Related papers: Exploring the Paradigm Shift from Grounding to Sko…

Large Language Models (LLMs) provide flexible natural language processing capabilities, while knowledge graphs (KGs) offer explicit and structured knowledge. Integrating these two in a complementary manner enables the development of…

Multi-modal Large Language Models (MLLMs) for Visual Question Answering (VQA) often suffer from dual limitations: knowledge hallucination and insufficient fine-grained visual perception. Crucially, we identify that commonsense graphs and…

Large Language Models (LLMs) may suffer from hallucinations in real-world applications due to the lack of relevant knowledge. In contrast, knowledge graphs encompass extensive, multi-relational structures that store a vast array of symbolic…

Charts are widely used for data visualization across various fields, including education, research, and business. Chart Question Answering (CQA) is an emerging task focused on the automatic interpretation and reasoning of data presented in…

Generalization in Visual Question Answering (VQA) requires models to answer questions about images with contexts beyond the training distribution. Existing attempts primarily refine unimodal aspects, overlooking enhancements in multimodal…

Zero-shot visual question answering (ZS-VQA), an emerged critical research area, intends to answer visual questions without providing training samples. Existing research in ZS-VQA has proposed to leverage knowledge graphs or large language…

Deploying Vision-Language Models (VLMs) on edge devices is challenged by resource constraints and performance degradation under distribution shifts. While test-time adaptation (TTA) can counteract such shifts, existing methods are too…

Large Language Models (LLMs) exhibit persistent logical failures in complex reasoning due to the lack of an internal axiomatic framework. We propose Mathesis, a neuro-symbolic architecture that encodes mathematical states as higher-order…

Large language models (LLMs) have shown promise in table Question Answering (Table QA). However, extending these capabilities to multi-table QA remains challenging due to unreliable schema linking across complex tables. Existing methods…

In this paper, the LCV2 modular method is proposed for the Grounded Visual Question Answering task in the vision-language multimodal domain. This approach relies on a frozen large language model (LLM) as intermediate mediator between the…

State-of-the-art vision-language models (VLMs) score impressively on video benchmarks yet stumble on basic visual reasoning tasks involving spatial relations, navigation, and object selection that a preschooler solves easily. We hypothesize…

Large vision-language models (LVLMs) struggle to reliably detect visual primitives in charts and align them with semantic representations, which severely limits their performance on complex visual reasoning. This lack of perceptual…

Existing Multimodal Large Language Models (MLLMs) and Visual Language Pretrained Models (VLPMs) have shown remarkable performances in the general Visual Question Answering (VQA). However, these models struggle with VQA questions that…

Vision-Language Models (VLMs) have been increasingly applied in real-world scenarios due to their outstanding understanding and reasoning capabilities. Although VLMs have already demonstrated impressive capabilities in common visual…

We have seen great progress in basic perceptual tasks such as object recognition and detection. However, AI models still fail to match humans in high-level vision tasks due to the lack of capacities for deeper reasoning. Recently the new…

Knowledge graphs contain informative factual knowledge but are considered incomplete. To answer complex queries under incomplete knowledge, learning-based Complex Query Answering (CQA) models are proposed to directly learn from the…

Emerging multimodal large language models (MLLMs) exhibit great potential for chart question answering (CQA). Recent efforts primarily focus on scaling up training datasets (i.e., charts, data tables, and question-answer (QA) pairs) through…

Complex Query Answering (CQA) has been extensively studied in recent years. In order to model data that is closer to real-world distribution, knowledge graphs with different modalities have been introduced. Triple KGs, as the classic KGs…

Compositional spatio-temporal reasoning poses a significant challenge in the field of video question answering (VideoQA). Existing approaches struggle to establish effective symbolic reasoning structures, which are crucial for answering…

Large language models (LLMs) have demonstrated remarkable performance on question-answering (QA) tasks because of their superior capabilities in natural language understanding and generation. However, LLM-based QA struggles with complex QA…