English
Related papers

Related papers: Looped Transformers for Length Generalization

200 papers

Even for simple arithmetic tasks like integer addition, it is challenging for Transformers to generalize to longer sequences than those encountered during training. To tackle this problem, we propose position coupling, a simple yet…

Machine Learning · Computer Science 2024-10-31 Hanseul Cho , Jaeyoung Cha , Pranjal Awasthi , Srinadh Bhojanapalli , Anupam Gupta , Chulhee Yun

Length generalization (LG) is a challenging problem in learning to reason. It refers to the phenomenon that when trained on reasoning problems of smaller lengths or sizes, the resulting model struggles with problems of larger sizes or…

Artificial Intelligence · Computer Science 2024-04-02 Changnan Xiao , Bing Liu

The ability to plan for multi-step manipulation tasks in unseen situations is crucial for future home robots. But collecting sufficient experience data for end-to-end learning is often infeasible in the real world, as deploying robots in…

Robotics · Computer Science 2022-05-18 Chen Wang , Danfei Xu , Li Fei-Fei

In Transformers, Position Embeddings (PEs) significantly influence Length Generalization (LG) performance, yet their fundamental role remains unclear. In this work, we investigate the limitations and capabilities of PEs in achieving LG. We…

Machine Learning · Computer Science 2025-10-07 Yang Chen , Yitao Liang , Zhouchen Lin

Large language models (LLMs) based on the Transformer have demonstrated strong performance across diverse tasks. However, current models still exhibit substantial limitations in out-of-distribution (OOD) generalization compared with humans.…

Machine Learning · Computer Science 2026-02-02 Huanyu Liu , Ge Li , Yihong Dong , Sihan Wu , Peixu Wang , Sihao Cheng , Taozhi Chen , Kechi Zhang , Hao Zhu , Tongxuan Liu

Transformers have significantly impacted domains like natural language processing, computer vision, and robotics, where they improve performance compared to other neural networks. This survey explores how transformers are used in…

Machine Learning · Computer Science 2023-07-13 Pranav Agarwal , Aamer Abdul Rahman , Pierre-Luc St-Charles , Simon J. D. Prince , Samira Ebrahimi Kahou

We train a linear attention transformer on millions of masked-block matrix completion tasks: each prompt is masked low-rank matrix whose missing block may be (i) a scalar prediction target or (ii) an unseen kernel slice of Nystr\"om…

Machine Learning · Computer Science 2025-09-25 Patrick Lutz , Aditya Gangrade , Hadi Daneshmand , Venkatesh Saligrama

Multi-task learning of deformable object manipulation is a challenging problem in robot manipulation. Most previous works address this problem in a goal-conditioned way and adapt goal images to specify different tasks, which limits the…

Robotics · Computer Science 2024-01-30 Yuhong Deng , Kai Mo , Chongkun Xia , Xueqian Wang

We study the sequence-to-sequence mapping capacity of transformers by relating them to finite transducers, and find that they can express surprisingly large classes of transductions. We do so using variants of RASP, a programming language…

Formal Languages and Automata Theory · Computer Science 2024-11-07 Lena Strobl , Dana Angluin , David Chiang , Jonathan Rawski , Ashish Sabharwal

Length generalization, the ability to solve problems longer than those seen during training, remains a critical challenge for large language models (LLMs). Previous work modifies positional encodings (PEs) and data formats to improve length…

Computation and Language · Computer Science 2025-05-20 Yi Hu , Shijia Kang , Haotong Yang , Haotian Xu , Muhan Zhang

In-context learning has been recognized as a key factor in the success of Large Language Models (LLMs). It refers to the model's ability to learn patterns on the fly from provided in-context examples in the prompt during inference. Previous…

Machine Learning · Computer Science 2025-03-04 Bo Chen , Xiaoyu Li , Yingyu Liang , Zhenmei Shi , Zhao Song

We study length generalization in sequence models on a composite problem involving both state tracking and associative recall. Prior work finds that recurrent networks handle state tracking well but struggle with recall, whereas…

Machine Learning · Computer Science 2025-10-02 Buu Phan , Reza Ebrahimi , Sanjay Haresh , Roland Memisevic

Transformer, originally devised for natural language processing, has also attested significant success in computer vision. Thanks to its super expressive power, researchers are investigating ways to deploy transformers to reinforcement…

Machine Learning · Computer Science 2023-01-24 Shengchao Hu , Li Shen , Ya Zhang , Yixin Chen , Dacheng Tao

Algorithmic generalization in machine learning refers to the ability to learn the underlying algorithm that generates data in a way that generalizes out-of-distribution. This is generally considered a difficult task for most machine…

Machine Learning · Computer Science 2024-01-17 Simon Ouellette , Rolf Pfister , Hansueli Jud

Large language models (LLMs)-based code generation for robotic manipulation has recently shown promise by directly translating human instructions into executable code, but existing methods remain noisy, constrained by fixed primitives and…

Robotics · Computer Science 2025-09-26 Yuan Meng , Zhenguo Sun , Max Fest , Xukun Li , Zhenshan Bing , Alois Knoll

Trained transformer models have been found to implement interpretable procedures for tasks like arithmetic and associative recall, but little is understood about how the circuits that implement these procedures originate during training. To…

Machine Learning · Computer Science 2024-10-08 Ziqian Zhong , Jacob Andreas

Large Language Models demonstrate remarkable mathematical capabilities but at the same time struggle with abstract reasoning and planning. In this study, we explore whether Transformers can learn to abstract and generalize the rules…

Neural and Evolutionary Computing · Computer Science 2024-12-03 Mikhail Burtsev

Length generalization remains a persistent challenge for neural networks: recurrent models tend to suffer from positional biases, while transformers are constrained by fixed computational depth. Regular languages provide a frequently used…

Machine Learning · Computer Science 2026-05-26 Charles Pert , Dalal Alrajeh , Alessandra Russo

Transformer models cannot easily scale to long sequences due to their O(N^2) time and space complexity. This has led to Transformer variants seeking to lower computational complexity, such as Longformer and Performer. While such models have…

Computation and Language · Computer Science 2024-12-10 Guanghui Qin , Yukun Feng , Benjamin Van Durme

Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has…

Machine Learning · Computer Science 2023-09-20 Colin Raffel , Noam Shazeer , Adam Roberts , Katherine Lee , Sharan Narang , Michael Matena , Yanqi Zhou , Wei Li , Peter J. Liu