Related papers: Recursive Decoding: A Situated Cognition Approach …

Compositional generalization -- the ability to understand and generate novel combinations of learned concepts -- enables models to extend their capabilities beyond limited experiences. While effective, the data structures and principles…

An important and difficult task in code-switched speech recognition is to recognize the language, as lots of words in two languages can sound similar, especially in some accents. We focus on improving performance of end-to-end Automatic…

In real-world recommender systems, such as in the music domain, repeat consumption is a common phenomenon where users frequently listen to a small set of preferred songs or artists repeatedly. The key point of modeling repeat consumption is…

We propose reCSE, a self supervised contrastive learning sentence representation framework based on feature reshaping. This framework is different from the current advanced models that use discrete data augmentation methods, but instead…

Recently CKY-based models show great potential in unsupervised grammar induction thanks to their human-like encoding paradigm, which runs recursively and hierarchically, but requires $O(n^3)$ time-complexity. Recursive Transformer based on…

We present a new method for large language models to solve compositional tasks. Although they have shown strong performance on traditional language understanding tasks, large language models struggle to solve compositional tasks, where the…

Compositional generalization remains a foundational weakness of modern neural networks, limiting their robustness and applicability in domains requiring out-of-distribution reasoning. A central, yet unverified, assumption in neuro-symbolic…

In recent years, neural machine translation (NMT) has become the dominant approach in automated translation. However, like many other deep learning approaches, NMT suffers from overfitting when the amount of training data is limited. This…

Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial…

It is believed that Gradient Descent (GD) induces an implicit bias towards good generalization in training machine learning models. This paper provides a fine-grained analysis of the dynamics of GD for the matrix sensing problem, whose goal…

Language models have recently been shown capable of performing regression wherein numeric predictions are represented as decoded strings. In this work, we provide theoretical grounds for this capability and furthermore investigate the…

Sequence-to-sequence learning with neural networks has become the de facto standard for sequence prediction tasks. This approach typically models the local distribution over the next word with a powerful neural network that can condition on…

Compositional generalization is the ability to generalize systematically to a new data distribution by combining known components. Although humans seem to have a great ability to generalize compositionally, state-of-the-art neural models…

Mainstream 3D representation learning approaches are built upon contrastive or generative modeling pretext tasks, where great improvements in performance on various downstream tasks have been achieved. However, we find these two paradigms…

End-to-end trained Recurrent Neural Networks (RNNs) have been successfully applied to numerous problems that require processing sequences, such as image captioning, machine translation, and text recognition. However, RNNs often struggle to…

Compositional generalization is the ability of generalizing novel compositions from seen primitives, and has received much attention in vision-and-language (V\&L) recently. Due to the multi-modal nature of V\&L tasks, the primitives…

Recurrent Neural Networks can be trained to produce sequences of tokens given some input, as exemplified by recent results in machine translation and image captioning. The current approach to training them consists of maximizing the…

Radiology Report Generation (RRG) aims to produce accurate and coherent diagnostics from medical images. Although large vision language models (LVLM) improve report fluency and accuracy, they exhibit hallucinations, generating plausible yet…

Recent advances in large language models have shown that autoregressive modeling can generate complex and novel sequences that have many real-world applications. However, these models must generate outputs autoregressively, which becomes…

In natural language processing, most models try to learn semantic representations merely from texts. The learned representations encode the distributional semantics but fail to connect to any knowledge about the physical world. In contrast,…