niklas Deckers , Martin Potthast , Harrisen Scells

Despite the success of distillation in large language models (LLMs), most prior work applies identical loss functions to both teacher- and student-generated data. These strategies overlook the synergy between loss formulations and data…

Computation and Language · Computer Science 2025-06-02 Jongwoo Ko , Tianyi Chen , Sungnyun Kim , Tianyu Ding , Luming Liang , Ilya Zharkov , Se-Young Yun

Traditional approaches to RL have focused on learning decision policies directly from episodic decisions, while slowly and implicitly learning the semantics of compositional representations needed for generalization. While some approaches…

Computation and Language · Computer Science 2022-12-23 Chris Lengerich , Gabriel Synnaeve , Amy Zhang , Hugh Leather , Kurt Shuster , François Charton , Charysse Redwood

Large language models trained with reinforcement learning (RL) for mathematical reasoning face a fundamental challenge: on problems the model cannot solve at all - "cliff" prompts - the RL gradient vanishes entirely, preventing any learning…

Machine Learning · Computer Science 2026-03-26 Ken Ding

Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories. While reinforcement learning with…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Hao Lin , Kunyang Lv , Xu Jiang , Jingqi Tian , Zhongjing Du , Jiayu Ding , Qiaoman Zhang , Hongbo Jin

Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student"…

Artificial Intelligence · Computer Science 2023-01-31 Chaochen Gao , Xing Wu , Peng Wang , Jue Wang , Liangjun Zang , Zhongyuan Wang , Songlin Hu