Related papers: CINet: A Learning Based Approach to Incremental Co…

Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. However, they are often overconfident in their predictions, which leads to inaccurate and miscalibrated…

Learning a policy capable of moving an agent between any two states in the environment is important for many robotics problems involving navigation and manipulation. Due to the sparsity of rewards in such tasks, applying reinforcement…

The ability to generate appropriate verbal and non-verbal backchannels by an agent during human-robot interaction greatly enhances the interaction experience. Backchannels are particularly important in applications like tutoring and…

Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters. However, some agents can solve new tasks without updating any parameters by simply conditioning…

Motivated by the prevalence and success of machine learning, a line of recent work has studied learning-augmented algorithms in the streaming model. These results have shown that for natural and practical oracles implemented with machine…

While large neural-based conversational models have become increasingly proficient dialogue agents, recent work has highlighted safety issues with these systems. For example, these systems can be goaded into generating toxic content, which…

Recurrent Neural Networks are showing much promise in many sub-areas of natural language processing, ranging from document classification to machine translation to automatic question answering. Despite their promise, many recurrent models…

Contextual information at inference time, such as demonstrations, retrieved knowledge, or interaction history, can substantially improve large language models (LLMs) without parameter updates, yet its theoretical role remains poorly…

Pre-trained language models (PLM) have marked a huge leap in neural dialogue modeling. While PLMs are pre-trained on large-scale text corpora, they are usually fine-tuned on scarce dialogue data with specific domain knowledge and dialogue…

Real-world time series often exhibit complex interdependencies that cannot be captured in isolation. Global models that model past data from multiple related time series globally while producing series-specific forecasts locally are now…

Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns…

Social norms are shared rules that govern and facilitate social interaction. Violating such social norms via teasing and insults may serve to upend power imbalances or, on the contrary reinforce solidarity and rapport in conversation,…

Convolutional Neural Networks (CNNs) have been used extensively for computer vision tasks and produce rich feature representation for objects or parts of an image. But reasoning about scenes requires integration between the low-level…

Deep neural networks have shown superior performance in many regimes to remember familiar patterns with large amounts of data. However, the standard supervised deep learning paradigm is still limited when facing the need to learn new…

Long-horizon tasks requiring multi-step reasoning and dynamic re-planning remain challenging for large language models (LLMs). Sequential prompting methods are prone to context drift, loss of goal information, and recurrent failure cycles,…

Generative image models are increasingly being used for training data augmentation in vision tasks. In the context of automotive object detection, methods usually focus on producing augmented frames that look as realistic as possible, for…

Convolutional Neural Networks (CNNs) for visual tasks are believed to learn both the low-level textures and high-level object attributes, throughout the network depth. This paper further investigates the `texture bias' in CNNs. To this end,…

We introduce a neural architecture finetuned for the task of scenario context generation: The relevant location and time of an event or entity mentioned in text. Contextualizing information extraction helps to scope the validity of…

Traffic scene recognition, which requires various visual classification tasks, is a critical ingredient in autonomous vehicles. However, most existing approaches treat each relevant task independently from one another, never considering the…

Predictive models in acute care settings must be able to immediately recognize precipitous changes in a patient's status when presented with data reflecting such changes. Recurrent neural networks (RNNs) have become common for training and…