We list the filtering criteria in Tab. 1.

Consequently, image datasets depicting these groups have limited capacity to fully represent these demographics and intersectional identities. While we recognize that assigning a bias score based on these limited resources might not be entirely accurate, it is a vital first step in the right direction. Moreover, the bias effect size (Eq 8) may sometimes be unreliable [Meade et al., As described in Sec. 5, we manually compare our best HardNeg Stable Diffusion with vanilla Stable A storefront with'Hello W orld' written on it. This leaves us with 6 categories and 104 prompts:Category Prompts Colours A brown bird and a blue bear. An elephant is behind a tree.

We list the filtering criteria in Tab. 1.

The original version of this story appeared in Quanta Magazine. When Todd Sacktor was about to turn 3, his 4-year-old sister died of leukemia. A swing set with two seats instead of one," he said, recalling the lingering traces of her presence in the house. "There was this missing person--never spoken of--for which I had only one memory." That memory, faint but enduring, was set in the downstairs den of their home.

Variable binding -- the ability to associate variables with values -- is fundamental to symbolic computation and cognition. Although classical architectures typically implement variable binding via addressable memory, it is not well understood how modern neural networks lacking built-in binding operations may acquire this capacity. We investigate this by training a Transformer to dereference queried variables in symbolic programs where variables are assigned either numerical constants or other variables. Each program requires following chains of variable assignments up to four steps deep to find the queried value, and also contains irrelevant chains of assignments acting as distractors. Our analysis reveals a developmental trajectory with three distinct phases during training: (1) random prediction of numerical constants, (2) a shallow heuristic prioritizing early variable assignments, and (3) the emergence of a systematic mechanism for dereferencing assignment chains. Using causal interventions, we find that the model learns to exploit the residual stream as an addressable memory space, with specialized attention heads routing information across token positions. This mechanism allows the model to dynamically track variable bindings across layers, resulting in accurate dereferencing. Our results show how Transformer models can learn to implement systematic variable binding without explicit architectural support, bridging connectionist and symbolic approaches. To facilitate reproducible research, we developed Variable Scope, an interactive web platform for exploring our findings at https://variablescope.org

We propose a normative model for spatial representation in the hippocampal formation that combines optimality principles, such as maximizing coding range and spatial information per neuron, with an algebraic framework for computing in distributed representation. Spatial position is encoded in a residue number system, with individual residues represented by high-dimensional, complex-valued vectors. These are composed into a single vector representing position by a similarity-preserving, conjunctive vector-binding operation. Self-consistency between the vectors representing position and the individual residues is enforced by a modular attractor network whose modules correspond to the grid cell modules in entorhinal cortex. The vector binding operation can also be used to bind different contexts to spatial representations, yielding a model for entorhinal cortex and hippocampus.

Circadian rhythms regulate the physiology and behavior of humans and animals. Despite advancements in understanding these rhythms and predicting circadian phases at the transcriptional level, predicting circadian phases from proteomic data remains elusive. This challenge is largely due to the scarcity of time labels in proteomic datasets, which are often characterized by small sample sizes, high dimensionality, and significant noise. Furthermore, existing methods for predicting circadian phases from transcriptomic data typically rely on prior knowledge of known rhythmic genes, making them unsuitable for proteomic datasets. To address this gap, we developed a novel computational method using unsupervised deep learning techniques to predict circadian sample phases from proteomic data without requiring time labels or prior knowledge of proteins or genes. Our model involves a two-stage training process optimized for robust circadian phase prediction: an initial greedy one-layer-at-a-time pre-training which generates informative initial parameters followed by fine-tuning. During fine-tuning, a specialized loss function guides the model to align protein expression levels with circadian patterns, enabling it to accurately capture the underlying rhythmic structure within the data. We tested our method on both time-labeled and unlabeled proteomic data. For labeled data, we compared our predictions to the known time labels, achieving high accuracy, while for unlabeled human datasets, including postmortem brain regions and urine samples, we explored circadian disruptions. Notably, our analysis identified disruptions in rhythmic proteins between Alzheimer's disease and control subjects across these samples.

Entity tracking is essential for complex reasoning. To perform in-context entity tracking, language models (LMs) must bind an entity to its attribute (e.g., bind a container to its content) to recall attribute for a given entity. For example, given a context mentioning ``The coffee is in Box Z, the stone is in Box M, the map is in Box H'', to infer ``Box Z contains the coffee'' later, LMs must bind ``Box Z'' to ``coffee''. To explain the binding behaviour of LMs, Feng and Steinhardt (2023) introduce a Binding ID mechanism and state that LMs use a abstract concept called Binding ID (BI) to internally mark entity-attribute pairs. However, they have not directly captured the BI determinant information from entity activations. In this work, we provide a novel view of the Binding ID mechanism by localizing the prototype of BI information. Specifically, we discover that there exists a low-rank subspace in the hidden state (or activation) of LMs, that primarily encodes the order of entity and attribute and which is used as the prototype of BI to causally determine the binding. To identify this subspace, we choose principle component analysis as our first attempt and it is empirically proven to be effective. Moreover, we also discover that when editing representations along directions in the subspace, LMs tend to bind a given entity to other attributes accordingly. For example, by patching activations along the BI encoding direction we can make the LM to infer ``Box Z contains the stone'' and ``Box Z contains the map''.

Open source machine learning (ML) libraries enable developers to integrate advanced ML functionality into their own applications. However, popular ML libraries, such as TensorFlow, are not available natively in all programming languages and software package ecosystems. Hence, developers who wish to use an ML library which is not available in their programming language or ecosystem of choice, may need to resort to using a so-called binding library (or binding). Bindings provide support across programming languages and package ecosystems for reusing a host library. For example, the Keras .NET binding provides support for the Keras library in the NuGet (.NET) ecosystem even though the Keras library was written in Python. In this paper, we collect 2,436 cross-ecosystem bindings for 546 ML libraries across 13 software package ecosystems by using an approach called BindFind, which can automatically identify bindings and link them to their host libraries. Furthermore, we conduct an in-depth study of 133 cross-ecosystem bindings and their development for 40 popular open source ML libraries. Our findings reveal that the majority of ML library bindings are maintained by the community, with npm being the most popular ecosystem for these bindings. Our study also indicates that most bindings cover only a limited range of the host library's releases, often experience considerable delays in supporting new releases, and have widespread technical lag. Our findings highlight key factors to consider for developers integrating bindings for ML libraries and open avenues for researchers to further investigate bindings in software package ecosystems.