Related papers: EtriCA: Event-Triggered Context-Aware Story Genera…

The finetuning of pretrained transformer-based language generation models are typically conducted in an end-to-end manner, where the model learns to attend to relevant parts of the input by itself. However, there does not exist a mechanism…

Recent approaches to data-to-text generation have shown great promise thanks to the use of large-scale datasets and the application of neural network architectures which are trained end-to-end. These models rely on representation learning…

Our brain receives a dynamically changing stream of sensorimotor data. Yet, we perceive a rather organized world, which we segment into and perceive as events. Computational theories of cognitive science on event-predictive cognition…

Recent neural approaches to data-to-text generation have mostly focused on improving content fidelity while lacking explicit control over writing styles (e.g., word choices, sentence structures). More traditional systems use templates to…

The advent of large pre-trained generative language models has provided a common framework for AI story generation via sampling the model to create sequences that continue the story. However, sampling alone is insufficient for story…

Large language model agents rely on effective model context to obtain task-relevant information for decision-making. Many existing context engineering approaches primarily rely on the context generated from the past experience and retrieval…

Neural sequence to sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on cases where generation is conditioned on both a short…

Automated storytelling has long captured the attention of researchers for the ubiquity of narratives in everyday life. However, it is challenging to maintain coherence and stay on-topic toward a specific ending when generating narratives…

Current context augmentation methods, such as retrieval-augmented generation, are essential for solving knowledge-intensive reasoning tasks. However, they typically adhere to a rigid, brute-force strategy that executes retrieval at every…

Retrieval-augmented generation (RAG) systems rely on retrieval models for identifying relevant contexts and answer generation models for utilizing those contexts. However, retrievers exhibit imperfect recall and precision, limiting…

Question Generation is the task of automatically creating questions from textual input. In this work we present a new Attentional Encoder--Decoder Recurrent Neural Network model for automatic question generation. Our model incorporates…

In this paper, we propose a recent and under-researched paradigm for the task of event detection (ED) by casting it as a question-answering (QA) problem with the possibility of multiple answers and the support of entities. The extraction of…

Story generation aims to produce image sequences that depict coherent narratives while maintaining subject consistency across frames. Although existing methods have excelled in producing coherent and expressive stories, they remain largely…

Neural sequence-to-sequence models have provided a viable new approach for abstractive text summarization (meaning they are not restricted to simply selecting and rearranging passages from the original text). However, these models have two…

The quadratic complexity of self-attention in Transformers has hindered the processing of long text. To alleviate this problem, previous works have proposed to sparsify the attention matrix, taking advantage of the observation that crucial…

The Neural Contextual Reinforcement Framework introduces an innovative approach to enhancing the logical coherence and structural consistency of text generated by large language models. Leveraging reinforcement learning principles, the…

Despite the tremendous success in text-to-image generative models, localized text-to-image generation (that is, generating objects or features at specific locations in an image while maintaining a consistent overall generation) still…

Utilizing large-scale pretrained models is a well-known strategy to enhance performance on various target tasks. It is typically achieved through fine-tuning pretrained models on target tasks. However, na\"{\i}ve fine-tuning may not fully…

Achieving ID-preserving text-to-video (T2V) generation remains challenging despite recent advances in diffusion-based models. Existing approaches often fail to capture fine-grained facial dynamics or maintain temporal identity coherence. To…

The inherent ambiguity of cause and effect boundaries poses a challenge in evaluating causal event extraction tasks. Traditional metrics like Exact Match and BertScore poorly reflect model performance, so we trained evaluation models to…