Related papers: Guided Learning: Lubricating End-to-End Modeling f…

Federated Learning (FL) holds great potential for diverse applications owing to its privacy-preserving nature. However, its convergence is often challenged by non-IID data distributions, limiting its effectiveness in real-world deployments.…

Decision making algorithms are used in a multitude of different applications. Conventional approaches for designing decision algorithms employ principled and simplified modelling, based on which one can determine decisions via tractable…

We build a theoretical framework for designing and understanding practical meta-learning methods that integrates sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential…

Adapting to diverse user needs at test time is a key challenge in controllable multi-objective generation. Existing methods are insufficient: merging-based approaches provide indirect, suboptimal control at the parameter level, often…

We consider a class of a nested optimization problems involving inner and outer objectives. We observe that by taking into explicit account the optimization dynamics for the inner objective it is possible to derive a general framework that…

Over the past decade, deep neural networks have demonstrated significant success using the training scheme that involves mini-batch stochastic gradient descent on extensive datasets. Expanding upon this accomplishment, there has been a…

In this paper, we advocate for two stages in a neural network's decision making process. The first is the existing feed-forward inference framework where patterns in given data are sensed and associated with previously learned patterns. The…

Deep learning, a branch of artificial intelligence, is a data-driven method that uses multiple layers of interconnected units or neurons to learn intricate patterns and representations directly from raw input data. Empowered by this…

Autonomous driving systems have a pipeline of perception, decision, planning, and control. The decision module processes information from the perception module and directs the execution of downstream planning and control modules. On the…

Artificial intelligence (AI) plays a crucial role in autonomous driving (AD) research, propelling its development towards intelligence and efficiency. Currently, the development of AD technology follows two main technical paths:…

In recent years, vision-based end-to-end autonomous driving has emerged as a new paradigm. However, popular end-to-end approaches typically rely on visual feature extraction networks trained under label supervision. This limited supervision…

In this research we propose a new method for training predictive machine learning models for prescriptive applications. This approach, which we refer to as coupled validation, is based on tweaking the validation step in the standard…

Key objectives in conditional molecular generation include ensuring chemical validity, aligning generated molecules with target properties, promoting structural diversity, and enabling efficient sampling for discovery. Recent advances in…

Traditional quantitative investment research is encountering diminishing returns alongside rising labor and time costs. To overcome these challenges, we introduce the Large Investment Model (LIM), a novel research paradigm designed to…

In some applications, edge learning is experiencing a shift in focusing from conventional learning from scratch to new two-stage learning unifying pre-training and task-specific fine-tuning. This paper considers the problem of joint…

Planning is a critical component of end-to-end autonomous driving. However, prevailing imitation learning methods often suffer from mode collapse, failing to produce diverse trajectory hypotheses. Meanwhile, existing generative approaches…

While end-to-end autonomous driving has advanced significantly, prevailing methods remain fundamentally misaligned with human cognitive principles in both perception and planning. In this paper, we propose CogAD, a novel end-to-end…

Repeated Sampling (RS) is a simple inference-time algorithm that has been shown to improve model performance on complex tasks. Although it is an effective way of scaling inference time, it often struggles to generate diverse solution…

Many IoT applications at the network edge demand intelligent decisions in a real-time manner. The edge device alone, however, often cannot achieve real-time edge intelligence due to its constrained computing resources and limited local…

We introduce DualMind, a generalist agent designed to tackle various decision-making tasks that addresses challenges posed by current methods, such as overfitting behaviors and dependence on task-specific fine-tuning. DualMind uses a novel…