相关论文: Seeing as Experts Do: A Knowledge-Augmented Agent …

Different from the general visual classification, some classification tasks are more challenging as they need the professional categories of the images. In the paper, we call them expert-level classification. Previous fine-grained vision…

Large Language Models (LLMs) have demonstrated significant potential across various domains. However, they often struggle with integrating external knowledge and performing complex reasoning, leading to hallucinations and unreliable…

Entity alignment (EA) aims to identify entities across different knowledge graphs (KGs) that refer to the same real-world object and plays a critical role in knowledge fusion and integration. Traditional EA methods mainly rely on knowledge…

As Large Language Models (LLMs) gain expertise across diverse domains and modalities, scalable oversight becomes increasingly challenging, particularly when their capabilities may surpass human evaluators. Debate has emerged as a promising…

Humans can robustly localize visual evidence and provide grounded answers even in noisy environments by identifying critical cues and then relating them to the full context in a bottom-up manner. Inspired by this, we propose DeepScan, a…

When answering questions about an image, it not only needs knowing what -- understanding the fine-grained contents (e.g., objects, relationships) in the image, but also telling why -- reasoning over grounding visual cues to derive the…

Legal question answering (QA) has attracted increasing attention from people seeking legal advice, which aims to retrieve the most applicable answers from a large-scale database of question-answer pairs. Previous methods mainly use a…

Fact-based Visual Question Answering (FVQA), a challenging variant of VQA, requires a QA-system to include facts from a diverse knowledge graph (KG) in its reasoning process to produce an answer. Large KGs, especially common-sense KGs, are…

Fine-grained visual classification (FGVC) is challenging but more critical than traditional classification tasks. It requires distinguishing different subcategories with the inherently subtle intra-class object variations. Previous works…

Complex information needs in real-world search scenarios demand deep reasoning and knowledge synthesis across diverse sources, which traditional retrieval-augmented generation (RAG) pipelines struggle to address effectively. Current…

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to…

Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieval fragments reasoning, imposing a hidden "tool tax" of extra tokens and steps. Second,…

Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e.g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the…

Vision-language models (VLMs) show promise for autonomous driving but often lack transparent reasoning capabilities that are critical for safety. We investigate whether explicitly modeling reasoning during fine-tuning enhances VLM…

Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation rooted in their lack of commonsense world knowledge. To…

Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including…

Vision-language models benefit from high-resolution images, but the increase in visual-token count incurs high compute overhead. Humans resolve this tension via foveation: a coarse view guides "where to look", while selectively acquired…

Vision evaluations are typically done through multi-step processes. In most contemporary fields, experts analyze images using structured, evidence-based adaptive questioning. In plant pathology, botanists inspect leaf images, identify…

Reinforcement learning (RL) has emerged as a critical technique for enhancing LLM-based deep search agents. However, existing approaches primarily rely on binary outcome rewards, which fail to capture the comprehensiveness and factuality of…

Vision-Language-Action (VLA) models benefit from chain-of-thought (CoT) reasoning, but existing approaches incur high inference overhead and rely on discrete reasoning representations that mismatch continuous perception and control. We…