Related papers: Struct2D: A Perception-Guided Framework for Spatia…
Multimodal Large Language Models (MLLMs) demonstrate exceptional semantic reasoning but struggle with 3D spatial perception when restricted to pure RGB inputs. Despite leveraging implicit geometric priors from 3D reconstruction models,…
Advancing towards artificial superintelligence requires rich and intelligent perceptual capabilities. A critical frontier in this pursuit is overcoming the limited spatial understanding of Multimodal Large Language Models (MLLMs), where…
We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…
Spatial relation reasoning is a crucial task for multimodal large language models (MLLMs) to understand the objective world. However, current benchmarks have issues like relying on bounding boxes, ignoring perspective substitutions, or…
Recent advancements in Spatial Intelligence (SI) have predominantly relied on Vision-Language Models (VLMs), yet a critical question remains: does spatial understanding originate from visual encoders or the fundamental reasoning backbone?…
Chain-of-Thought (CoT) reasoning has proven effective in natural language tasks but remains underexplored in multimodal alignment. This study investigates its integration into 3D vision-language learning by embedding structured reasoning…
Spatiotemporal reasoning is a fundamental capability for artificial intelligence (AI) in soft tissue surgery, paving the way for intelligent assistive systems and autonomous robotics. While 2D vision-language models show increasing promise…
Embodied intelligence fundamentally requires a capability to determine where to act in 3D space. We formalize this requirement as embodied localization -- the problem of predicting executable 3D points conditioned on visual observations and…
A navigable agent needs to understand both high-level semantic instructions and precise spatial perceptions. Building navigation agents centered on Multimodal Large Language Models (MLLMs) demonstrates a promising solution due to their…
Reasoning lies at the heart of intelligence, shaping the ability to make decisions, draw conclusions, and generalize across domains. In artificial intelligence, as systems increasingly operate in open, uncertain, and multimodal…
This paper addresses the high demand in advanced intelligent robot navigation for a more holistic understanding of spatial environments, by introducing a novel system that harnesses the capabilities of Large Language Models (LLMs) to…
With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to…
We present Team asdfo123's submission to the LLMSR@XLLM25 shared task, which evaluates large language models on producing fine-grained, controllable, and interpretable reasoning processes. Systems must extract all problem conditions,…
When reading long-form text, human cognition is complex and structurized. While large language models (LLMs) process input contexts through a causal and sequential perspective, this approach can potentially limit their ability to handle…
Recent advancements in multi-modal large language models (MLLMs) have shown strong potential for 3D scene understanding. However, existing methods struggle with fine-grained object grounding and contextual reasoning, limiting their ability…
Large language models (LLMs) are becoming attractive as few-shot reasoners to solve Natural Language (NL)-related tasks. However, the understanding of their capability to process structured data like tables remains an under-explored area.…
While diffusion models have shown exceptional capabilities in aesthetic image synthesis, they often struggle with complex spatial understanding and reasoning. Existing approaches resort to Multimodal Large Language Models (MLLMs) to enhance…
Understanding 3D point clouds through language remains a fundamental challenge in computer graphics and visual computing, due to the irregular structure of point cloud data and the lack of explicit reasoning in existing 3D multimodal…
Vision-language models (VLMs) achieve strong performance on spatial reasoning benchmarks, yet it remains unclear whether this reflects structured 3D understanding or reliance on statistical shortcuts in natural images. We introduce a…
Spatial reasoning, the ability to ground language in 3D understanding, remains a persistent challenge for Vision-Language Models (VLMs). We identify two fundamental bottlenecks: inadequate 3D understanding capabilities stemming from…