Related papers: PolyGen: Fully Synthetic Vision-Language Training …

Recent text-to-image diffusion models are able to learn and synthesize images containing novel, personalized concepts (e.g., their own pets or specific items) with just a few examples for training. This paper tackles two interconnected…

In the era of deep learning, data is the critical determining factor in the performance of neural network models. Generating large datasets suffers from various difficulties such as scalability, cost efficiency and photorealism. To avoid…

Reinforcement learning (RL) has emerged as a powerful paradigm for improving large language models beyond supervised fine-tuning, yet sustaining performance gains at scale remains an open challenge, as data diversity and structure, rather…

StyleGAN is a state-of-art generative adversarial network architecture that generates random 2D high-quality synthetic facial data samples. In this paper, we recap the StyleGAN architecture and training methodology and present our…

Offline reinforcement learning (RL) offers a promising framework for training agents using pre-collected datasets without the need for further environment interaction. However, policies trained on offline data often struggle to generalise…

Polygon representation learning is essential for diverse applications, encompassing tasks such as shape coding, building pattern classification, and geographic question answering. While recent years have seen considerable advancements in…

In this paper, we introduce LDGen, a novel method for integrating large language models (LLMs) into existing text-to-image diffusion models while minimizing computational demands. Traditional text encoders, such as CLIP and T5, exhibit…

Multimodal Large Language Models (MLLMs) have significantly advanced vision-language understanding. However, even state-of-the-art models struggle with geometric reasoning, revealing a critical bottleneck: the extreme scarcity of…

Accurately reconstructing complex full multi-object scenes from sparse observations remains a core challenge in computer vision and a key step toward scalable and reliable simulation for robotics. In this work, we introduce RecGen, a…

Videos show continuous events, yet most $-$ if not all $-$ video synthesis frameworks treat them discretely in time. In this work, we think of videos of what they should be $-$ time-continuous signals, and extend the paradigm of neural…

Skills are a promising way to improve LLM agent capabilities without retraining, while keeping the added procedure reusable and controllable. However, high-quality skills are still largely written by hand. We introduce SkillGen, a…

Computational models have emerged as powerful tools for multi-scale energy modeling research at the building and urban scale, supporting data-driven analysis across building and urban energy systems. However, these models require large…

Visual grouping -- operationalized through tasks such as instance segmentation, visual grounding, and object detection -- enables applications ranging from robotic perception to photo editing. These fundamental problems in computer vision…

Recent research has highlighted the risk of generative model collapse, where performance progressively degrades when continually trained on self-generated data. However, existing exploration on model collapse is limited to single, unimodal…

Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require separate training, operate on misaligned objectives, and exhibit…

While modern Requirements Engineering (RE) heavily relies on natural language processing and Machine Learning (ML) techniques, their effectiveness is limited by the scarcity of high-quality datasets. This paper introduces Synthline, a…

Deep learning algorithms require extensive data to achieve robust performance. However, data availability is often restricted in the medical domain due to patient privacy concerns. Synthetic data presents a possible solution to these…

The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations. As a result, the research challenge shifts from devising…

Recently, dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs). The final task-specific model often achieves…

Supervised training of an automated medical image analysis system often requires a large amount of expert annotations that are hard to collect. Moreover, the proportions of data available across different classes may be highly imbalanced…