Related papers: LRTA: A Transparent Neural-Symbolic Reasoning Fram…
Complex visual reasoning remains a key challenge today. Typically, the challenge is tackled using methodologies such as Chain of Thought (COT) and visual instruction tuning. However, how to organically combine these two methodologies for…
Visual Question Answering (VQA) has attracted a lot of attention in both Computer Vision and Natural Language Processing communities, not least because it offers insight into the relationships between two important sources of information.…
Reinforcement learning (RL) has recently shown strong potential in improving the reasoning capabilities of large language models and is now being actively extended to vision-language models (VLMs). However, existing RL applications in VLMs…
Video Question Answering (VideoQA) has made significant strides by leveraging multimodal learning to align visual and textual modalities. However, current benchmarks overwhelmingly focus on questions answerable through explicit visual…
Recent work has begun to equip vision-language-action (VLA) policies with explicit intermediate reasoning. In embodied control, however, textual chain-of-thought is a poor fit: irrelevant or weakly textual information can interfere with…
Video Question Answering (VideoQA), aiming to correctly answer the given question based on understanding multi-modal video content, is challenging due to the rich video content. From the perspective of video understanding, a good VideoQA…
Building robust vision systems for high-stakes domains such as remote sensing requires stronger visual reasoning than what single-pass inference typically provides; yet, retraining large models is often computationally expensive and data…
A reliable driving assistant should provide consistent responses based on temporally grounded reasoning derived from observed information. In this work, we investigate whether Vision-Language Models (VLMs), when applied as driving…
Despite their linguistic competence, Large Language Models (LLMs) often struggle to reason reliably and flexibly. To identify these shortcomings, we introduce the Non-Linear Reasoning (NLR) dataset, a collection of 55 unique, hand-designed…
Recent developments in multimodal large language models (MLLM) have equipped language models to reason about vision and language jointly. This permits MLLMs to both perceive and answer questions about data visualization across a variety of…
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…
Despite recent advances in Visual QuestionAnswering (VQA), it remains a challenge todetermine how much success can be attributedto sound reasoning and comprehension ability.We seek to investigate this question by propos-ing a new task…
Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation.…
Recently, Vision Language Models (VLMs) have increasingly emphasized document visual grounding to achieve better human-computer interaction, accessibility, and detailed understanding. However, its application to visualizations such as…
Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the cost of tool calls or rely on localized patch-based embeddings that are insufficient to…
Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems which require extensive multi-step reasoning. This is primarily due to the progressive dilution…
Visual question answering is an important task in both natural language and vision understanding. However, in most of the public visual question answering datasets such as VQA, CLEVR, the questions are human generated that specific to the…
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…
Temporal logical understanding, a core facet of human cognition, plays a pivotal role in capturing complex sequential events and their temporal relationships within videos. This capability is particularly crucial in tasks like Video…
To address the hallucination in generative question answering (GQA) where the answer can not be derived from the document, we propose a novel evidence-enhanced triplet generation framework, EATQA, encouraging the model to predict all the…