Related papers: Learning Bidirectional Translation between Descrip…

We explore best practices for training small, memory efficient machine translation models with sequence-level knowledge distillation in the domain adaptation setting. While both domain adaptation and knowledge distillation are widely-used,…

Human emotion is expressed in many communication modalities and media formats and so their computational study is equally diversified into natural language processing, audio signal analysis, computer vision, etc. Similarly, the large…

When trained on large-scale datasets, image captioning models can understand the content of images from a general domain but often fail to generate accurate, detailed captions. To improve performance, pretraining-and-finetuning has been a…

The many-to-many multilingual neural machine translation can translate between language pairs unseen during training, i.e., zero-shot translation. Improving zero-shot translation requires the model to learn universal representations and…

Social robot navigation can be helpful in various contexts of daily life but requires safe human-robot interactions and efficient trajectory planning. While modeling pairwise relations has been widely studied in multi-agent interacting…

Advancements in graphics technology has increased the use of simulated data for training machine learning models. However, the simulated data often differs from real-world data, creating a distribution gap that can decrease the efficacy of…

Representation learning (RL) methods for cyberattack detection face the diversity and sophistication of attack data, leading to the issue of mixed representations of different classes, particularly as the number of classes increases. To…

During co-manipulation involving humans and robots, it is necessary to base robot controllers on human behaviors to achieve comfortable and coordinated movement between the human-robot dyad. In this paper, we describe an experiment between…

We present a deep imitation learning framework for robotic bimanual manipulation in a continuous state-action space. A core challenge is to generalize the manipulation skills to objects in different locations. We hypothesize that modeling…

Intelligent agents must reason over both continuous dynamics and discrete representations to generate effective plans in complex environments. Previous studies have shown that symbolic abstractions can emerge from neural effect predictors…

The field of visual representation learning has seen explosive growth in the past years, but its benefits in robotics have been surprisingly limited so far. Prior work uses generic visual representations as a basis to learn (task-specific)…

While neural machine translation (NMT) is making good progress in the past two years, tens of millions of bilingual sentence pairs are needed for its training. However, human labeling is very costly. To tackle this training data bottleneck,…

Modern robotics is gravitating toward increasingly collaborative human robot interaction. Tools such as acceleration policies can naturally support the realization of reactive, adaptive, and compliant robots. These tools require us to model…

When humans work together to complete a joint task, each person builds an internal model of the situation and how it will evolve. Efficient collaboration is dependent on how these individual models overlap to form a shared mental model…

Teaching robots to autonomously complete everyday tasks remains a challenge. Imitation Learning (IL) is a powerful approach that imbues robots with skills via demonstrations, but is limited by the labor-intensive process of collecting…

Prior works have demonstrated that implicit representations trained only for reconstruction tasks typically generate encodings that are not useful for semantic tasks. In this work, we propose a method that contextualises the encodings of…

Autonomous mobile service robots, like lawnmowers or cleaning robots, operating in human-populated environments need to reason about local human-human interactions to support safe and socially aware navigation while fulfilling their tasks.…

Current methods for action recognition primarily rely on deep convolutional networks to derive feature embeddings of visual and motion features. While these methods have demonstrated remarkable performance on standard benchmarks, we are…

Despite the impressive results achieved by multimodal large language models (MLLMs), their training typically relies on jointly curated multimodal data, requiring substantial human effort to construct multi-way aligned datasets and thereby…

Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of the inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically…