This information would be provided by experts in the chosen domain, i.e. epidemiologists working on epidemic

Neural networks are capable of superposition -- representing more features than there are dimensions. Recent work considers the analogous concept for computation instead of storage, proposing theoretical constructions. But there has been little investigation into whether these circuits can be learned in practice. In this work, we investigate a toy model for the Universal-AND problem which computes the AND of all $m\choose 2$ pairs of $m$ sparse inputs. The hidden dimension that determines the number of non-linear activations is restricted to pressure the model to find a compute-efficient circuit, called compressed computation. We find that the training process finds a simple solution that does not correspond to theoretical constructions. It is fully dense -- every neuron contributes to every output. The solution circuit naturally scales with dimension, trading off error rates for neuron efficiency. It is similarly robust to changes in sparsity and other key parameters, and extends naturally to other boolean operations and boolean circuits. We explain the found solution in detail and compute why it is more efficient than the theoretical constructions at low sparsity. Our findings shed light on the types of circuits that models like to form and the flexibility of the superposition representation. This contributes to a broader understanding of network circuitry and interpretability.

Mixed Boolean-Arithmetic (MBA) obfuscation protects intellectual property by converting programs into forms that are more complex to analyze. However, MBA has been increasingly exploited by malware developers to evade detection and cause significant real-world problems. Traditional MBA deobfuscation methods often consider these expressions as part of a black box and overlook their internal semantic information. To bridge this gap, we propose a truth table, which is an automatically constructed semantic representation of an expression's behavior that does not rely on external resources. The truth table is a mathematical form that represents the output of expression for all possible combinations of input. We also propose a general and extensible guided MBA deobfuscation framework (gMBA) that modifies a Transformer-based neural encoder-decoder Seq2Seq architecture to incorporate this semantic guidance. Experimental results and in-depth analysis show that integrating expression semantics significantly improves performance and highlights the importance of internal semantic expressions in recovering obfuscated code to its original form.

Human beings naturally utilize multiple reasoning modalities to learn and solve logical problems, i.e., different representational formats such as natural language, code, and symbolic logic. In contrast, most existing LLM-based approaches operate with a single reasoning modality during training, typically natural language. Although some methods explored modality selection or augmentation at inference time, the training process remains modality-blind, limiting synergy among modalities. To fill in this gap, we propose Mixture-of-Thought (MoT), a framework that enables LLMs to reason across three complementary modalities: natural language, code, and a newly introduced symbolic modality, truth-table, which systematically enumerates logical cases and partially mitigates key failure modes in natural language reasoning. MoT adopts a two-phase design: (1) self-evolving MoT training, which jointly learns from filtered, self-generated rationales across modalities; and (2) MoT inference, which fully leverages the synergy of three modalities to produce better predictions. Experiments on logical reasoning benchmarks including FOLIO and ProofWriter demonstrate that our MoT framework consistently and significantly outperforms strong LLM baselines with single-modality chain-of-thought approaches, achieving up to +11.7pp average accuracy gain. Further analyses show that our MoT framework benefits both training and inference stages; that it is particularly effective on harder logical reasoning problems; and that different modalities contribute complementary strengths, with truth-table reasoning helping to overcome key bottlenecks in natural language inference.

Logic synthesis, a critical stage in electronic design automation (EDA), optimizes gate-level circuits to minimize power consumption and area occupancy in integrated circuits (ICs). Traditional logic synthesis tools rely on human-designed heuristics, often yielding suboptimal results. Although differentiable architecture search (DAS) has shown promise in generating circuits from truth tables, it faces challenges such as high computational complexity, convergence to local optima, and extensive hyperparameter tuning. Consequently, we propose a novel approach integrating conditional generative models with DAS for circuit generation. Our approach first introduces CircuitVQ, a circuit tokenizer trained based on our Circuit AutoEncoder We then develop CircuitAR, a masked autoregressive model leveraging CircuitVQ as the tokenizer. CircuitAR can generate preliminary circuit structures from truth tables, which guide DAS in producing functionally equivalent circuits. Notably, we observe the scalability and emergent capability in generating complex circuit structures of our CircuitAR models. Extensive experiments also show the superior performance of our method. This research bridges the gap between probabilistic generative models and precise circuit generation, offering a robust solution for logic synthesis.

TabPFN [Hollmann et al., 2023], a Transformer model pretrained to perform in-context learning on fresh tabular classification problems, was presented at the last ICLR conference. To better understand its behavior, we treat it as a black-box function approximator generator and observe its generated function approximations on a varied selection of training datasets. Exploring its learned inductive biases in this manner, we observe behavior that is at turns either brilliant or baffling. We conclude this post with thoughts on how these results might inform the development, evaluation, and application of prior-data fitted networks (PFNs) in the future.

This paper investigates the learnability of the nonlinearity property of Boolean functions using neural networks. We train encoder style deep neural networks to learn to predict the nonlinearity of Boolean functions from examples of functions in the form of a truth table and their corresponding nonlinearity values. We report empirical results to show that deep neural networks are able to learn to predict the property for functions in 4 and 5 variables with an accuracy above 95%. While these results are positive and a disciplined analysis is being presented for the first time in this regard, we should also underline the statutory warning that it seems quite challenging to extend the idea to higher number of variables, and it is also not clear whether one can get advantage in terms of time and space complexity over the existing combinatorial algorithms.