Related papers: WIMLE: Uncertainty-Aware World Models with IMLE fo…

Evaluating LLMs and text-to-image models is a computationally intensive task often overlooked. Efficient evaluation is crucial for understanding the diverse capabilities of these models and enabling comparisons across a growing number of…

Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is commonly used to create and curate these datasets, its potential…

World models aim to improve robotic decision making by predicting the consequences of actions. However, in practice, their predictions often become unreliable once the robot encounters states outside the training distribution, limiting…

Observational epidemiological studies commonly seek to estimate the causal effect of an exposure on an outcome. Adjustment for potential confounding bias in modern studies is challenging due to the presence of high-dimensional confounding,…

Shape completion is the problem of completing partial input shapes such as partial scans. This problem finds important applications in computer vision and robotics due to issues such as occlusion or sparsity in real-world data. However,…

Control of wheeled humanoid locomotion is a challenging problem due to the nonlinear dynamics and under-actuated characteristics of these robots. Traditionally, feedback controllers have been utilized for stabilization and locomotion.…

Accurate beam prediction is essential for mitigating signalling overhead and latency in integrated sensing and communication-enabled massive multi-input multi-output systems. With the aid of multimodal learning, the prediction accuracy can…

Control applications present hard operational constraints. A violation of these can result in unsafe behavior. This paper introduces Safe Interactive Model Based Learning (SiMBL), a framework to refine an existing controller and a system…

Large Language Models (LLMs) have achieved rapid progress in Chinese language understanding, yet accurately evaluating their capabilities remains challenged by benchmark saturation and prohibitive computational costs. While static…

Knowing the link between observed predictive variables and outcomes is crucial for making inference in any regression model. When this link is missing, partially or completely, classical estimation methods fail in recovering the true…

The integration of imitation and reinforcement learning has enabled remarkable advances in humanoid whole-body control, facilitating diverse human-like behaviors. However, research on environment-dependent motions remains limited. Existing…

In this paper, we propose SimMLM, a simple yet powerful framework for multimodal learning with missing modalities. Unlike existing approaches that rely on sophisticated network architectures or complex data imputation techniques, SimMLM…

Unbiased assessment of the predictivity of models learnt by supervised machine-learning methods requires knowledge of the learned function over a reserved test set (not used by the learning algorithm). The quality of the assessment depends,…

Direct preference optimization methods have emerged as a computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) for aligning Large Language Models (LLMs). Latest approaches have streamlined the alignment…

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Despite the advantages of multi-agent reinforcement learning (MARL) for wireless use case such as medium access control (MAC), their real-world deployment in Internet of Things (IoT) is hindered by their sample inefficiency. To alleviate…

General-purpose control demands agents that act across many tasks and embodiments, yet research on reinforcement learning (RL) for continuous control remains dominated by single-task or offline regimes, reinforcing a view that online RL…

The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability…

Training deep neural networks with noise and data heterogeneity is a major challenge. We introduce Lightweight Learnable Adaptive Weighting (LiLAW), a method that dynamically adjusts the loss weight of each training sample based on its…

Due to the notorious modality imbalance problem, multimodal learning (MML) leads to the phenomenon of optimization imbalance, thus struggling to achieve satisfactory performance. Recently, some representative methods have been proposed to…