Related papers: OCRGenBench: A Comprehensive Benchmark for Evaluat…
Modern voice cloning, also known as zero-shot text-to-speech (TTS), can synthesize speech that closely matches a target speaker from only seconds of reference audio, enabling applications such as personalized speech interfaces and dubbing.…
We present OCR-Quality, a comprehensive human-annotated dataset designed for evaluating and developing OCR quality assessment methods. The dataset consists of 1,000 PDF pages converted to PNG images at 300 DPI, sampled from diverse…
Recent advances in text-to-video generation have achieved impressive performance on short clips, yet evaluating long-form generation under complex textual inputs remains a significant challenge. In response to this challenge, we present…
The ability to research and synthesize knowledge is central to human expertise and progress. A new class of AI systems--designed for generative research synthesis--aims to automate this process by retrieving information from the live web…
In this work, we introduce OmniGen2, a versatile and open-source generative model designed to provide a unified solution for diverse generation tasks, including text-to-image, image editing, and in-context generation. Unlike OmniGen v1,…
In recent years, large-scale models have achieved significant advancements, accompanied by the emergence of numerous high-quality benchmarks for evaluating various aspects of their comprehension abilities. However, most existing benchmarks…
DeepSeek-OCR utilizes an optical 2D mapping approach to achieve high-ratio vision-text compression, claiming to decode text tokens exceeding ten times the input visual tokens. While this suggests a promising solution for the LLM…
The rapid advancement of AIGC-based video generation has underscored the critical need for comprehensive evaluation frameworks that go beyond traditional generation quality metrics to encompass aesthetic appeal. However, existing benchmarks…
Offline goal-conditioned reinforcement learning (GCRL) is a major problem in reinforcement learning (RL) because it provides a simple, unsupervised, and domain-agnostic way to acquire diverse behaviors and representations from unlabeled…
Recent advances in text-to-video (T2V) technology, as demonstrated by models such as Runway Gen-3, Pika, Sora, and Kling, have significantly broadened the applicability and popularity of the technology. This progress has created a growing…
Generating images conditioned on multiple visual references is critical for real-world applications such as multi-subject composition, narrative illustration, and novel view synthesis, yet current models suffer from severe performance…
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…
Many real-world applications involve the use of Optical Character Recognition (OCR) engines to transform handwritten images into transcripts on which downstream Natural Language Processing (NLP) models are applied. In this process, OCR…
Although contemporary text-to-image generation models have achieved remarkable breakthroughs in producing visually appealing images, their capacity to generate precise and flexible typographic elements, especially non-Latin alphabets,…
While current video generation focuses on text or image conditions, practical applications like video editing and vlogging often need to seamlessly connect separate clips. In our work, we introduce Video Connecting, an innovative task that…
Reading comprehension is one of the crucial tasks for furthering research in natural language understanding. A lot of diverse reading comprehension datasets have recently been introduced to study various phenomena in natural language,…
Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two core capabilities: \textbf{\textit{composition}} and…
We introduce OSVBench, a new benchmark for evaluating Large Language Models (LLMs) on the task of generating complete formal specifications for verifying the functional correctness of operating system kernels. This benchmark is built upon a…
While Large Vision-Language Models (LVLMs) demonstrate promising multilingual capabilities, their evaluation is currently hindered by two critical limitations: (1) the use of non-parallel corpora, which conflates inherent language…
In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis. Our framework categorizes evaluations into two distinct groups: first,…