arXiv:2406. 07049v3 Announce Type: replace-cross Abstract: Understanding spatial relationships across all dimensions is fundamental for intelligent systems.
arXiv:2606. 12334v1 Announce Type: new Abstract: High-precision robotic manipulation requires fine-grained spatial reasoning that is often difficult to achieve with RGB-only policies due to depth ambiguity and perspective scale issues.
The article investigates how grid cells can reduce spatial aliasing in hippocampal place representations that arise when boundary vector cell (BVC) inputs alone produce indistinguishable sensory patterns across multiple locations. By integrating analytically constructed grid cell modules with BVC-driven place cells, the study demonstrates a 94–99% reduction in spatial aliasing across three environments, with the greatest improvement in the most visually symmetric maze. The results show that grid cells provide complementary spatial signals that disambiguate perceptually identical locations.
arXiv:2606. 17961v1 Announce Type: cross Abstract: Positional encoding is a fundamental component of Transformer architectures, as it injects information about the spatial or sequential arrangement of inputs.
arXiv:2606. 31394v1 Announce Type: cross Abstract: Artificial intelligence is transforming our capability to solve biological challenges.
arXiv:2608.24823v1 Announce Type: new Abstract: Spatially resolved biology requires representations that preserve biological neighborhood structure rather than only exact cross-modal correspondences....
arXiv:2606. 00124v1 Announce Type: cross Abstract: Positional embeddings (PEs) in Vision Transformers (ViTs) are known to impact performance and robustness, but their role in shaping internal spatial representations is not well understood.
arXiv:2603.15412v2 Announce Type: replace Abstract: The mammalian brain, most extensively studied in rodents and bats, solves an enormous variety of non-spatial cognitive tasks using neural circuitry...
arXiv:2609.36217v1 Announce Type: new Abstract: A deeper understanding of brain function requires a precise, structured characterization of behavior.Yet, extracting behavioral representations from vi...
arXiv:2606. 02841v1 Announce Type: new Abstract: Deep neural networks learn representations where individual features often lack interpretable meaning; a single neuron may activate for scattered, unrelated inputs.
O3N is a novel framework that performs open‑vocabulary occupancy prediction from a single omnidirectional RGB image. It introduces a polar‑spiral voxel embedding (PsM) for continuous 360° spatial representation, an Occupancy Cost Aggregation (OCA) module that unifies geometric and semantic supervision, and a Natural Modality Alignment (NMA) pathway that aligns visual, voxel, and text features. Experiments show state‑of‑the‑art results on QuadOcc and Human360Occ benchmarks, with strong cross‑scene generalization and semantic scalability.
arXiv:2606. 01172v1 Announce Type: new Abstract: Modeling unknown latent functions from finite, irregularly sampled measurements is a recurring challenge across science and engineering.
arXiv:2505. 21736v2 Announce Type: replace-cross Abstract: Translation equivariance is a central reason convolutional neural networks have been successful in computer vision.