Related papers: VQEL: Enabling Self-Play in Emergent Language Game…

Quantum machine learning (QML) has been identified as one of the key fields that could reap advantages from near-term quantum devices, next to optimization and quantum chemistry. Research in this area has focused primarily on variational…

With advances in deep learning, neural network based speech enhancement (SE) has developed rapidly in the last decade. Meanwhile, the self-supervised pre-trained model and vector quantization (VQ) have achieved excellent performance on many…

We propose a quantum algorithm for `extremal learning', which is the process of finding the input to a hidden function that extremizes the function output, without having direct access to the hidden function, given only partial input-output…

Text-based games present a unique challenge for autonomous agents to operate in natural language and handle enormous action spaces. In this paper, we propose the Contextual Action Language Model (CALM) to generate a compact set of action…

Large Language Models (LLMs) have shown strong potential as conversational agents. Yet, their effectiveness remains limited by deficiencies in robust long-term memory, particularly in complex, long-term web-based services such as online…

Vector-Quantized Image Modeling (VQIM) is a fundamental research problem in image synthesis, which aims to represent an image with a discrete token sequence. Existing studies effectively address this problem by learning a discrete codebook…

Vector quantization is a technique in machine learning that discretizes continuous representations into a set of discrete vectors. It is widely employed in tokenizing data representations for large language models, diffusion models, and…

Recent findings in multi-agent deep learning systems point towards the emergence of compositional languages. These claims are often made without exact analysis or testing of the language. In this work, we analyze the emergent language…

In this paper, we investigate whether artificial agents can develop a shared language in an ecological setting where communication relies on a sensory-motor channel. To this end, we introduce the Graphical Referential Game (GREG) where a…

Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to…

Emergent communication offers insight into how agents develop shared structured representations, yet most research assumes homogeneous modalities or aligned representational spaces, overlooking the perceptual heterogeneity of real-world…

Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and…

Agent-based models and signalling games are useful tools with which to study the emergence of linguistic communication in a tractable setting. These techniques have been used to study the compositional property of natural languages, but…

One of the main goals of robotics and intelligent agent research is to enable natural communication with humans in physically situated settings. While recent work has focused on verbal modes such as language and speech, non-verbal…

While state-of-the-art models that rely upon massively multilingual pretrained encoders achieve sample efficiency in downstream applications, they still require abundant amounts of unlabelled text. Nevertheless, most of the world's…

We propose an interactive multimodal framework for language learning. Instead of being passively exposed to large amounts of natural text, our learners (implemented as feed-forward neural networks) engage in cooperative referential games…

Recent advances in large language models (LLMs) have enabled the development of autonomous agents capable of complex reasoning and multi-step problem solving. However, these agents struggle to adapt to specialized environments and do not…

Progress in long-context reasoning for large language models (LLMs) has lagged behind other recent advances. This gap arises not only from the intrinsic difficulty of processing long texts, but also from the scarcity of reliable human…

When engaging in conversations, dialogue agents in a virtual simulation environment may exhibit their own emotional states that are unrelated to the immediate conversational context, a phenomenon known as self-emotion. This study explores…

In multi-user semantic communication, language mismatche poses a significant challenge when independently trained agents interact. We present a novel semantic equalization algorithm that enables communication between agents with different…