相关论文: SL-BiLEM: Structured Learnable Behavior-in-the-Loo…

We investigate the information-theoretical limits of inference tasks in epidemic spreading on graphs in the thermodynamic limit. The typical inference tasks consist in computing observables of the posterior distribution of the epidemic…

Emotional Support Conversation (ESC) plays a critical role in mental health assistance by providing accessible psychological support in real-world applications. Large Language Models (LLMs) have shown strong empathetic abilities in ESC…

Batch Reinforcement Learning (Batch RL) consists in training a policy using trajectories collected with another policy, called the behavioural policy. Safe policy improvement (SPI) provides guarantees with high probability that the trained…

Phenomenological models are highly effective tools for forecasting disease dynamics using real world data, particularly in scenarios where detailed knowledge of disease mechanisms is limited. However, their reliability depends on the model…

Predicting group behavior, how individuals coordinate, communicate, and interact during collaborative tasks, is essential for designing systems that can support team performance through real-time prediction and realistic simulation of…

Human-in-the-loop (HitL) robot deployment has gained significant attention in both academia and industry as a semi-autonomous paradigm that enables human operators to intervene and adjust robot behaviors at deployment time, improving…

While most ML models expect independent and identically distributed data, this assumption is often violated in real-world scenarios due to distribution shifts, resulting in the degradation of machine learning model performance. Until now,…

Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency. We introduce Efficient Selective Language Modeling (ESLM), a risk-aware algorithm that improves training…

The architecture design and multi-scale learning principles of the human brain that evolved over hundreds of millions of years are crucial to realizing human-like intelligence. Spiking Neural Network (SNN) based Liquid State Machine (LSM)…

Large language models (LLMs) trained with next-word-prediction have achieved success as clinical foundation models. Representations from these language backbones yield strong linear probe performance across biomedical tasks, suggesting that…

Service-level mobile traffic prediction for individual users is essential for network efficiency and quality of service enhancement. However, current prediction methods are limited in their adaptability across different urban environments…

Robot manipulation has seen tremendous progress in recent years, with imitation learning policies enabling successful performance of dexterous and hard-to-model tasks. Concurrently, scaling data and model size has led to the development of…

Recent work has questioned whether large language models (LLMs) can perform genuine in-context learning (ICL) for scientific experimental design, with prior studies suggesting that LLM-based agents exhibit no sensitivity to experimental…

One of the most important branches of nonlinear control theory is the so-called sliding-mode. Its aim is the design of a (nonlinear) feedback law that brings and maintains the state trajectory of a dynamic system on a given sliding surface.…

While reinforcement learning (RL) has achieved notable success in various domains, training effective policies for complex tasks remains challenging. Agents often converge to local optima and fail to maximize long-term rewards. Existing…

Speech-to-Speech (S2S) Large Language Models (LLMs) are foundational to natural human-computer interaction, enabling end-to-end spoken dialogue systems. However, evaluating these models remains a fundamental challenge. We propose…

This paper considers Safe Policy Improvement (SPI) in Batch Reinforcement Learning (Batch RL): from a fixed dataset and without direct access to the true environment, train a policy that is guaranteed to perform at least as well as the…

Susceptible-Exposed-Infectious-Recovered (SEIR) models with inter-individual variation in susceptibility or exposure to infection were proposed early in the COVID-19 pandemic as a potential element of the mathematical/statistical toolset…

Human migration exhibits complex spatiotemporal dependence driven by environmental and socioeconomic forces. Modeling such patterns at scale requires methods that accommodate many random effects while remaining feasible when raw data or…

Epidemic threshold is one of the most important features of the epidemic dynamics. Through a lot of numerical simulations in classic Susceptible-Infected-Recovered (SIR) and Susceptible-Infected-Susceptible (SIS) models on various types of…