Related papers: Map2Thought: Explicit 3D Spatial Reasoning via Met…
The evolution of Remote Sensing Vision-Language Models(RS-VLMs) emphasizes the importance of transitioning from perception-centric recognition toward high-level deductive reasoning to enhance cognitive reliability in complex spatial tasks.…
Understanding the physical world - governed by laws of motion, spatial relations, and causality - poses a fundamental challenge for multimodal large language models (MLLMs). While recent advances such as OpenAI o3 and GPT-4o demonstrate…
Charts are high-density visualization carriers for complex data, serving as a crucial medium for information extraction and analysis. Automated chart understanding poses significant challenges to existing multimodal large language models…
In recent years, video question answering based on multimodal large language models (MLLM) has garnered considerable attention, due to the benefits from the substantial advancements in LLMs. However, these models have a notable deficiency…
Pretrained multi-modal large language models (MLLMs) demonstrate strong performance on diverse multimodal tasks, but remain limited in reasoning capabilities for domains where annotations are difficult to collect. In this work, we focus on…
Vision-Language Models (VLMs) have made significant strides in static image understanding but continue to face critical hurdles in spatiotemporal reasoning. A major bottleneck is "multi-image reasoning hallucination", where a massive…
This paper introduces GeoChain, a large-scale benchmark for evaluating step-by-step geographic reasoning in multimodal large language models (MLLMs). Leveraging 1.46 million Mapillary street-level images, GeoChain pairs each image with a…
Images usually convey richer detail than text, but often include redundant information, which potentially downgrades multimodal reasoning performance. When faced with lengthy or complex messages, humans tend to employ abstract thinking to…
Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning. However, existing CoT-based T2I methods largely…
Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their inability to capture fine-grained 3D geometry and spatial…
Multimodal Large Language Models (MLLMs) have achieved remarkable success in open-vocabulary perceptual tasks, yet their ability to solve complex cognitive problems remains limited, especially when visual details are abstract and require…
Spatial reasoning is a critical capability for intelligent robots, yet current vision-language models (VLMs) still fall short of human-level performance in video-based spatial reasoning. This gap mainly stems from two challenges: a…
Recent advances in multimodal techniques have led to significant progress in Medical Visual Question Answering (Med-VQA). However, most existing models focus on global image features rather than localizing disease-specific regions crucial…
Due to the proliferation of short-form content and the rapid adoption of AI, opportunities for deep, reflective thinking have significantly diminished, undermining users' critical thinking and reducing engagement with the reasoning behind…
Large Language Models (LLMs) have demonstrated strong reasoning capabilities through \emph{Chain-of-Thought} (CoT) prompting, which enables step-by-step intermediate reasoning. However, explicit CoT methods rely on discrete token-level…
Geometric Problem Solving (GPS) remains at the heart of enhancing mathematical reasoning in large language models because it requires the combination of diagrammatic understanding, symbolic manipulation and logical inference. In existing…
Spatial understanding is a crucial capability that enables robots to perceive their surroundings, reason about their environment, and interact with it meaningfully. In modern robotics, these capabilities are increasingly provided by…
We present a central-peripheral vision-inspired framework (CVP), a simple yet effective multimodal model for spatial reasoning that draws inspiration from the two types of human visual fields -- central vision and peripheral vision.…
Current text-to-image (T2I) generation models struggle to align spatial composition with the input text, especially in complex scenes. Even layout-based approaches yield suboptimal spatial control, as their generation process is decoupled…
Reasoning about spatial relationships between objects is essential for many real-world robotic tasks, such as fetch-and-delivery, object rearrangement, and object search. The ability to detect and disambiguate different objects and identify…