相关论文: IRIS: Intent Resolution via Inference-time Saccade…

Referring Image Segmentation (RIS) aims to segment the target object in an image given a natural language expression. While recent methods leverage pre-trained vision backbones and more training corpus to achieve impressive results, they…

Reinforcement learning with verifiable rewards (RLVR) has become a key technique for en- hancing LLM reasoning, yet its data ineffi- ciency remains a major bottleneck. Existing methods address this problem only partially, each missing at…

While Multimodal Large Language Models (MLLMs) offer strong perception and reasoning capabilities for image-text input, Visual Question Answering (VQA) focusing on small image details still remains a challenge. Although visual cropping…

Composed image retrieval (CIR) searches a corpus with a reference image and a text describing how to modify it. Despite rapid progress from triplet-trained compositors to zero-shot and generative methods, essentially all systems share one…

Referring Image Segmentation (RIS) is an advanced vision-language task that involves identifying and segmenting objects within an image as described by free-form text descriptions. While previous studies focused on aligning visual and…

Large Language Models (LLMs) demonstrate impressive reasoning ability and the maintenance of world knowledge not only in natural language tasks, but also in some vision-language tasks such as open-domain knowledge-based visual question…

Intent-aware session recommendation (ISR) is pivotal in discerning user intents within sessions for precise predictions. Traditional approaches, however, face limitations due to their presumption of a uniform number of intents across all…

Existing debiasing approaches in Visual Question Answering (VQA) primarily focus on enhancing visual learning, integrating auxiliary models, or employing data augmentation strategies. However, these methods exhibit two major drawbacks.…

Multimodal large language models (MLLMs) still struggle with complex reasoning tasks in Visual Question Answering (VQA). While current methods have advanced by incorporating visual prompts, our study uncovers critical limitations: these…

Large Vision-Language Models (LVLMs) frequently hallucinate, limiting their safe deployment in real-world applications. Existing LLM self-evaluation methods rely on a model's ability to estimate the correctness of its own outputs, which can…

Vision-Language Models (VLMs) have been applied to autonomous driving to support decision-making in complex real-world scenarios. However, their training on static, web-sourced image-text pairs fundamentally limits the precise…

Medical visual question answering (Med-VQA) aims to answer clinically relevant questions grounded in medical images. However, existing multimodal large language models (MLLMs) often exhibit shortcut answering, producing plausible responses…

Multimodal Large Language Models (MLLMs) excel in numerous vision-language tasks yet suffer from hallucinations, producing content inconsistent with input visuals, that undermine reliability in precision-sensitive domains. This issue stems…

Ambiguity resolution is key to effective communication. While humans effortlessly address ambiguity through conversational grounding strategies, the extent to which current language models can emulate these strategies remains unclear. In…

Retrieval-augmented generation (RAG) with large language models (LLMs) plays a crucial role in question answering, as LLMs possess limited knowledge and are not updated with continuously growing information. Most recent work on RAG has…

Object hallucination critically undermines the reliability of Multimodal Large Language Models, often stemming from a fundamental failure in cognitive introspection, where models blindly trust linguistic priors over specific visual…

Human intention is an internal, mental characterization for acquiring desired information. From interactive interfaces containing either textual or graphical information, intention to perceive desired information is subjective and strongly…

In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities. To overcome these challenges, we introduce a novel Visual…

Referring Image Segmentation (RIS) requires identifying objects from images based on textual descriptions. We observe that existing methods significantly underperform on motion-related queries compared to appearance-based ones. To address…

Natural (such as lunar) occultations have long been used to study sources on small angular scales, while coronographs have been used to study high contrast sources. We propose launching the Improved Resolution and Image Selection (IRIS)…