相关论文: Scientific Graphics Program Synthesis via Dual Sel…

Competitive programming poses a significant challenge for Code LLMs. While recent models have shown promise, they heavily rely on finite real-world data, raising concerns about scalability and contamination. In this paper, we investigate a…

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…

Training of semantic segmentation models for material analysis requires micrographs and their corresponding masks. It is quite unlikely that perfect masks will be drawn, especially at the edges of objects, and sometimes the amount of data…

Simulation-based data synthesis has emerged as a powerful paradigm for advancing real-world robotic manipulation. Yet existing datasets remain insufficient for robust bimanual manipulation due to (1) the lack of scalable task generation…

Despite the potential of synthetic medical data for augmenting and improving the generalizability of deep learning models, memorization in generative models can lead to unintended leakage of sensitive patient information and limit model…

Significant strides have been made toward designing better generative models in recent years. Despite this progress, however, state-of-the-art approaches are still largely unable to capture complex global structure in data. For example,…

Self-supervised learning (SSL) with vision transformers (ViTs) has proven effective for representation learning as demonstrated by the impressive performance on various downstream tasks. Despite these successes, existing ViT-based SSL…

In the rapidly advancing field of robotics, dual-arm coordination and complex object manipulation are essential capabilities for developing advanced autonomous systems. However, the scarcity of diverse, high-quality demonstration data and…

We propose a new approach for synthesizing fully detailed art-stylized images from sketches. Given a sketch, with no semantic tagging, and a reference image of a specific style, the model can synthesize meaningful details with colors and…

In autoregressive (AR) image generation, visual tokenizers compress images into compact discrete latent tokens, enabling efficient training of downstream autoregressive models for visual generation via next-token prediction. While scaling…

We investigate how to generate multimodal image outputs, such as RGB, depth, and surface normals, with a single generative model. The challenge is to produce outputs that are realistic, and also consistent with each other. Our solution…

Visual generative models based on latent space have achieved great success, underscoring the significance of visual tokenization. Mapping images to latents boosts efficiency and enables multimodal alignment for scaling up in downstream…

Modern HPC applications produce increasingly large amounts of data, which limits the performance of current extreme-scale systems. Data reduction techniques, such as lossy compression, help to mitigate this issue by decreasing the size of…

In this work, we show the generative capability of an image classifier network by synthesizing high-resolution, photo-realistic, and diverse images at scale. The overall methodology, called Synthesize-It-Classifier (STIC), does not require…

Graph learning algorithms have attained state-of-the-art performance on many graph analysis tasks such as node classification, link prediction, and clustering. It has, however, become hard to track the field's burgeoning progress. One…

Reverse engineering and rapid prototyping of computer-aided design (CAD) models from 3D scans, sketches, or simple text prompts are vital in industrial product design. However, recent advances in geometric deep learning techniques lack a…

Synthetic data offers a scalable solution for vision-language pre-training, yet current state-of-the-art methods typically rely on scaling up a single generative backbone, which introduces generator-specific spectral biases and limits…

Visual generative and understanding models typically rely on distinct tokenizers to process images, presenting a key challenge for unifying them within a single framework. Recent studies attempt to address this by connecting the training of…

Recent advances in deep learning have driven rapid progress in time series forecasting, yet many state-of-the-art models continue to struggle with robust performance in real-world applications, even when they achieve strong results on…

Large scale simulations of complex systems ranging from climate and astrophysics to crowd dynamics, produce routinely petabytes of data and are projected to reach the zettabytes level in the coming decade. These simulations enable…