相关论文: Towards Unifying Reference Expression Generation a…

Joint entity and relation extraction plays a pivotal role in various applications, notably in the construction of knowledge graphs. Despite recent progress, existing approaches often fall short in two key aspects: richness of representation…

We present a unified formulation and model for three motion and 3D perception tasks: optical flow, rectified stereo matching and unrectified stereo depth estimation from posed images. Unlike previous specialized architectures for each…

We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for cross modality…

Text and formulas constitute the core informational components of many documents. Accurately and efficiently recognizing both is crucial for developing robust and generalizable document parsing systems. Recently, vision-language models…

Self-evolving memory serves as the trainable parameters for Large Language Models (LLMs)-based agents, where extraction (distilling insights from experience) and management (updating the memory bank) must be tightly coordinated. Existing…

Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel…

This paper introduces a novel unified representation of diffusion models for image generation and segmentation. Specifically, we use a colormap to represent entity-level masks, addressing the challenge of varying entity numbers while…

Representing code changes as numeric feature vectors, i.e., code change representations, is usually an essential step to automate many software engineering tasks related to code changes, e.g., commit message generation and just-in-time…

We propose In-Context Translation (ICT), a general learning framework to unify visual recognition (e.g., semantic segmentation), low-level image processing (e.g., denoising), and conditional image generation (e.g., edge-to-image synthesis).…

Textual-visual cross-modal retrieval has been a hot research topic in both computer vision and natural language processing communities. Learning appropriate representations for multi-modal data is crucial for the cross-modal retrieval…

Visual question answering requires a deep understanding of both images and natural language. However, most methods mainly focus on visual concept; such as the relationships between various objects. The limited use of object categories…

Referring Camouflaged Object Detection (Ref-COD) segments specified camouflaged objects in a scene by leveraging a small set of referring images. Though effective, current systems adopt a dual-branch design that requires reference images at…

Large Language Models (LLMs) showcase remarkable abilities, yet they struggle with limitations such as hallucinations, outdated knowledge, opacity, and inexplicable reasoning. To address these challenges, Retrieval-Augmented Generation…

Relational understanding is critical for a number of visually-rich documents (VRDs) understanding tasks. Through multi-modal pre-training, recent studies provide comprehensive contextual representations and exploit them as prior knowledge…

Referring Expression Segmentation (RES) has attracted rising attention, aiming to identify and segment objects based on natural language expressions. While substantial progress has been made in RES, the emergence of Generalized Referring…

Referring expression generation (REG) algorithms offer computational models of the production of referring expressions. In earlier work, a corpus of referring expressions (REs) in Mandarin was introduced. In the present paper, we annotate…

Large Language Models (LLMs) have achieved impressive performance across a wide range of applications. However, they often suffer from hallucinations in knowledge-intensive domains due to their reliance on static pretraining corpora. To…

Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring…

Existing methods for detection rule generation are tightly coupled to specific input-output combinations, requiring dedicated pipelines for each. We formalize this problem as a unified mapping f:C*L->R and characterize optimal rules through…

Traditional Retrieval-Augmented Generation (RAG) approaches generally assume that retrieval and generation occur on powerful servers removed from the end user. While this reduces local hardware constraints, it introduces significant…