Various stuff and things in visual data possess specific traits, which can be learned by deep neural networks and are implicitly represented as the visual prior, e.g., object location and shape, in the model.

In recent years, there has been a rapid development of spatio-temporal prediction techniques in response to the increasing demands of traffic management and travel planning. While advanced end-to-end models have achieved notable success in improving predictive performance, their integration and expansion pose significant challenges. This work aims to address these challenges by introducing a spatio-temporal pre-training framework that seamlessly integrates with downstream baselines and enhances their performance. The framework is built upon two key designs: (i) We propose a spatio-temporal mask autoencoder as a pre-training model for learning spatio-temporal dependencies. The model incorporates customized parameter learners and hierarchical spatial pattern encoding networks. These modules are specifically designed to capture spatio-temporal customized representations and intra-and inter-cluster region semantic relationships, which have often been neglected in existing approaches.

Foundation models refer to architectures trained on vast datasets using autoregressive pre-training from natural language processing to capture intricate patterns and motifs. They were originally developed to transfer such learned knowledge to downstream predictive tasks. Recently, however, some studies repurpose these learned representations for phenotype discovery without rigorous validation, risking superficially realistic but clinically incoherent embeddings. To test this mismatch, we trained two autoregressive models -- a sequence-to-sequence LSTM and a reduced Transformer -- on longitudinal ART for HIV and Acute Hypotension datasets. Controlled irregularity was added during training via random inter-visit gaps, while test sequences stayed complete. Patient-trajectory synthesis evaluated distributional and correlational fidelity. Both reproduced feature distributions but failed to preserve cross-feature structure -- showing that generative pre-training yields local realism but limited clinical coherence. These results highlight the need for domain-specific evaluation and support trajectory synthesis as a practical probe before fine-tuning or deployment.

Diffusion distillation is a widely used technique to reduce the sampling cost of diffusion models, yet it often requires extensive training, and the student performance tends to be degraded. Recent studies show that incorporating a GAN objective may alleviate these issues, yet the underlying mechanism remains unclear. In this work, we first identify a key limitation of distillation: mismatched step sizes and parameter numbers between the teacher and the student model lead them to converge to different local minima, rendering direct imitation suboptimal. We further demonstrate that a standalone GAN objective, without relying a distillation loss, overcomes this limitation and is sufficient to convert diffusion models into efficient one-step generators. Based on this finding, we propose that diffusion training may be viewed as a form of generative pre-training, equipping models with capabilities that can be unlocked through lightweight GAN fine-tuning. Supporting this view, we create a one-step generation model by fine-tuning a pre-trained model with 85% of parameters frozen, achieving strong performance with only 0.2M images and near-SOTA results with 5M images. We further present a frequency-domain analysis that may explain the one-step generative capability gained in diffusion training. Overall, our work provides a new perspective for diffusion training, highlighting its role as a powerful generative pre-training process, which can be the basis for building efficient one-step generation models.

Various stuff and things in visual data possess specific traits, which can be learned by deep neural networks and are implicitly represented as the visual prior, e.g., object location and shape, in the model. For example, in conditional image synthesis, spatial conditions failing to adhere to the prior can result in visually inaccurate synthetic results. This work aims to explicitly learn the visual prior and enable the customization of sampling. Inspired by advances in language modeling, we propose to learn Visual prior via Generative Pre-Training, dubbed VisorGPT. By discretizing visual locations, e.g., bounding boxes, human pose, and instance masks, into sequences, VisorGPT can model visual prior through likelihood maximization.

In recent years, there has been a rapid development of spatio-temporal prediction techniques in response to the increasing demands of traffic management and travel planning. While advanced end-to-end models have achieved notable success in improving predictive performance, their integration and expansion pose significant challenges. This work aims to address these challenges by introducing a spatio-temporal pre-training framework that seamlessly integrates with downstream baselines and enhances their performance. The framework is built upon two key designs: (i) We propose a spatio-temporal mask autoencoder as a pre-training model for learning spatio-temporal dependencies. The model incorporates customized parameter learners and hierarchical spatial pattern encoding networks.

Modeling the evolutions of driving scenarios is important for the evaluation and decision-making of autonomous driving systems. Most existing methods focus on one aspect of scene evolution such as map generation, motion prediction, and trajectory planning. In this paper, we propose a unified Generative Pre-training for Driving (GPD-1) model to accomplish all these tasks altogether without additional fine-tuning. We represent each scene with ego, agent, and map tokens and formulate autonomous driving as a unified token generation problem. We adopt the autoregressive transformer architecture and use a scene-level attention mask to enable intra-scene bi-directional interactions. For the ego and agent tokens, we propose a hierarchical positional tokenizer to effectively encode both 2D positions and headings. For the map tokens, we train a map vector-quantized autoencoder to efficiently compress ego-centric semantic maps into discrete tokens. We pre-train our GPD-1 on the large-scale nuPlan dataset and conduct extensive experiments to evaluate its effectiveness. With different prompts, our GPD-1 successfully generalizes to various tasks without finetuning, including scene generation, traffic simulation, closed-loop simulation, map prediction, and motion planning. Code: https://github.com/wzzheng/GPD.

We open-source a state-of-the-art 4B-parameter generative model series for Vietnamese, which includes the base pre-trained monolingual model PhoGPT-4B and its chat variant, PhoGPT-4B-Chat. The base model, PhoGPT-4B, with exactly 3.7B parameters, is pre-trained from scratch on a Vietnamese corpus of 102B tokens, with an 8192 context length, employing a vocabulary of 20480 token types. The chat variant, PhoGPT-4B-Chat, is the modeling output obtained by fine-tuning PhoGPT-4B on a dataset of 70K instructional prompts and their responses, along with an additional 290K conversations. We demonstrate its strong performance compared to previous closed-source and open-source 7B-parameter models. Our PhoGPT models are available at: https://github.com/VinAIResearch/PhoGPT

Generative models have gained more and more attention in recent years for their remarkable success in tasks that required estimating and sampling data distribution to generate high-fidelity synthetic data. In speech, text-to-speech synthesis and neural vocoder are good examples where generative models have shined. While generative models have been applied to different applications in speech, there exists no general-purpose generative model that models speech directly. In this work, we take a step toward this direction by showing a single pre-trained generative model can be adapted to different downstream tasks with strong performance. Specifically, we pre-trained a generative model, named SpeechFlow, on 60k hours of untranscribed speech with Flow Matching and masked conditions. Experiment results show the pre-trained generative model can be fine-tuned with task-specific data to match or surpass existing expert models on speech enhancement, separation, and synthesis. Our work suggested a foundational model for generation tasks in speech can be built with generative pre-training.

This paper introduces TRACE-GPT, which stands for Time-seRies Anomaly-detection with Convolutional Embedding and Generative Pre-trained Transformers. TRACE-GPT is designed to pre-train univariate time-series sensor data and detect faults on unlabeled datasets in semiconductor manufacturing. In semiconductor industry, classifying abnormal time-series sensor data from normal data is important because it is directly related to wafer defect. However, small, unlabeled, and even mixed training data without enough anomalies make classification tasks difficult. In this research, we capture features of time-series data with temporal convolutional embedding and Generative Pre-trained Transformer (GPT) to classify abnormal sequences from normal sequences using cross entropy loss. We prove that our model shows better performance than previous unsupervised models with both an open dataset, the University of California Riverside (UCR) time-series classification archive, and the process log of our Chemical Vapor Deposition (CVD) equipment. Our model has the highest F1 score at Equal Error Rate (EER) across all datasets and is only 0.026 below the supervised state-of-the-art baseline on the open dataset.