相关论文: Emergent Communication between Heterogeneous Visua…

Driving in a dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision-making policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level…

Self-supervised methods have shown remarkable progress in learning high-level semantics and low-level temporal correspondence. Building on these results, we take one step further and explore the possibility of integrating these two features…

This paper introduces a methodology through which a population of autonomous agents can establish a linguistic convention that enables them to refer to arbitrary entities that they observe in their environment. The linguistic convention…

We study a symmetric collaborative dialogue setting in which two agents, each with private knowledge, must strategically communicate to achieve a common goal. The open-ended dialogue state in this setting poses new challenges for existing…

Token Communication (TokenCom) is a new paradigm, motivated by the recent success of Large AI Models (LAMs) and Multimodal Large Language Models (MLLMs), where tokens serve as unified units of communication and computation, enabling…

Human speakers encode information into raw speech which is then decoded by the listeners. This complex relationship between encoding (production) and decoding (perception) is often modeled separately. Here, we test how encoding and decoding…

Emergence, a global property of complex adaptive systems (CASs) constituted by interactive agents, is prevalent in real-world dynamic systems, e.g., network-level traffic congestions. Detecting its formation and evaporation helps to monitor…

Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's evolving understanding of the world. When agents can only partially observe their…

Transformers have offered a new methodology of designing neural networks for visual recognition. Compared to convolutional networks, Transformers enjoy the ability of referring to global features at each stage, yet the attention module…

Visual-semantic embedding enables various tasks such as image-text retrieval, image captioning, and visual question answering. The key to successful visual-semantic embedding is to express visual and textual data properly by accounting for…

Semantic communication systems often use an end-to-end neural network to map input data into continuous symbols. These symbols, which are essentially neural network features, usually have fixed dimensions and heavy-tailed distributions.…

We consider a multi-agent reinforcement learning problem where each agent seeks to maximize a shared reward while interacting with other agents, and they may or may not be able to communicate. Typically the agents do not have access to…

Human language processing relies on the brain's capacity for predictive inference. We present a machine learning framework for decoding neural (EEG) responses to dynamic visual language stimuli in Deaf signers. Using coherence between…

The mean-field framework has been used to find approximate solutions to problems involving very large populations of symmetric, anonymous agents, which may be intractable by other methods. The cooperative mean-field control (MFC) problem…

Automatic generation of high-quality commit messages for code commits can substantially facilitate software developers' works and coordination. However, the semantic gap between source code and natural language poses a major challenge for…

Complementary Learning Systems theory holds that intelligent agents need two learning systems. Semantic memory is encoded in the neocortex with dense, overlapping representations and acquires structured knowledge. Episodic memory is encoded…

Representation is a core issue in artificial intelligence. Humans use discrete language to communicate and learn from each other, while machines use continuous features (like vector, matrix, or tensor in deep neural networks) to represent…

Emergent communication enables partially observant Autonomous Mobile Robots (AMRs) to coordinate effectively in decentralized multi-agent reinforcement learning (MARL) settings. However, existing approaches often struggle with unstable…

This paper proposes a generative probabilistic model integrating emergent communication and multi-agent reinforcement learning. The agents plan their actions by probabilistic inference, called control as inference, and communicate using…

The ability of algorithms to evolve or learn (compositional) communication protocols has traditionally been studied in the language evolution literature through the use of emergent communication tasks. Here we scale up this research by…