相关论文: OneVision: An End-to-End Generative Framework for …

While multi-modal Visual Language Models (VLMs) have demonstrated significant success across various domains, the integration of VLMs into recommendation and retrieval systems remains a challenge, due to issues like training objective…

Constrained by the separate encoding of vision and language, existing grounding and referring segmentation works heavily rely on bulky Transformer-based fusion en-/decoders and a variety of early-stage interaction technologies.…

In this paper, we present a unified end-to-end approach to build a large scale Visual Search and Recommendation system for e-commerce. Previous works have targeted these problems in isolation. We believe a more effective and elegant…

Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual…

Synthesizing multi-view 3D from one single image is a significant but challenging task. Zero-1-to-3 methods have achieved great success by lifting a 2D latent diffusion model to the 3D scope. The target view image is generated with a…

Visual grounding is a task that aims to locate a target object according to a natural language expression. As a multi-modal task, feature interaction between textual and visual inputs is vital. However, previous solutions mainly handle each…

On large-scale e-commerce platforms with tens of millions of active monthly users, recommending visually similar products is essential for enabling users to efficiently discover items that align with their preferences. This study presents…

Almost all digital videos are coded into compact representations before being transmitted. Such compact representations need to be decoded back to pixels before being displayed to humans and - as usual - before being enhanced/analyzed by…

This paper addresses the challenge of building multimodal recommender systems for the movie domain, where sparse item metadata (e.g., title and genres) can limit retrieval quality and downstream recommendations. We introduce RAG-VisualRec,…

Vision-Language Models(VLMs) excel at autoregressive text generation, yet end-to-end autonomous driving requires multi-task learning with structured outputs and heterogeneous decoding behaviors, such as autoregressive language generation,…

Unifying multimodal understanding, generation and reconstruction representation in a single tokenizer remains a key challenge in building unified models. Previous research predominantly attempts to address this in a dual encoder paradigm,…

Generative Design workflows have introduced alternative paradigms in the domain of computational design, allowing designers to generate large pools of valid solutions by defining a set of goals and constraints. However, analyzing and…

The evaluation of text-generative vision-language models is a challenging yet crucial endeavor. By addressing the limitations of existing Visual Question Answering (VQA) benchmarks and proposing innovative evaluation methodologies, our…

Visual search offers an intuitive way for customers to explore diverse product catalogs, particularly in consumer-to-consumer (C2C) marketplaces where listings are often unstructured and visually driven. This paper presents a scalable…

Sparse-view 3D modeling represents a fundamental tension between reconstruction fidelity and generative plausibility. While feed-forward reconstruction excels in efficiency and input alignment, it often lacks the global priors needed for…

Improving vision-language models (VLMs) in the post-training stage typically relies on supervised fine-tuning or reinforcement learning, methods that necessitate costly, human-annotated data. While self-supervised techniques have proven…

One of the fundamental challenges in video object segmentation is to find an effective representation of the target and background appearance. The best performing approaches resort to extensive fine-tuning of a convolutional neural network…

Large Multimodal Models (LMMs) have made significant strides in visual question-answering for single images. Recent advancements like long-context LMMs have allowed them to ingest larger, or even multiple, images. However, the ability to…

Recent vision-language models (VLMs) typically rely on a single vision encoder trained with contrastive image-text objectives, such as CLIP-style pretraining. While contrastive encoders are effective for cross-modal alignment and retrieval,…

Knowledge-based Vision Question Answering (KB-VQA) systems address complex visual-grounded questions with knowledge retrieved from external knowledge bases. The tasks of knowledge retrieval and answer generation tasks both necessitate…