Related papers: A broken duet: multistable dynamics of dyadic inte…

When an agent can articulate why something works, we typically take this as evidence of genuine understanding. This presupposes that effective action and correct explanation covary, and that coherent explanation reliably signals both. I…

Robust causal discovery from observational data under imperfect prior knowledge remains a significant and largely unresolved challenge. Existing methods typically presuppose perfect priors or can only handle specific, pre-identified error…

Human interlocutors tend to engage in adaptive behavior known as entrainment to become more similar to each other. Isolating the effect of consistency, i.e., speakers adhering to their individual styles, is a critical part of the analysis…

In task-oriented dialogue systems, Dialogue State Tracking (DST) aims to extract users' intentions from the dialogue history. Currently, most existing approaches suffer from error propagation and are unable to dynamically select relevant…

The Goldberger-Wise mechanism enables one to stabilize the length of the warped extra dimension employed in Randall-Sundrum models. In this work we generalize this mechanism to models with multiple warped throats sharing a common…

Large language models require consistent behavioral patterns for safe deployment, yet there are indications of large variability that may lead to an instable expression of personality traits in these models. We present PERSIST (PERsonality…

Neural generative models have been become increasingly popular when building conversational agents. They offer flexibility, can be easily adapted to new domains, and require minimal domain engineering. A common criticism of these systems is…

Diffusion based generative models have achieved unprecedented fidelity in synthesizing high dimensional data, yet the theoretical mechanisms governing multimodal generation remain poorly understood. Here, we present a theoretical framework…

We present a data-driven modeling strategy to overcome improperly modeled dynamics for systems exhibiting complex spatio-temporal behaviors. We propose a Deep Learning framework to resolve the differences between the true dynamics of the…

How to effectively utilize the dialogue history is a crucial problem in multi-turn dialogue generation. Previous works usually employ various neural network architectures (e.g., recurrent neural networks, attention mechanisms, and…

Multi-Agent Reinforcement Learning involves agents that learn together in a shared environment, leading to emergent dynamics sensitive to initial conditions and parameter variations. A Dynamical Systems approach, which studies the evolution…

With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…

In recent years there has been increased interest in understanding the interplay between deep generative models (DGMs) and the manifold hypothesis. Research in this area focuses on understanding the reasons why commonly-used DGMs succeed or…

Large Language Models (LLMs) achieve strong performance through extended inference-time deliberation, yet how their reasoning failures arise remains poorly understood. By analyzing model-generated reasoning trajectories, we find that errors…

Intelligent agents must be able to articulate its own uncertainty. In this work, we show that pre-trained sequence models are naturally capable of probabilistic reasoning over exchangeable data points -- forming informed beliefs and…

Maintaining engagement and consistency is particularly important in dialogue systems. Existing works have improved the performance of dialogue systems by intentionally learning interlocutor personas with sophisticated network structures.…

In real-life conversations, the content is diverse, and there exists the one-to-many problem that requires diverse generation. Previous studies attempted to introduce discrete or Gaussian-based continuous latent variables to address the…

The deep learning revolution has spurred a rise in advances of using AI in sciences. Within physical sciences the main focus has been on discovery of dynamical systems from observational data. Yet the reliability of learned surrogates and…

Large-scale pretrained language models are the major driving force behind recent improvements in performance on the Winograd Schema Challenge, a widely employed test of common sense reasoning ability. We show, however, with a new diagnostic…

The Dirichlet Belief Network~(DirBN) has been recently proposed as a promising approach in learning interpretable deep latent representations for objects. In this work, we leverage its interpretable modelling architecture and propose a deep…