Related papers: What Matters for Grocery Product Retrieval with Op…

Multimodal Large Language Models (MLLMs) have advanced VQA and now support Vision-DeepResearch systems that use search engines for complex visual-textual fact-finding. However, evaluating these visual and textual search abilities is still…

Multimodal large language models have various practical applications that demand strong reasoning abilities. Despite recent advancements, these models still struggle to solve complex geometric problems. A key challenge stems from the lack…

Although large visual-language models (LVLMs) have demonstrated strong performance in multimodal tasks, errors may occasionally arise due to biases during the reasoning process. Recently, reward models (RMs) have become increasingly pivotal…

In autonomous driving, robust place recognition is critical for global localization and loop closure detection. While inter-modality fusion of camera and LiDAR data in multimodal place recognition (MPR) has shown promise in overcoming the…

Multimodal Large Language Models (MLLMs) have achieved strong performance across vision-language tasks, but suffer from significant computational overhead due to the quadratic growth of attention computations with the number of multimodal…

"Bigger the better" has been the predominant trend in recent Large Language Models (LLMs) development. However, LLMs do not suit well for scenarios that require on-device processing, energy efficiency, low memory footprint, and response…

Nowadays, the product search service of e-commerce platforms has become a vital shopping channel in people's life. The retrieval phase of products determines the search system's quality and gradually attracts researchers' attention.…

Retail product or packaged grocery goods images need to classified in various computer vision applications like self checkout stores, supply chain automation and retail execution evaluation. Previous works explore ways to finetune deep…

Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although token pruning has proven effective for accelerating inference, determining when and where to…

Multilingual e-commerce search suffers from severe data imbalance across languages, label noise, and limited supervision for low-resource languages--challenges that impede the cross-lingual generalization of relevance models despite the…

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities, yet they encounter significant computational bottlenecks due to the massive volume of visual tokens. Consequently, visual token pruning, which substantially…

Vision-and-Language Pre-training (VLP) improves model performance for downstream tasks that require image and text inputs. Current VLP approaches differ on (i) model architecture (especially image embedders), (ii) loss functions, and (iii)…

In this report, we introduce InternVL 1.5, an open-source multimodal large language model (MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding. We introduce three simple…

Open-vocabulary change detection (OVCD) seeks to recognize arbitrary changes of interest by enabling generalization beyond a fixed set of predefined classes. We reformulate OVCD as a two-stage pipeline: first generate class-agnostic change…

Vision-language models (VLMs) such as CLIP have shown promising performance on a variety of recognition tasks using the standard zero-shot classification procedure -- computing similarity between the query image and the embedded words for…

Comparative settings (e.g. pairwise choice, listwise ranking) have been adopted by a wide range of subjective studies for image quality assessment (IQA), as it inherently standardizes the evaluation criteria across different observers and…

Open-source Vision-Language Models show immense promise for enterprise applications, yet a critical disconnect exists between academic evaluation and enterprise deployment requirements. Current benchmarks rely heavily on multiple-choice…

Pre-ranking is a critical stage in industrial recommendation systems, tasked with efficiently scoring thousands of recalled items for downstream ranking. A key challenge is the train-serving discrepancy: pre-ranking models are trained only…

Large Vision Language Models (VLMs), such as CLIP, have significantly contributed to various computer vision tasks, including object recognition and object detection. Their open vocabulary feature enhances their value. However, their…

Vision-language pre-trained models have achieved impressive performance on various downstream tasks. However, their large model sizes hinder their utilization on platforms with limited computational resources. We find that directly using…