相关论文: Extrapolative Controlled Sequence Generation via I…

The conformational landscape of proteins is crucial to understanding their functionality in complex biological processes. Traditional physics-based computational methods, such as molecular dynamics (MD) simulations, suffer from rare event…

Learning goal conditioned control in the real world is a challenging open problem in robotics. Reinforcement learning systems have the potential to learn autonomously via trial-and-error, but in practice the costs of manual reward design,…

The field of video generation has expanded significantly in recent years, with controllable and compositional video generation garnering considerable interest. Most methods rely on leveraging annotations such as text, objects' bounding…

We propose ARISE, a framework that iteratively induces rules and generates synthetic data for text classification. We combine synthetic data generation and automatic rule induction, via bootstrapping, to iteratively filter the generated…

Standard supervised classification trains models to imitate the exact labels provided by a perfect oracle. This imitation happens in a single pass, restricting the model to a fixed compute budget even when inputs vary in complexity.…

Generative AI models offer powerful capabilities but often lack transparency, making it difficult to interpret their output. This is critical in cases involving artistic or copyrighted content. This work introduces a search-inspired…

When the world changes, so does the text that humans write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are…

Neural networks are surprisingly good at interpolating and perform remarkably well when the training set examples resemble those in the test set. However, they are often unable to extrapolate patterns beyond the seen data, even when the…

Generative Adversarial Networks (GANs) advance face synthesis through learning the underlying distribution of observed data. Despite the high-quality generated faces, some minority groups can be rarely generated from the trained models due…

Generative Artificial Intelligence (AI) has rapidly become a powerful tool, capable of generating various types of data, such as images and text. However, despite the significant advancement of generative AI, time series generative AI…

Recent advances in Deep Learning and probabilistic modeling have led to strong improvements in generative models for images. On the one hand, Generative Adversarial Networks (GANs) have contributed a highly effective adversarial learning…

We investigate the expressive power of deep residual neural networks idealized as continuous dynamical systems through control theory. Specifically, we consider two properties that arise from supervised learning, namely universal…

With the rapid development of Large Language Models (LLMs), Controllable Text Generation (CTG) has become a critical technology for enhancing system reliability and user experience. Addressing the limitations of traditional methods, this…

Training large transformers using next-token prediction has given rise to groundbreaking advancements in AI. While this generative AI approach has produced impressive results, it heavily leans on human supervision. Even state-of-the-art AI…

This beta technical report asks how reusable experience should be represented so that it can function as effective test-time control and as a substrate for iterative evolution. We study this question in 4.590 controlled trials across 45…

Class Incremental Learning (CIL) requires models to continuously learn new classes without forgetting previously learned ones, while maintaining stable performance across all possible class sequences. In real-world settings, the order in…

The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is…

We introduce a simple, general strategy to manipulate the behavior of a neural decoder that enables it to generate outputs that have specific properties of interest (e.g., sequences of a pre-specified length). The model can be thought of as…

We introduce Adaptive Procedural Task Generation (APT-Gen), an approach to progressively generate a sequence of tasks as curricula to facilitate reinforcement learning in hard-exploration problems. At the heart of our approach, a task…

Loss functions play a crucial role in deep metric learning thus a variety of them have been proposed. Some supervise the learning process by pairwise or tripletwise similarity constraints while others take advantage of structured similarity…