Related papers: Skywork UniPic: Unified Autoregressive Modeling fo…
Visual-language models have advanced the development of universal models, yet their application in medical imaging remains constrained by specific functional requirements and the limited data. Current general-purpose models are typically…
Deploying foundation models is increasingly constrained by memory footprint, latency, and hardware costs. Post-training compression can mitigate these bottlenecks by reducing the precision of model parameters without significantly degrading…
Deepface generation has traditionally followed a task-driven paradigm, where distinct tasks (e.g., face transfer and hair transfer) are addressed by task-specific models. Nevertheless, this single-task setting severely limits model…
Generative recommendation has recently emerged as a transformative paradigm that directly generates target items, surpassing traditional cascaded approaches. It typically involves two components: a tokenizer that learns item identifiers and…
The rapid progress of large multimodal models has inspired efforts toward unified frameworks that couple understanding and generation. While such paradigms have shown remarkable success in 2D, extending them to 3D remains largely…
Vision-language large models are moving toward the unification of visual understanding and visual generation tasks. However, whether generation can enhance understanding is still under-explored on large data scale. In this work, we analysis…
Recent advancements in Generative Artificial Intelligence (GenAI) have significantly enhanced the capabilities of both image generation and editing. However, current approaches often treat these tasks separately, leading to inefficiencies…
Self-supervised learning has shown its great potential to extract powerful visual representations without human annotations. Various works are proposed to deal with self-supervised learning from different perspectives: (1) contrastive…
Image-text interleaved data, consisting of multiple images and texts arranged in a natural document format, aligns with the presentation paradigm of internet data and closely resembles human reading habits. Recent studies have shown that…
Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often train separate models for each problem setting, which fixes the input-output mapping and…
The success of contrastive learning depends on the construction and utilization of high-quality positive pairs. However, current methods face critical limitations on two fronts: on the construction side, both handcrafted and generative…
In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio. All modalities are trained from scratch under a unified…
Large Language Models (LLMs) have made the ambitious quest for generalist agents significantly far from being a fantasy. A key hurdle for building such general models is the diversity and heterogeneity of tasks and modalities. A promising…
Image processing is a fundamental task in computer vision, which aims at enhancing image quality and extracting essential features for subsequent vision applications. Traditionally, task-specific models are developed for individual tasks…
Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision…
The segmentation of 2D vascular structures via deep learning holds significant clinical value but is hindered by the scarcity of annotated data, severely limiting its widespread application. Developing a universal few-shot vascular…
We introduce ShapeCodeBench, a synthetic benchmark for perception-to-program reconstruction: given a rendered raster image, a model must emit an executable drawing program that a deterministic evaluator re-renders and compares with the…
Recent advancements in unified image generation models, such as OmniGen, have enabled the handling of diverse image generation and editing tasks within a single framework, accepting multimodal, interleaved texts and images in free form.…
In this work, we present VARGPT-v1.1, an advanced unified visual autoregressive model that builds upon our previous framework VARGPT. The model preserves the dual paradigm of next-token prediction for visual understanding and next-scale…
The development of unified multimodal large language models (MLLMs) is fundamentally challenged by the granularity gap between visual understanding and generation: understanding requires high-level semantic abstractions, while image…