paper-with-me

홈 › Papers

Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model

2025-07-07 · Mengyao Xu, Gabriel Moreira, Ronay Ak, Radek Osmulski, Yauhen Babakhin, Zhiding Yu, Benedikt Schifferer, Even Oldridge

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 release two model variants, 1B and 3B. The 3B model achieves state of the art performance, scoring NDCG@5 91.0 on ViDoRe V1 and 63.5 on ViDoRe V2, placing first on both leaderboards as of June 27, 2025. Our approach leverages the NVIDIA Eagle2 Vision-Language model (VLM), modifies its architecture by replacing causal attention with bidirectional attention, and integrates a ColBERT-style late interaction mechanism to enable fine-grained multimodal retrieval in a shared embedding space. While this mechanism delivers superior retrieval accuracy, it introduces trade-offs in storage and efficiency. We provide a comprehensive analysis of these trade-offs. Additionally, we adopt a two-stage training strategy to enhance the model's retrieval capabilities.

📄 PDF Abstract BibTeX arXiv:2507.05513

Code (0)

등록된 구현이 없습니다.

Tasks

Image RetrievalLanguage ModelingLanguage ModellingRetrieval

Methods 이 논문이 사용한 방법론

ADOPT Please enter a description about the method here

Similar Papers 제목 키워드 기반

NVIDIA Nemotron Parse 1.1

2025-11-25 · Kateryna Chumachenko, Amala Sanjay Deshmukh, Jarno Seppanen, Ilia Karmanov 외 arxiv

We introduce Nemotron-Parse-1.1, a lightweight document parsing and OCR model that advances the capabilities of its predecessor, Nemoretriever-Parse-1.0. Nemotron-Parse-1.1 delivers improved capabilities across general O…

Applying LLMs for Rescoring N-best ASR Hypotheses of Casual Conversations: Effects of Domain Adaptation and Context Carry-over

2024-06-27 · Atsunori Ogawa, Naoyuki Kamo, Kohei Matsuura, Takanori Ashihara 외

Large language models (LLMs) have been successfully applied for rescoring automatic speech recognition (ASR) hypotheses. However, their ability to rescore ASR hypotheses of casual conversations has not been sufficiently …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Domain Adaptationspeech-recognition+1

ViT3D Alignment of LLaMA3: 3D Medical Image Report Generation

2024-10-11 · Siyou Li, Beining Xu, Yihao Luo, Dong Nie 외

Automatic medical report generation (MRG), which aims to produce detailed text reports from medical images, has emerged as a critical task in this domain. MRG systems can enhance radiological workflows by reducing the ti…

DiagnosticLanguage ModelingLanguage ModellingLarge Language Model+5

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

2024-06-10 · Peize Sun, Yi Jiang, Shoufa Chen, Shilong Zhang 외

We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla a…

Conditional Image GenerationImage GenerationImage Reconstruction

The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling Capabilities

2025-01-23 · MediaTek Research, :, Chan-Jan Hsu, Chia-Sheng Liu 외

Llama-Breeze2 (hereinafter referred to as Breeze2) is a suite of advanced multi-modal language models, available in 3B and 8B parameter configurations, specifically designed to enhance Traditional Chinese language repres…

General KnowledgeInstruction FollowingLanguage ModelingLanguage Modelling