Related papers: Arbitrary-Length Generalization for Addition in a …

The objective of this work is to improve the accuracy of building demand forecasting. This is a more challenging task than grid level forecasting. For the said purpose, we develop a new technique called recurrent transform learning (RTL).…

Generative approaches have been recently shown to be effective for both Entity Disambiguation and Entity Linking (i.e., joint mention detection and disambiguation). However, the previously proposed autoregressive formulation for EL suffers…

Decreasing skilled workers is a very serious problem in the world. To deal with this problem, the skill transfer from experts to robots has been researched. These methods which teach robots by human motion are called imitation learning.…

Language is by its very nature incremental in how it is produced and processed. This property can be exploited by NLP systems to produce fast responses, which has been shown to be beneficial for real-time interactive applications. Recent…

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Inverse text normalization (ITN) is used to convert the spoken form output of an automatic speech recognition (ASR) system to a written form. Traditional handcrafted ITN rules can be complex to transcribe and maintain. Meanwhile neural…

Retrieval-augmented generation (RAG) has emerged as a promising solution for mitigating hallucinations of large language models (LLMs) with retrieved external knowledge. Adaptive RAG enhances this approach by enabling dynamic retrieval…

Diffusion models have gained significant attention in the realm of image generation due to their exceptional performance. Their success has been recently expanded to text generation via generating all tokens within a sequence concurrently.…

Data augmentation is a series of techniques that generate high-quality artificial data by manipulating existing data samples. By leveraging data augmentation techniques, AI models can achieve significantly improved applicability in tasks…

Reinforcement learning (RL) has shown its strength in challenging sequential decision-making problems. The reward function in RL is crucial to the learning performance, as it serves as a measure of the task completion degree. In real-world…

In this work, we introduce Adapt & Align, a method for continual learning of neural networks by aligning latent representations in generative models. Neural Networks suffer from abrupt loss in performance when retrained with additional…

Adapter-based training has emerged as a key mechanism for extending the capabilities of powerful foundation image generators, enabling personalized and stylized text-to-image synthesis. These adapters are typically trained to capture a…

Generative models are widely used for unsupervised learning with various applications, including data compression and signal restoration. Training methods for such systems focus on the generality of the network given limited amount of…

We study the problem of length generalization (LG) in transformers: the ability of a model trained on shorter sequences to maintain performance when evaluated on much longer, previously unseen inputs. Prior work by Huang et al. (2025)…

Unsupervised representation learning methods are widely used for gaining insight into high-dimensional, unstructured, or structured data. In some cases, users may have prior topological knowledge about the data, such as a known cluster…

Transformers trained on tokenized text, audio, and images can generate high-quality autoregressive samples. But handwriting data, represented as sequences of pen coordinates, remains underexplored. We introduce a novel tokenization scheme…

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Data augmentation methods are commonly integrated into the training of anomaly detection models. Previous approaches have primarily focused on replicating real-world anomalies or enhancing diversity, without considering that the standard of…

We present a training-free style-aligned image generation method that leverages a scale-wise autoregressive model. While large-scale text-to-image (T2I) models, particularly diffusion-based methods, have demonstrated impressive generation…

Generative adversarial networks (GANs) learn a deep generative model that is able to synthesise novel, high-dimensional data samples. New data samples are synthesised by passing latent samples, drawn from a chosen prior distribution,…