English
Related papers

Related papers: WST: Weak-to-Strong Knowledge Transfer via Reinfor…

200 papers

With Large Language Models (LLMs) rapidly approaching and potentially surpassing human-level performance, it has become imperative to develop approaches capable of effectively supervising and enhancing these powerful models using smaller,…

Machine Learning · Computer Science 2025-06-06 Aakriti Agrawal , Mucong Ding , Zora Che , Chenghao Deng , Anirudh Satheesh , Bang An , Bayan Bruss , John Langford , Furong Huang

Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional modules to capture…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Haoxing Chen , Zizheng Huang , Yan Hong , Yanshuo Wang , Zhongcai Lyu , Zhuoer Xu , Jun Lan , Zhangxuan Gu

We present a new method LiST is short for Lite Prompted Self-Training for parameter-efficient fine-tuning of large pre-trained language models (PLMs) for few-shot learning. LiST improves over recent methods that adopt prompt-based…

Computation and Language · Computer Science 2022-05-20 Yaqing Wang , Subhabrata Mukherjee , Xiaodong Liu , Jing Gao , Ahmed Hassan Awadallah , Jianfeng Gao

Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of…

Distilling the tool-using capabilities of large language models (LLMs) into smaller, more efficient small language models (SLMs) is a key challenge for their practical application. The predominant approach, supervised fine-tuning (SFT),…

Computation and Language · Computer Science 2025-10-29 ChangSu Choi , Hoyun Song , Dongyeon Kim , WooHyeon Jung , Minkyung Cho , Sunjin Park , NohHyeob Bae , Seona Yu , KyungTae Lim

In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation…

Computation and Language · Computer Science 2020-12-15 Fei Yuan , Linjun Shou , Jian Pei , Wutao Lin , Ming Gong , Yan Fu , Daxin Jiang

Training reasoning language models (LMs) with reinforcement learning (RL) for one-hot correctness inherently relies on the LM being able to explore and solve its task with some chance at initialization. Furthermore, a key use case of…

Machine Learning · Computer Science 2025-10-30 Edoardo Cetin , Tianyu Zhao , Yujin Tang

Large language models have shown their ability to become effective few-shot learners with prompting, revolutionizing the paradigm of learning with data scarcity. However, this approach largely depends on the quality of prompt…

Computation and Language · Computer Science 2024-10-04 Xiaoming Liu , Chen Liu , Zhaohan Zhang , Chengzhengxu Li , Longtian Wang , Yu Lan , Chao Shen

As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow highly confident, further training yields diminishing returns. While existing methods continue…

Artificial Intelligence · Computer Science 2026-02-10 Zehao Chen , Gongxun Li , Tianxiang Ai , Yifei Li , Zixuan Huang , Wang Zhou , Fuzhen Zhuang , Xianglong Liu , Jianxin Li , Deqing Wang , Yikun Ban

Weak-to-strong (W2S) generalization is a type of finetuning (FT) where a strong (large) student model is trained on pseudo-labels generated by a weak teacher. Surprisingly, W2S FT often outperforms the weak teacher. We seek to understand…

Machine Learning · Computer Science 2026-04-21 Yijun Dong , Yicheng Li , Yunai Li , Jason D. Lee , Qi Lei

The goal of diffusion generative models is to align the learned distribution with the real data distribution through gradient score matching. However, inherent limitations in training data quality, modeling strategies, and architectural…

Machine Learning · Computer Science 2025-04-25 Lichen Bai , Masashi Sugiyama , Zeke Xie

Weak-to-Strong generalization (W2SG) is a new trend to elicit the full capabilities of a strong model with supervision from a weak model. While existing W2SG studies focus on simple tasks like binary classification, we extend this paradigm…

Machine Learning · Computer Science 2026-03-10 Ruimeng Ye , Zihan Wang , Yang Xiao , Zinan Ling , Manling Li , Bo Hui

Recent years have witnessed remarkable progress in world models, which primarily aim to capture the spatio-temporal correlations between an agent's actions and the evolving environment. However, existing approaches often suffer from tight…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Guangfeng Jiang , Yueru Luo , Jun Liu , Yi Huang , Yiyao Zhu , Zhan Qu , Dave Zhenyu Chen , Bingbing Liu , Xu Yan

Large language models excel at complex instructions yet struggle to deviate from their helpful assistant persona, as post-training instills strong priors that resist conflicting instructions. We introduce system prompt strength, a…

Computation and Language · Computer Science 2026-01-13 Yijiang River Dong , Tiancheng Hu , Zheng Hui , Nigel Collier

Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…

Computation and Language · Computer Science 2026-03-11 Yen-Ju Lu , Yashesh Gaur , Wei Zhou , Benjamin Muller , Jesus Villalba , Najim Dehak , Luke Zettlemoyer , Gargi Ghosh , Mike Lewis , Srinivasan Iyer , Duc Le

How can "weak teacher models" such as average human annotators or existing AI systems, effectively supervise LLMs to improve performance on hard reasoning tasks, especially those that challenge and requires expertise or daily practice from…

Machine Learning · Computer Science 2025-02-26 Xuan He , Da Yin , Nanyun Peng

Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for…

Computer Vision and Pattern Recognition · Computer Science 2024-04-01 Anurag Roy , Riddhiman Moulick , Vinay K. Verma , Saptarshi Ghosh , Abir Das

Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks. However,…

Computation and Language · Computer Science 2023-03-07 Zhen Wang , Rameswar Panda , Leonid Karlinsky , Rogerio Feris , Huan Sun , Yoon Kim

Recent advancements in large language models have sparked interest in their extraordinary and near-superhuman capabilities, leading researchers to explore methods for evaluating and optimizing these abilities, which is called…

Computer Vision and Pattern Recognition · Computer Science 2024-02-07 Jianyuan Guo , Hanting Chen , Chengcheng Wang , Kai Han , Chang Xu , Yunhe Wang

Language model approaches have recently been integrated into binary analysis tasks, such as function similarity detection and function signature recovery. These models typically employ a two-stage training process: pre-training via Masked…

Software Engineering · Computer Science 2024-12-24 Hanxiao Lu , Hongyu Cai , Yiming Liang , Antonio Bianchi , Z. Berkay Celik