Related papers: DODO: Discrete OCR Diffusion Models

Modern diffusion-based image generative models have made significant progress and become promising to enrich training data for the object detection task. However, the generation quality and the controllability for complex scenes containing…

Image tokenization plays a central role in modern generative modeling by mapping visual inputs into compact representations that serve as an intermediate signal between pixels and generative models. Diffusion-based decoders have recently…

Information extraction from copy-heavy documents, characterized by massive volumes of structurally similar content, represents a critical yet understudied challenge in enterprise document processing. We present a systematic framework that…

Large Multimodal Models (LMMs) have recently shown strong performance on Optical Character Recognition (OCR) tasks, demonstrating their promising capability in document literacy. However, their effectiveness in real-world applications…

The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one. We present a diffusion-based captioning model, dubbed the name DDCap, to allow more decoding flexibility. Unlike image…

Despite the great success of Large Vision-Language Models (LVLMs), they inevitably suffer from hallucination. As we know, both the visual encoder and the Large Language Model (LLM) decoder in LVLMs are Transformer-based, allowing the model…

OCR (Optical Character Recognition) is a technology that offers comprehensive alphanumeric recognition of handwritten and printed characters at electronic speed by merely scanning the document. Recently, the understanding of visual data has…

Detecting objects based on language information is a popular task that includes Open-Vocabulary object Detection (OVD) and Referring Expression Comprehension (REC). In this paper, we advance them to a more practical setting called Described…

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through an iterative denoising process, DLMs possess inherent…

The limited understanding capacity of the visual encoder in Contrastive Language-Image Pre-training (CLIP) has become a key bottleneck for downstream performance. This capacity includes both Discriminative Ability (D-Ability), which…

Optical chemical structure recognition (OCSR) translates molecular images into machine-readable representations like SMILES strings or molecular graphs, but remains challenging in real-world documents due to inexhaustible variations in…

Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation, but generation quality depends critically on the generation order. Prior work either hard-codes an ordering (e.g., blockwise…

Optical Chemical Structure Recognition (OCSR) is critical for converting 2D molecular diagrams from printed literature into machine-readable formats. While Vision-Language Models have shown promise in end-to-end OCR tasks, their direct…

End-to-end autonomous driving via Vision-Language-Action (VLA) models demands a precarious balance between high-fidelity trajectory planning and efficient inference. Existing paradigms typically fall short: autoregressive (AR) VLAs are…

Discrete diffusion language models (dLLMs) provide a fast and flexible alternative to autoregressive models (ARMs) via iterative denoising with parallel updates. However, their evaluation is challenging: existing metrics conflate denoiser…

Recent vision-centric approaches have made significant strides in long-context modeling. Represented by DeepSeek-OCR, these models encode rendered text into continuous vision tokens, achieving high compression rates without sacrificing…

Visual Document Retrieval (VDR) requires representations that capture both fine-grained visual details and global document structure to ensure retrieval efficacy while maintaining computational efficiency. Existing VDR models struggle to…

Although autoregressive models have dominated language modeling in recent years, there has been a growing interest in exploring alternative paradigms to the conventional next-token prediction framework. Diffusion-based language models have…

Transformer-based language models (LMs) are inefficient in long contexts. We propose Dodo, a solution for context compression. Instead of one vector per token in a standard transformer model, Dodo represents text with a dynamic number of…