Related papers: TeNet: Text-to-Network for Compact Policy Synthesi…

Recent advancements in large language models (LLMs) have shown significant promise in various domains, especially robotics. However, most prior LLM-based work in robotic applications either directly predicts waypoints or applies LLMs within…

While achieving remarkable progress in a broad range of tasks, large language models (LLMs) remain significantly limited in properly using massive external tools. Existing in-context learning approaches simply format tools into a list of…

Many pre-trained language models (PLMs) exhibit suboptimal performance on mid- and low-resource languages, largely due to limited exposure to these languages during pre-training. A common strategy to address this is to introduce new tokens…

Achieving robust networks is a challenging problem due to its NP-hard nature and complex solution space. Current methods, from handcrafted feature extraction to deep learning, have made progress but remain rigid, requiring manual design and…

Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…

Analyzing network topologies and communication graphs plays a crucial role in contemporary network management. However, the absence of a cohesive approach leads to a challenging learning curve, heightened errors, and inefficiencies. In this…

We aim for domestic robots to perform long-term indoor service. Under the object-level scene dynamics induced by daily human activities, a robot needs to robustly localize itself in the environment subject to scene uncertainties. Previous…

Neural control of memory-constrained, agile robots requires small, yet highly performant models. We leverage graph hyper networks to learn graph hyper policies trained with off-policy reinforcement learning resulting in networks that are…

We present ComplexityNet, a streamlined language model designed for assessing task complexity. This model predicts the likelihood of accurate output by various language models, each with different capabilities. Our initial application of…

Incorporating prior knowledge or specifications of input-output relationships into machine learning models has attracted significant attention, as it enhances generalization from limited data and yields conforming outputs. However, most…

The increasing prevalence of Large Language Models (LMs) in critical applications highlights the need for controlled language generation strategies that are not only computationally efficient but that also enjoy performance guarantees. To…

We present a framework for learning hierarchical policies from demonstrations, using sparse natural language annotations to guide the discovery of reusable skills for autonomous decision-making. We formulate a generative model of action…

Transformer-based embedding methods have dominated the field of sentence representation in recent years. Although they have achieved remarkable performance on NLP missions, such as semantic textual similarity (STS) tasks, their black-box…

Network representation learning (NRL) methods aim to map each vertex into a low dimensional space by preserving the local and global structure of a given network, and in recent years they have received a significant attention thanks to…

As robot fleets become more heterogeneous, including humanoids, rovers, quadrupeds, and drones, selecting the right robot for a task becomes a core systems problem. We study robot skill prediction: mapping a natural-language task…

Our goal is for robots to follow natural language instructions like "put the towel next to the microwave." But getting large amounts of labeled data, i.e. data that contains demonstrations of tasks labeled with the language instruction, is…

Network representation learning (NRL) methods have received significant attention over the last years thanks to their success in several graph analysis problems, including node classification, link prediction, and clustering. Such methods…

As multiple robots are expected to coexist in future households, natural language is increasingly envisioned as a primary medium for human-robot and robot-robot communication. This paper introduces the concept of a Natural Language…

Applying end-to-end learning to solve complex, interactive, pixel-driven control tasks on a robot is an unsolved problem. Deep Reinforcement Learning algorithms are too slow to achieve performance on a real robot, but their potential has…

We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic…