arXiv:2603.25713v1 Announce Type: new Abstract: High-resolution brain imaging can now capture not just synapse locations but their molecular composition, with the cost of such mapping falling exponentially. Yet such ultrastructural data has so far told us little about local neuronal physiology – specifically, the parameters (e.g., synaptic efficacies, local conductances) that govern neural dynamics. We […]
Grokking as a Falsifiable Finite-Size Transition
arXiv:2603.24746v1 Announce Type: cross Abstract: Grokking — the delayed onset of generalization after early memorization — is often described with phase-transition language, but that claim has lacked falsifiable finite-size inputs. Here we supply those inputs by treating the group order $p$ of $mathbbZ_p$ as an admissible extensive variable and a held-out spectral head-tail contrast as […]
DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers
arXiv:2603.25293v1 Announce Type: new Abstract: Directed Acyclic Graphs (DAGs) are widely used to represent structured knowledge in scientific and technical domains. However, datasets for real-world DAGs remain scarce because constructing them typically requires expert interpretation of domain documents. We study Doc2SemDAG construction: recovering a preferred semantic DAG from a document together with the cited evidence […]
4OPS: Structural Difficulty Modeling in Integer Arithmetic Puzzles
arXiv:2603.25356v1 Announce Type: new Abstract: Arithmetic puzzle games provide a controlled setting for studying difficulty in mathematical reasoning tasks, a core challenge in adaptive learning systems. We investigate the structural determinants of difficulty in a class of integer arithmetic puzzles inspired by number games. We formalize the problem and develop an exact dynamic-programming solver that […]
Quantifying plasticity: a network-based framework linking structure to dynamical regimes
arXiv:2603.25180v1 Announce Type: new Abstract: Plasticity is a fundamental property of complex systems, such as the brain or an organism. Yet it typically remains a descriptive concept inferred retrospectively from observed outcomes, such as modifications in activity or morphology. Here, the network-based operationalization of plasticity is further formalized as the ratio between system size and […]
Probabilistic Abstract Interpretation on Neural Networks via Grids Approximation
arXiv:2603.25266v1 Announce Type: new Abstract: Probabilistic abstract interpretation is a theory used to extract particular properties of a computer program when it is infeasible to test every single inputs. In this paper we apply the theory on neural networks for the same purpose: to analyse density distribution flow of all possible inputs of a neural […]
Mechanistically Interpreting Compression in Vision-Language Models
arXiv:2603.25035v1 Announce Type: new Abstract: Compressed vision-language models (VLMs) are widely used to reduce memory and compute costs, making them a suitable choice for real-world deployment. However, compressing these models raises concerns about whether internal computations and safety behaviors are preserved. In this work, we use causal circuit analysis and crosscoder-based feature comparisons to examine […]
When Sensing Varies with Contexts: Context-as-Transform for Tactile Few-Shot Class-Incremental Learning
arXiv:2603.25115v1 Announce Type: new Abstract: Few-Shot Class-Incremental Learning (FSCIL) can be particularly susceptible to acquisition contexts with only a few labeled samples. A typical scenario is tactile sensing, where the acquisition context (it e.g., diverse devices, contact state, and interaction settings) degrades performance due to a lack of standardization. In this paper, we propose Context-as-Transform […]
Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure
arXiv:2603.22384v2 Announce Type: replace-cross Abstract: Autonomous agents operating in continuous environments must decide not only what to do, but when to act. We introduce a lightweight adaptive temporal control system that learns the optimal interval between cognitive ticks from experience, replacing ad hoc biologically inspired timers with a principled learned policy. The policy state is […]
SWAA: Sliding Window Attention Adaptation for Efficient and Quality Preserving Long Context Processing
arXiv:2512.10411v5 Announce Type: replace-cross Abstract: The quadratic complexity of self attention in Transformer based LLMs renders long context inference prohibitively expensive. While Sliding Window Attention (SWA), the simplest sparse attention pattern, offers a linear complexity alternative, it suffers from catastrophic long context performance collapse, which stems from two fundamental factors: the training inference mismatch when […]
Central Dogma Transformer III: Interpretable AI Across DNA, RNA, and Protein
arXiv:2603.23361v2 Announce Type: replace-cross Abstract: Biological AI models increasingly predict complex cellular responses, yet their learned representations remain disconnected from the molecular processes they aim to capture. We present CDT-III, which extends mechanism-oriented AI across the full central dogma: DNA, RNA, and protein. Its two-stage Virtual Cell Embedder architecture mirrors the spatial compartmentalization of the […]
FEAST: Fully Connected Expressive Attention for Spatial Transcriptomics
arXiv:2603.25247v1 Announce Type: cross Abstract: Spatial Transcriptomics (ST) provides spatially-resolved gene expression, offering crucial insights into tissue architecture and complex diseases. However, its prohibitive cost limits widespread adoption, leading to significant attention on inferring spatial gene expression from readily available whole slide images. While graph neural networks have been proposed to model interactions between tissue […]