Related papers: NVIDIA Nemotron Parse 1.1

Abstractive compression utilizes smaller langauge models to condense query-relevant context, reducing computational costs in retrieval-augmented generation (RAG). However, retrieved documents often include information that is either…

Despite rapid recent progress in the terminal capabilities of large language models, the training data strategies behind state-of-the-art terminal agents remain largely undisclosed. We address this gap through a systematic study of data…

In this work we present a new framework for neural networks compression with fine-tuning, which we called Neural Network Compression Framework (NNCF). It leverages recent advances of various network compression methods and implements some…

Recent advances in vision-language models have demonstrated remarkable performance across diverse multi-modal tasks, including document question answering that leverages structured visual cues from text, tables, and figures. However, unlike…

Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning…

Large Language Models (LLMs) have shown strong reasoning capabilities, particularly when enhanced through Reinforcement Learning (RL). While prior work has successfully applied RL to mathematical reasoning -- where rules and correctness are…

Why do security cameras, sensors, and siri use cloud servers instead of on-board computation? The lack of very-low-power, high-performance chips greatly limits the ability to field untethered edge devices. We present the NV-1, a new…

Learning high-quality, robust, efficient, and disentangled representations is a central challenge in artificial intelligence (AI). Deep metric learning frameworks tackle this challenge primarily using architectural and optimization…

We present Arabic-Nougat, a suite of OCR models for converting Arabic book pages into structured Markdown text. Based on Meta's Nougat architecture, Arabic-Nougat includes three specialized models: arabic-small-nougat, arabic-base-nougat,…

Hardware accelerator for convolution neural network (CNNs) enables real time applications of artificial intelligence technology. However, most of the accelerators only support dense CNN computations or suffers complex control to support…

This paper proposes OCR++, an open-source framework designed for a variety of information extraction tasks from scholarly articles including metadata (title, author names, affiliation and e-mail), structure (section headings and body text,…

GLM-OCR is an efficient 0.9B-parameter compact multimodal model designed for real-world document understanding. It combines a 0.4B-parameter CogViT visual encoder with a 0.5B-parameter GLM language decoder, achieving a strong balance…

Multimodal documents contain diverse elements, such as tables, figures, and layouts, which can complicate retrieval tasks. While current approaches typically combine dense visual embedding models with supervised rerankers to achieve…

Implicit Neural representations (INRs) have emerged as a promising approach for video compression, and have achieved comparable performance to the state-of-the-art codecs such as H.266/VVC. However, existing INR-based methods struggle to…

We propose OmniCaptioner, a versatile visual captioning framework for generating fine-grained textual descriptions across a wide variety of visual domains. Unlike prior methods limited to specific image types (e.g., natural images or…

Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their abilities to generate and understand cross-modal data. However, processing long sequences of visual tokens extracted…

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The…

Recent advancements in the area of Computer Vision with state-of-art Neural Networks has given a boost to Optical Character Recognition (OCR) accuracies. However, extracting characters/text alone is often insufficient for relevant…

Motivated by the growing demand for retrieval systems that operate across modalities, we introduce llama-nemoretriever-colembed, a unified text-image retrieval model that delivers state-of-the-art performance across multiple benchmarks. We…

Optical character recognition (OCR) technology has been widely used in various scenes, as shown in Figure 1. Designing a practical OCR system is still a meaningful but challenging task. In previous work, considering the efficiency and…