相关论文: XFBoost: Improving Text Generation with Controllab…

We propose a soft gradient boosting framework for sequential regression that embeds a learnable linear feature transform within the boosting procedure. At each boosting iteration, we train a soft decision tree and learn a linear input…

Maintaining semantic consistency over extended text sequences remains a fundamental challenge in long-form text generation, where conventional training methodologies often struggle to prevent contextual drift and coherence degradation. A…

Large pre-trained language models have repeatedly shown their ability to produce fluent text. Yet even when starting from a prompt, generation can continue in many plausible directions. Current decoding methods with the goal of controlling…

Attributes such as style, fine-grained text, and trajectory are specific conditions for describing motion. However, existing methods often lack precise user control over motion attributes and suffer from limited generalizability to unseen…

This work introduces Focused-Variation Network (FVN), a novel model to control language generation. The main problems in previous controlled language generation models range from the difficulty of generating text according to the given…

As generative models become ubiquitous, there is a critical need for fine-grained control over the generation process. Yet, while controlled generation methods from prompting to fine-tuning proliferate, a fundamental question remains…

The diversity, quantity, and quality of manipulation data are critical for training effective robot policies. However, due to hardware and physical setup constraints, collecting large-scale real-world manipulation data remains difficult to…

With the rapid development of AI-generated content (AIGC), video generation has emerged as one of its most dynamic and impactful subfields. In particular, the advancement of video generation foundation models has led to growing demand for…

Multi-modal keyphrase generation aims to produce a set of keyphrases that represent the core points of the input text-image pair. In this regard, dominant methods mainly focus on multi-modal fusion for keyphrase generation. Nevertheless,…

Text-to-image diffusion models are typically trained to optimize the log-likelihood objective, which presents challenges in meeting specific requirements for downstream tasks, such as image aesthetics and image-text alignment. Recent…

Counterfactual explanations play a pivotal role in explainable artificial intelligence (XAI) by offering intuitive, human-understandable alternatives that elucidate machine learning model decisions. Despite their significance, existing…

The performance of computer vision models in certain real-world applications (e.g., rare wildlife observation) is limited by the small number of available images. Expanding datasets using pre-trained generative models is an effective way to…

Diffusion models have demonstrated remarkable capabilities in generating high-quality samples and enhancing performance across diverse domains through Classifier-Free Guidance (CFG). However, the quality of generated samples is highly…

Text generation often requires high-precision output that obeys task-specific rules. This fine-grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we consider augmenting neural generation models…

In controllable generation tasks, flexibly manipulating the generated images to attain a desired appearance or structure based on a single input image cue remains a critical and longstanding challenge. Achieving this requires the effective…

Recent work has shown that inference-time reasoning and reflection can improve text-to-image generation without retraining. However, existing approaches often rely on implicit, holistic critiques or unconstrained prompt rewrites, making…

We address the issue of hallucination in data-to-text generation, i.e., reducing the generation of text that is unsupported by the source. We conjecture that hallucination can be caused by an encoder-decoder model generating content phrases…

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which,…

Text detoxification is a conditional text generation task aiming to remove offensive content from toxic text. It is highly useful for online forums and social media, where offensive content is frequently encountered. Intuitively, there are…

Recently, text-guided content generation has received extensive attention. In this work, we explore the possibility of text description-based speaker generation, i.e., using text prompts to control the speaker generation process.…