相关论文: SoPE: Spherical Coordinate-Based Positional Embedd…

Rotary Positional Embedding (RoPE) is a common choice in transformer architectures for encoding relative positional information. Although earlier work has examined omitting RoPE in specific layers, the effect of varying the fraction of…

The rapid advancement of Multimodal Large Language Models (MLLMs) has significantly impacted various multimodal tasks. However, these models face challenges in tasks that require spatial understanding within 3D environments. Efforts to…

Spatial reasoning from monocular images is essential for autonomous driving, yet current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception, particularly under large scale variation and ambiguous object…

Effective multimodal reasoning depends on the alignment of visual and linguistic representations, yet the mechanisms by which vision-language models (VLMs) achieve this alignment remain poorly understood. Following the LiMBeR framework, we…

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved 2D visual understanding, prompting interest in their application to complex 3D reasoning tasks. However, it remains unclear whether these models can…

Autonomous robots that interact with their environment require a detailed semantic scene model. For this, volumetric semantic maps are frequently used. The scene understanding can further be improved by including object-level information in…

Scientific discovery increasingly requires learning on federated datasets, fed by streams from high-resolution instruments, that have extreme class imbalance. Current ML approaches either require impractical data aggregation or fail due to…

Vision Language Models (VLMs) have achieved impressive performance in 2D image understanding, however they are still struggling with spatial understanding which is the foundation of Embodied AI. In this paper, we propose SpatialBot for…

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…

Predictive world models that simulate future observations under explicit camera control are fundamental to interactive AI. Despite rapid advances, current systems lack spatial persistence: they fail to maintain stable scene structures over…

Seamless integration of virtual and physical worlds in augmented reality benefits from the system semantically "understanding" the physical environment. AR research has long focused on the potential of context awareness, demonstrating novel…

While MLLMs perform well on perceptual tasks, they lack precise multimodal alignment, limiting performance. To address this challenge, we propose Vision Dynamic Embedding-Guided Pretraining (VDEP), a hybrid autoregressive training paradigm…

A key challenge in robot manipulation lies in developing policy models with strong spatial understanding, the ability to reason about 3D geometry, object relations, and robot embodiment. Existing methods often fall short: 3D point cloud…

Recent advances in large multimodal models suggest that explicit reasoning mechanisms play a critical role in improving model reliability, interpretability, and cross-modal alignment. While such reasoning-centric approaches have been proven…

Rotary Positional Encoding (RoPE) is widely used in modern large language models. However, when sequences are extended beyond the range seen during training, rotary phases can enter out-of-distribution regimes, leading to spurious…

Large Language Models (LLMs) often suffer from ''Reasoning Collapse'' on challenging mathematical reasoning tasks, where stochastic sampling produces lexical variations of the same erroneous logic rather than genuine semantic exploration.…

Vision-language models (VLMs) have advanced rapidly, but their ability to capture spatial relationships remains a blindspot. Current VLMs are typically built with contrastive language-image pretraining (CLIP) style image encoders. The…

Open-world promptable 3D semantic segmentation remains brittle as semantics are inferred in the input sensor coordinates. Yet, humans, in contrast, interpret parts via functional roles in a canonical space -- wings extend laterally, handles…

Visual-spatial understanding, the ability to infer object relationships and layouts from visual input, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, existing methods face spatial…

In this paper, we propose a robust end-to-end multi-modal pipeline for place recognition where the sensor systems can differ from the map building to the query. Our approach operates directly on images and LiDAR scans without requiring any…