Related papers: ReConText3D: Replay-based Continual Text-to-3D Gen…

A major obstacle to developing artificial intelligence applications capable of true lifelong learning is that artificial neural networks quickly or catastrophically forget previously learned tasks when trained on a new one. Numerous methods…

This paper investigates a 2D to 3D image translation method with a straightforward technique, enabling correlated 2D X-ray to 3D CT-like reconstruction. We observe that existing approaches, which integrate information across multiple 2D…

We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge. The learned features are…

Reading and repeatedly retelling a short story is a common and effective approach to learning the meanings and usages of target words. However, learners often struggle with comprehending, recalling, and retelling the story contexts of these…

Modern Neural Machine Translation systems exhibit strong performance in several different languages and are constantly improving. Their ability to learn continuously is, however, still severely limited by the catastrophic forgetting issue.…

Text-to-3D generation has achieved significant success by incorporating powerful 2D diffusion models, but insufficient 3D prior knowledge also leads to the inconsistency of 3D geometry. Recently, since large-scale multi-view datasets have…

Large Language Models(LLMs) have revolutionized text generation and multimodal perception,but their capabilities in 3D content generation remain underexplored. Existing methods compromise by producing either low-resolution meshes or coarse…

This work presents a lifelong learning approach to train a multilingual Text-To-Speech (TTS) system, where each language was seen as an individual task and was learned sequentially and continually. It does not require pooled data from all…

Table-to-text generation involves generating appropriate textual descriptions given structured tabular data. It has attracted increasing attention in recent years thanks to the popularity of neural network models and the availability of…

While text-to-3D generation has attracted growing interest, existing methods often struggle to produce 3D assets that align well with human preferences. Current preference alignment techniques for 3D content typically rely on…

Recent advances in 3D scene generation produce visually appealing output, but current representations hinder artists' workflows that require modifiable 3D textured mesh scenes for visual effects and game development. Despite significant…

With the emergence of Transformers and Vision-Language Models (VLMs) such as CLIP, fine-tuning large pre-trained models has recently become a prevalent strategy in Continual Learning. This has led to the development of numerous prompting…

Autoregressive language models dominate modern text generation, yet their sequential nature introduces fundamental limitations: decoding is slow, and maintaining global coherence remains challenging. Diffusion models offer a promising…

Customized text-to-video generation (CTVG) has recently witnessed great progress in generating tailored videos from user-specific text. However, most CTVG methods assume that personalized concepts remain static and do not expand…

Recent AI-based 3D content creation has largely evolved along two paths: feed-forward image-to-3D reconstruction approaches and 3D generative models trained with 2D or 3D supervision. In this work, we show that existing feed-forward…

Text-to-3D generation has achieved remarkable progress in recent years, yet evaluating these methods remains challenging for two reasons: i) Existing benchmarks lack fine-grained evaluation on different prompt categories and evaluation…

Reinforcement learning (RL) has improved guided image generation with diffusion models by directly optimizing rewards that capture image quality, aesthetics, and instruction following capabilities. However, the resulting generative policies…

Humans are capable of learning new tasks without forgetting previous ones, while neural networks fail due to catastrophic forgetting between new and previously-learned tasks. We consider a class-incremental setting which means that the…

Future deep learning models will be distinguished by systems that perpetually learn through interaction, imagination, and cooperation, blurring the line between training and inference. This makes continual learning a critical challenge, as…

Federated Continual Learning (FCL) has recently emerged as a crucial research area, as data from distributed clients typically arrives as a stream, requiring sequential learning. This paper explores a more practical and challenging FCL…