English
Related papers

Related papers: Modular Networks for Compositional Instruction Fol…

200 papers

In this work we propose a planning and acting architecture endowed with a module which learns to select subgoals with Deep Q-Learning. This allows us to decrease the load of a planner when faced with scenarios with real-time restrictions.…

Artificial Intelligence · Computer Science 2024-06-24 Carlos Núñez-Molina , Juan Fernández-Olivares , Raúl Pérez

This paper offers a new perspective on Artificial Neural Networks (ANNs) architecture. Traditional ANNs commonly use tree-like or DAG structures for simplicity, which can be preset or determined by Neural Architecture Search (NAS). Yet,…

Machine Learning · Computer Science 2025-06-05 Xinshun Liu , Yizhi Fang , Yichao Jiang

Recent years have seen a paradigm shift in NLP towards using pretrained language models ({PLM}) for a wide range of tasks. However, there are many difficult design decisions to represent structures (e.g. tagged text, coreference chains) in…

Computation and Language · Computer Science 2022-11-18 Tianyu Liu , Yuchen Jiang , Nicholas Monath , Ryan Cotterell , Mrinmaya Sachan

Robots are often built from standardized assemblies, (e.g. arms, legs, or fingers), but each robot must be trained from scratch to control all the actuators of all the parts together. In this paper we demonstrate a new approach that takes a…

Robotics · Computer Science 2025-02-12 Megan Tjandrasuwita , Jie Xu , Armando Solar-Lezama , Wojciech Matusik

At present, neural network-based models, including transformers, struggle to generate memorable and readily comprehensible music from unified and repetitive musical material due to a lack of understanding of musical structure. Consequently,…

Sound · Computer Science 2026-01-21 Shangxuan Luo , Joshua Reiss

In recent years artificial neural networks achieved performance close to or better than humans in several domains: tasks that were previously human prerogatives, such as language processing, have witnessed remarkable improvements in state…

Neurons and Cognition · Quantitative Biology 2019-02-14 Andrea Alamia , Victor Gauducheau , Dimitri Paisios , Rufin VanRullen

Instruction following is a critical ability for Large Language Models to perform downstream tasks. The standard approach to instruction tuning has relied on a specific phase of supervised fine-tuning over curated instruction datasets,…

Computation and Language · Computer Science 2026-05-01 David Ponce , Thierry Etchegoyhen

Temporal action localization aims at localizing action instances from untrimmed videos. Existing works have designed various effective modules to precisely localize action instances based on appearance and motion features. However, by…

Computer Vision and Pattern Recognition · Computer Science 2022-05-30 Le Yang , Junwei Han , Tao Zhao , Nian Liu , Dingwen Zhang

Instruction-tuned large language models (LLMs) have shown strong performance on a variety of tasks; however, generalizing from synthetic to human-authored instructions in grounded environments remains a challenge for them. In this work, we…

Computation and Language · Computer Science 2025-08-19 Chalamalasetti Kranti , Sherzod Hakimov , David Schlangen

Complex environments and tasks pose a difficult problem for holistic end-to-end learning approaches. Decomposition of an environment into interacting controllable and non-controllable objects allows supervised learning for non-controllable…

Machine Learning · Computer Science 2019-01-30 Andrew Melnik , Sascha Fleer , Malte Schilling , Helge Ritter

We present a novel modular object detection convolutional neural network that significantly improves the accuracy of object detection. The network consists of two stages in a hierarchical structure. The first stage is a network that detects…

Computer Vision and Pattern Recognition · Computer Science 2020-09-15 Erez Yahalomi

Language-conditioned policies allow robots to interpret and execute human instructions. Learning such policies requires a substantial investment with regards to time and compute resources. Still, the resulting controllers are highly…

Robotics · Computer Science 2022-12-12 Yifan Zhou , Shubham Sonawani , Mariano Phielipp , Simon Stepputtis , Heni Ben Amor

Large Language Models (LLMs) have achieved remarkable results. However, existing models are expensive to train and deploy, and it is also difficult to expand their knowledge beyond pre-training data without forgetting previous knowledge.…

Computation and Language · Computer Science 2023-09-13 Yikang Shen , Zheyu Zhang , Tianyou Cao , Shawn Tan , Zhenfang Chen , Chuang Gan

In this paper, we address referring expression comprehension: localizing an image region described by a natural language expression. While most recent work treats expressions as a single unit, we propose to decompose them into three modular…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Licheng Yu , Zhe Lin , Xiaohui Shen , Jimei Yang , Xin Lu , Mohit Bansal , Tamara L. Berg

We introduce the first cut-free nested sequent systems for first-order modal logics that admit increasing, decreasing, constant, and empty domains along with so-called general path conditions and seriality. We obtain such systems by means…

Logic in Computer Science · Computer Science 2023-11-09 Tim S. Lyon

Answering compositional questions that require multiple steps of reasoning against text is challenging, especially when they involve discrete, symbolic operations. Neural module networks (NMNs) learn to parse such questions as executable…

Computation and Language · Computer Science 2020-02-18 Nitish Gupta , Kevin Lin , Dan Roth , Sameer Singh , Matt Gardner

We propose a modular architecture for the lifelong learning of hierarchically structured tasks. Specifically, we prove that our architecture is theoretically able to learn tasks that can be solved by functions that are learnable given…

Machine Learning · Computer Science 2021-12-22 Zihao Deng , Zee Fryer , Brendan Juba , Rina Panigrahy , Xin Wang

Hierarchical reinforcement learning has been a compelling approach for achieving goal directed behavior over long sequences of actions. However, it has been challenging to implement in realistic or open-ended environments. A main challenge…

Machine Learning · Computer Science 2023-09-22 Arun Ahuja , Kavya Kopparapu , Rob Fergus , Ishita Dasgupta

We introduce a modular prompting framework that supports safer and more adaptive use of large language models (LLMs) across dynamic, user-centered tasks. Grounded in human learning theory, particularly the Zone of Proximal Development…

Artificial Intelligence · Computer Science 2025-08-12 Vanessa Figueiredo

Classical Machine Learning (ML) pipelines often comprise of multiple ML models where models, within a pipeline, are trained in isolation. Conversely, when training neural network models, layers composing the neural models are simultaneously…

Machine Learning · Computer Science 2019-12-13 Gyeong-In Yu , Saeed Amizadeh , Sehoon Kim , Artidoro Pagnoni , Byung-Gon Chun , Markus Weimer , Matteo Interlandi