Related papers: Toward Forgetting-Sensitive Referring Expression G…

With the rapid development of deep learning, most of current state-of-the-art techniques in natural langauge processing are based on deep learning models trained with argescaled static textual corpora. However, we human beings learn and…

The ability of a machine to communicate with humans has long been associated with the general success of AI. This dates back to Alan Turing's epoch-making work in the early 1950s, which proposes that a machine's intelligence can be tested…

We present open domain response generation with meta-words. A meta-word is a structured record that describes various attributes of a response, and thus allows us to explicitly model the one-to-many relationship within open domain dialogues…

Towards human-like dialogue systems, current emotional dialogue approaches jointly model emotion and semantics with a unified neural network. This strategy tends to generate safe responses due to the mutual restriction between emotion and…

This paper introduces our approach to building a robot with communication capability based on the two key features: stochastic neural dynamics and prediction error minimization (PEM). A preliminary experiment with humanoid robots showed…

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

A growing field in robotics and Artificial Intelligence (AI) research is human-robot collaboration, whose target is to enable effective teamwork between humans and robots. However, in many situations human teams are still superior to…

We consider Representation Misdirection (RM), a class of large language model (LLM) unlearning methods that achieve forgetting by redirecting the forget-representations, that is, latent representations of forget-samples, toward a target…

We model human and animal learning by computing with high-dimensional vectors (H = 10,000 for example). The architecture resembles traditional (von Neumann) computing with numbers, but the instructions refer to vectors and operate on them…

Intelligence necessitates memory. Without memory, humans fail to perform various nontrivial tasks such as reading novels, playing games or solving maths. As the ultimate goal of machine learning is to derive intelligent systems that learn…

Conversation generation as a challenging task in Natural Language Generation (NLG) has been increasingly attracting attention over the last years. A number of recent works adopted sequence-to-sequence structures along with external…

The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions. However, this challenge is not well addressed in the literature, since most of the…

Research in multi-agent cooperation has shown that artificial agents are able to learn to play a simple referential game while developing a shared lexicon. This lexicon is not easy to analyze, as it does not show many properties of a…

Transformer-based language models excel at both recall (retrieving memorized facts) and reasoning (performing multi-step inference), but whether these abilities rely on distinct internal mechanisms remains unclear. Distinguishing recall…

A key question in reinforcement learning is how an intelligent agent can generalize knowledge across different inputs. By generalizing across different inputs, information learned for one input can be immediately reused for improving…

Humans excel at applying learned behavior to unlearned situations. A crucial component of this generalization behavior is our ability to compose/decompose a whole into reusable parts, an attribute known as compositionality. One of the…

We introduce Language World Models, a class of language-conditional generative model which interpret natural language messages by predicting latent codes of future observations. This provides a visual grounding of the message, similar to an…

Cognitive agents such as humans and robots perceive their environment through an abundance of sensors producing streams of data that need to be processed to generate intelligent behavior. A key question of cognition-enabled and AI-driven…

The exploration of whether agents can align with their environment without relying on human-labeled data presents an intriguing research topic. Drawing inspiration from the alignment process observed in intelligent organisms, where…

Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them. This has resulted in the development of models which treat conversation as a sequence-to-sequence…