Probing Spatial Structure
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Probing Spatial Structure in Pretrained Audio Representations
Announce Type: new Abstract: Pretrained spatial audio encoders are increasingly used as general-purpose representations for perceptual tasks, yet their spatial encoding capabilities remain poorly understood. We introduce the Spatial Audio Representation Learning (SARL) benchmark, a controlled framework for evaluating spatial information in pretrained audio models. SARL probes source-level factors (azimuth, elevation, distance, class) and room-level factors (RT60, volume, shape).
Imprints of primordial magnetic fields in gravitational collapse during early structure formation
Announce Type: replace-cross Abstract: Context. Primordial magnetic fields (PMFs) generated in the early Universe might have left observable imprints on present-day large-scale structure. However, the spatial scales on which primordial signatures are able to survive the nonlinear processes that accompany structure formation remain unclear.
Methods for Inferring Interaction Potentials from Cross-Linking Mass Spectrometry Data
Announce Type: new Abstract: Cross-linking mass spectrometry (XL-MS) has emerged as a powerful quantitative technique for probing intra-protein structural information as well as protein-protein interactions at an unprecedented scale. XL-MS data yield information on the pairwise spatial proximity of proteins through inter-molecular linkers. However, systematic methods for adapting such data for coarse-grained interacting particle models remain limited.
Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders
arXiv:2509.22015v2 Announce Type: replace Abstract: Standard Sparse Autoencoders (SAEs) excel at discovering a dictionary of a model's learned features, providing a powerful lens for passive feature discovery. However, this passive nature makes it difficult to systematically evaluate or analyze concepts that users explicitly care about. We introduce Concept-SAE, a framework that augments SAEs with a structured and controllable interface for probing user-defined concepts.
The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning
Announce Type: new Abstract: Large Language Model (LLM)-based navigation systems commonly construct explicit spatial representations (e.g., topological graphs, semantic raster maps) and translate them into textual descriptions as LLMs' inputs. However, the linguistic structures of such text-based spatial representations and the choices of contextual features (e.g., topology, geometry) they contain are often treated as neutral engineering decisions rather than key factors that shape LLMs'...
RPCASSM: Robust PCA State Space Model For Infrared Small Target Detection
arXiv:2606.01689v1 Announce Type: new Abstract: The detection and segmentation of infrared small targets have important application significance in the fields of surveillance and security, maritime rescue and so on. Due to the low occupancy of these targets in long-distance imaging, the mainstream visual state space model is inefficient and difficult to accurately model the target edge. The existing infrared state space models do not deviate from the mainstream visual state space structure...
Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures
Announce Type: replace Abstract: Large language models (LLMs) are deployed on increasingly complex tasks that require multi-step decision-making. Understanding their algorithmic reasoning abilities is therefore crucial. However, we lack a diagnostic benchmark for evaluating these capabilities.
A prognostic human brain network for diffuse midline glioma
Abstract Diffuse midline gliomas (DMGs) are near-universally lethal tumours of the childhood central nervous system1,2. In animal models, DMGs form brain-wide integrated networks through neuron-to-glioma synapses3,4,5,6 and glioma-to-glioma gap junctional coupling3. This extensive connectivity robustly promotes the growth and invasion of DMG3,4,5,6,7,8,9 and other glial malignancies10,11,12 through paracrine mechanisms and direct neuron-to-glioma synapses.
MeerKAT reveals three electron acceleration sites in one solar flare
MeerKAT reveals three electron acceleration sites in one solar flare Sadie Harley Scientific Editor Robert Egan Associate Editor Solar flares are the most explosive energy-release events in the solar corona, leading to intense particle acceleration, plasma heating and bulk plasma motions on short timescales. Core questions during solar flares remain unresolved, including how and where particle acceleration occurs, and how energized electrons propagate through coronal magnetic structures....
A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents
Announce Type: replace Abstract: Understanding an agent's goals helps explain and predict its behaviour, yet there is no established methodology for reliably attributing goals to agentic systems. We propose a framework for evaluating goal-directedness that integrates behavioural evaluation with interpretability-based analyses of models' internal representations. As a case study, we examine an LLM agent navigating a 2D grid world towards a goal state.