Pattern Selectivity
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models
arXiv:2606.05378v1 Announce Type: new Abstract: We test whether a single screen-and-ablate recipe -- identify attention-head circuits by task-pattern selectivity, then verify by causal ablation against a matched-random null -- produces consistent mechanistic claims across model families. The recipe ports across pipelines; the specific circuit it identifies does not. Across four composed tasks (indirect-object identification, greater-than, successor sequences, variable binding) and three...
Conditional Hypothesis Generation for LLM-Based Text Analysis with Researcher-Specified Covariates
Announce Type: new Abstract: A core goal of computational social science is to discover interpretable differences in how language varies across outcomes of interest, such as political affiliation or instructional quality. Recent LLM-based hypothesis generation methods describe such differences in natural language, but select for globally discriminative patterns without accounting for covariates that shape the data based on researchers' domain knowledge. When covariates are ignored, selected...
Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing
Announce Type: new Abstract: Real-world datasets often contain spurious correlations that are not causally related to the target label. When such correlations dominate the majority of training samples, models tend to rely on them, leading to misclassification of minority samples that do not exhibit the same spurious patterns. While a potential approach is to select subsets of data to better represent the minority samples, this may require access to group labels, which are typically unknown.
Modes of natural selection on maternal and zygotic gene expression in Drosophila melanogaster embryos
Early embryonic development involves the coordination of gene expression from two distinct genomes, as mothers load eggs with gene products prior to the beginning of zygotic transcription. Because the maternal transcriptome is controlled by the mothers regulatory genotype rather than that of the embryo, these two sequential developmental programs may experience distinct evolutionary constraints and selection pressures despite both existing within the embryo. To infer modes of selection on...
Recombination and repetitive genomic landscapes are decoupled in a close relative of Caenorhabditis elegans
Genomes often exhibit heterogeneity across chromosomes, and distributions of protein-coding genes, repetitive elements, and polymorphisms are not uniform along chromosomes in multiple species. One explanation for these patterns is recombination rate variation. As recombination interacts with selection to shape the evolutionary fates of alleles, variation in recombination rate within and between chromosomes could promote differences in the distribution of genomic features across chromosomes.
Co-optimization of Diffusive and Tomographic Blur in Computed Axial Lithography via Experimental Kernel Identification
Announce Type: cross Abstract: Computed Axial Lithography is a volumetric additive manufacturing method that selectively cures photosensitive resin through the 3D superposition of patterns of light, offering advantages over layer-based processes including rapid print times, reduced layer artifacts, and compatibility with high-viscosity materials. However, diffusive effects, primarily those of free-radical quenchers such as oxygen, blur the boundary between cured and uncured regions, limiting...
QBE – Compiler Back end: Version 1.3
QBE 1.3 took a while to cook, but it is the most significant release since 1.0 with around 7k new lines of code and 1.5k deleted ones. In addition to the usual bug fixes, QBE gained a new and original IL matching algorithm, new optimizations from Roland Paterson-Jones, Scott Graham added support for the Windows ABI, and I implemented a plan suggested by Michael Forney to have QBE produce position-independent code (as in shared objects). QBE is teamwork, and I am happy to thank all the...
MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models
arXiv:2606.04027v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autoregressive LLMs. Because mask tokens are native inputs and tokens are committed by confidence rather than position, harmful content can be induced through infilling and outside the monitored prefix. Existing jailbreaks either miss this native infill capability or rely...
A Held-Out Transition-Pair Falsifier for Long-Horizon Non-Abelian State Tracking
Announce Type: new Abstract: State tracking exposes a sharp limitation of sequence models: the relevant signal is often not a summary of observed tokens, but an ordered latent state that evolves through non-commutative transformations. We introduce a held-out transition-pair falsifier for finite non-Abelian group tracking. The protocol forbids selected ordered generator pairs during training and requires the same local patterns during evaluation, blocking one direct local-transition...
Electrolyte Bonding Engineering for Highly Uniform GeTe-based CBRAM and Parallel Hebbian Learning in Selector-free Hopfield Networks
arXiv:2606.05768v1 Announce Type: new Abstract: Hopfield networks offer a hardware-friendly framework for energy-efficient associative memory, yet their practical realization in memristor crossbar arrays is critically hindered by device-to-device (D2D) variability, which prevents reliable parallel programming. Here, we address this bottleneck through systematic composition engineering of the Ge-Te solid electrolyte in conductive bridge random access memory (CBRAM) devices.