English
Related papers

Related papers: Warmup Generations: A Task-Agnostic Approach for G…

200 papers

Foundation models trained on web-scale data have revolutionized robotics, but their application to low-level control remains largely limited to behavioral cloning. Drawing inspiration from the success of the reinforcement learning stage in…

Machine Learning · Computer Science 2025-09-19 Seyed Kamyar Seyed Ghasemipour , Ayzaan Wahid , Jonathan Tompson , Pannag Sanketi , Igor Mordatch

Foundation models contain a wealth of information from their vast number of training samples. However, most prior arts fail to extract this information in a precise and efficient way for small sample sizes. In this work, we propose a…

Machine Learning · Computer Science 2024-04-26 Nico Schiavone , Xingyu Li

Time Series Foundation Models (TSFMs) advance generalization and data efficiency in time series forecasting by unified large-scale pretraining. But TSFMs remain lacking when adapting to specific downstream forecasting tasks for two reasons.…

Signal Processing · Electrical Eng. & Systems 2026-05-04 Siyang Li , Yize Chen , Zijie Zhu , Yuxin Pan , Yan Guo , Ming Huang , Hui Xiong

While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation tasks remains a challenge. To solve this problem, we present…

Computation and Language · Computer Science 2021-10-22 Ting Jiang , Shaohan Huang , Zihan Zhang , Deqing Wang , Fuzhen Zhuang , Furu Wei , Haizhen Huang , Liangjie Zhang , Qi Zhang

Pre-trained large language models can efficiently interpolate human-written prompts in a natural way. Multitask prompted learning can help generalization through a diverse set of tasks at once, thus enhancing the potential for more…

Computation and Language · Computer Science 2022-12-22 M Saiful Bari , Aston Zhang , Shuai Zheng , Xingjian Shi , Yi Zhu , Shafiq Joty , Mu Li

Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous…

Machine Learning · Computer Science 2021-06-07 Robert-Florian Samoilescu , Arnaud Van Looveren , Janis Klaise

Counterfactuals have become a popular technique nowadays for interacting with black-box machine learning models and understanding how to change a particular instance to obtain a desired outcome from the model. However, most existing…

Machine Learning · Computer Science 2021-09-29 Philip Naumann , Eirini Ntoutsi

In natural language processing tasks, pure reinforcement learning (RL) fine-tuning methods often suffer from inefficient exploration and slow convergence; while supervised fine-tuning (SFT) methods, although efficient in training, have…

Computation and Language · Computer Science 2025-09-17 Min Zeng , Jingfei Sun , Xueyou Luo , Caiquan Liu , Shiqi Zhang , Li Xie , Xiaoxin Chen

Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we…

Artificial Intelligence · Computer Science 2026-05-05 Wangjie Gan , Miao Pan , Linbo Xi , Wenqi Zhang , Jintao Chen , Jianwei Yin , Xuhong Zhang

Sequence-to-sequence architectures built upon recurrent neural networks have become a standard choice for multi-step-ahead time series prediction. In these models, the decoder produces future values conditioned on contextual inputs,…

Machine Learning · Computer Science 2026-02-06 Qi Sima , Xinze Zhang , Yukun Bao , Siyue Yang , Liang Shen

Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization, through instruction fine-tuning. The fine-tuning data is generally sequentially concatenated from a specific…

Computation and Language · Computer Science 2023-08-24 Yijin Liu , Xianfeng Zeng , Fandong Meng , Jie Zhou

We investigate the integration of a planning mechanism into sequence-to-sequence models using attention. We develop a model which can plan ahead in the future when it computes its alignments between input and output sequences, constructing…

Machine Learning · Computer Science 2017-11-29 Francis Dutil , Caglar Gulcehre , Adam Trischler , Yoshua Bengio

Despite recent progress in time-series foundation models, challenges persist in improving representation learning and adapting to diverse downstream tasks. We introduce a General Time-series Model (GTM), which advances representation…

Machine Learning · Computer Science 2026-03-13 Cheng He , Xu Huang , Gangwei Jiang , Zhaoyi Li , Defu Lian , Hong Xie , Enhong Chen , Xijie Liang , Zengrong Zheng , Patrick P. C. Lee

Meta-learning stands for 'learning to learn' such that generalization to new tasks is achieved. Among these methods, Gradient-based meta-learning algorithms are a specific sub-class that excel at quick adaptation to new tasks with limited…

Machine Learning · Computer Science 2020-10-20 Jathushan Rajasegaran , Salman Khan , Munawar Hayat , Fahad Shahbaz Khan , Mubarak Shah

The prevailing post-training paradigm for Large Reasoning Models (LRMs) - Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) - suffers from an intrinsic optimization mismatch: the rigid supervision inherent in SFT induces…

Machine Learning · Computer Science 2026-03-19 Zhengyang Zhao , Lu Ma , Yizhen Jiang , Xiaochen Ma , Zimo Meng , Chengyu Shen , Lexiang Tang , Haoze Sun , Peng Pei , Wentao Zhang

Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models, but it often degrades pretrained capabilities such as reasoning and general-domain performance. We argue this forgetting arises because fine-tuning…

Computation and Language · Computer Science 2026-05-22 Jiarui Liu , Lechen Zhang , Yongjin Yang , Yinghui He , Yingheng Wang , Weihao Xuan , Zhijing Jin , Mona Diab

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains…

Computation and Language · Computer Science 2026-05-12 Guowei Xu , Wenxin Xu , Jiawang Zhao , Kaisheng Ma

Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcement Learning (RL) effectively preserves general capabilities.…

Machine Learning · Computer Science 2026-01-06 Muxi Diao , Lele Yang , Wuxuan Gong , Yutong Zhang , Zhonghao Yan , Yufei Han , Kongming Liang , Weiran Xu , Zhanyu Ma

Meta learning is a promising technique for solving few-shot fault prediction problems, which have attracted the attention of many researchers in recent years. Existing meta-learning methods for time series prediction, which predominantly…

Machine Learning · Computer Science 2023-11-07 Hai Su , Jiajun Hu , Songsen Yu

Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be…

Machine Learning · Computer Science 2020-03-27 Jathushan Rajasegaran , Salman Khan , Munawar Hayat , Fahad Shahbaz Khan , Mubarak Shah