English
Related papers

Related papers: Learning to Compose Skills

200 papers

According to the principle of compositional generalization, the meaning of a complex expression can be understood as a function of the meaning of its parts and of how they are combined. This principle is crucial for human language…

Computation and Language · Computer Science 2024-03-19 Sungjun Han , Sebastian Padó

One of the key limitations of modern deep learning approaches lies in the amount of data required to train them. Humans, by contrast, can learn to recognize novel categories from just a few examples. Instrumental to this rapid learning…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Pavel Tokmakov , Yu-Xiong Wang , Martial Hebert

Recent studies show that LLMs possess different skills and specialize in different tasks. In fact, we observe that their varied performance occur in several levels of granularity. For example, in the code optimization task, code LLMs excel…

Artificial Intelligence · Computer Science 2025-10-24 Yuanzhe Liu , Ryan Deng , Tim Kaler , Xuhao Chen , Charles E. Leiserson , Yao Ma , Jie Chen

Real-world tool-using agents operate over long-horizon workflows with recurring structure and diverse demands, where effective behavior requires not only invoking atomic tools but also abstracting, and reusing higher-level tool…

Social learning is widely observed in many species. Less experienced agents copy successful behaviors, exhibited by more experienced individuals. Nevertheless, the dynamical mechanisms behind this process remain largely unknown. Here we…

Dynamical Systems · Mathematics 2024-02-08 Carlos Calvo Tapia , Ivan Y. Tyukin , Valeriy A. Makarov Slizneva

Most model-free reinforcement learning methods leverage state representations (embeddings) for generalization, but either ignore structure in the space of actions or assume the structure is provided a priori. We show how a policy can be…

Machine Learning · Computer Science 2019-05-16 Yash Chandak , Georgios Theocharous , James Kostas , Scott Jordan , Philip S. Thomas

In tasks like semantic parsing, instruction following, and question answering, standard deep networks fail to generalize compositionally from small datasets. Many existing approaches overcome this limitation with model architectures that…

Computation and Language · Computer Science 2023-07-06 Ekin Akyürek , Jacob Andreas

Curriculum learning is a class of training strategies that organizes the data being exposed to a model by difficulty, gradually from simpler to more complex examples. This research explores a reverse curriculum generation approach that…

Machine Learning · Computer Science 2026-02-25 Wanru Zhao , Lucas Caccia , Zhengyan Shi , Minseon Kim , Weijia Xu , Alessandro Sordoni

Solving complex, temporally-extended tasks is a long-standing problem in reinforcement learning (RL). We hypothesize that one critical element of solving such problems is the notion of compositionality. With the ability to learn concepts…

Machine Learning · Computer Science 2019-11-21 Yiding Jiang , Shixiang Gu , Kevin Murphy , Chelsea Finn

Recent advances of gradient temporal-difference methods allow to learn off-policy multiple value functions in parallel with- out sacrificing convergence guarantees or computational efficiency. This opens up new possibilities for sound…

Artificial Intelligence · Computer Science 2014-05-22 Anna Harutyunyan , Tim Brys , Peter Vrancx , Ann Nowe

Obtaining compositional mappings is important for the model to generalize well compositionally. To better understand when and how to encourage the model to learn such mappings, we study their uniqueness through different perspectives.…

Machine Learning · Computer Science 2024-09-17 Yi Ren , Danica J. Sutherland

Humans learn complex latent structures from their environments (e.g., natural language, mathematics, music, social hierarchies). In cognitive science and cognitive neuroscience, models that infer higher-order structures from sensory or…

Artificial Intelligence · Computer Science 2018-10-03 Andrea E. Martin , Leonidas A. A. Doumas

A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, utilizes it during execution, and…

Artificial Intelligence · Computer Science 2026-05-13 Yaorui Shi , Yuxin Chen , Zhengxi Lu , Yuchun Miao , Shugui Liu , Qi GU , Xunliang Cai , Xiang Wang , An Zhang

Many techniques in computer vision, machine learning, and statistics rely on the fact that a signal of interest admits a sparse representation over some dictionary. Dictionaries are either available analytically, or can be learned from a…

Computer Vision and Pattern Recognition · Computer Science 2013-03-22 Simon Hawe , Matthias Seibert , Martin Kleinsteuber

A key requirement for generalist robots is compositional generalization - the ability to combine atomic skills to solve complex, long-horizon tasks. While prior work has primarily focused on synthesizing a planner that sequences pre-learned…

Robotics · Computer Science 2026-03-10 Han Qi , Changhe Chen , Heng Yang

The seemingly infinite diversity of the natural world arises from a relatively small set of coherent rules, such as the laws of physics or chemistry. We conjecture that these rules give rise to regularities that can be discovered through…

Language-conditioned robotic skills make it possible to apply the high-level reasoning of Large Language Models (LLMs) to low-level robotic control. A remaining challenge is to acquire a diverse set of fundamental skills. Existing…

Robotics · Computer Science 2024-08-19 Xufeng Zhao , Cornelius Weber , Stefan Wermter

In this work we create agents that can perform well beyond a single, individual task, that exhibit much wider generalisation of behaviour to a massive, rich space of challenges. We define a universe of tasks within an environment domain and…

This paper proposes to make a first step towards compatible and hence reusable network components. Rather than training networks for different tasks independently, we adapt the training process to produce network components that are…

Machine Learning · Computer Science 2020-12-17 Michael Gygli , Jasper Uijlings , Vittorio Ferrari

We study the problem of creating strong, yet narrow, AI systems. While recent AI progress has been driven by the training of large general-purpose foundation models, the creation of smaller models specialized for narrow domains could be…

Machine Learning · Computer Science 2025-10-31 Eric J. Michaud , Asher Parker-Sartori , Max Tegmark
‹ Prev 1 8 9 10 Next ›