AI Research & Papers — September 29, 2026

Findings

1. [1] 2026-09-29 Introducing Quine: An AI research system designed for the complexity of biology

   At a glance Quine (opens in new tab) is a research effort to create a multimodal world model of biology and an interactive harness connecting models, scientific tools, literature, and researchers.  In collaboration with researchers at the Broad Institute of…  Figure 2: Biology is multiscale and multimodal. (A) Biological evidence stacks from molecules to cells to tissues to patients, with scientific language running underneath all of it. (B) The modalities Project Quine trains on — genomics, proteins, chemistry, RNA and… It’s tempting to frame progress in AI for biology around benchmarks and leaderboards. Those matter, but the real test of Quine is what happens when it encounters science as it’s actually practiced. Can it be useful when evidence is incomplete?…

2. [2] 2026-09-29 The effects of an “algorithmic monoculture” depend on the details

   AI tools are increasingly replacing human judgements in some settings. For instance, resume screening algorithms are often used in hiring, where they may improve efficiency and consistency in decision-making.But some scholars have raised concerns that the adoption of automated systems… “In the latter scenario, you might just target a couple of firms’ algorithms and try to game them, giving yourself a bit of advantage with a few employers.”The wisdom of crowdsThey also considered a less-explored objection: that monoculture can increase…

3. [3] 2026-09-29 Who we become when we talk to machines

   Brian, a middle-aged financial consultant, spends his day sitting in front of three screens. Two of them involve his job. The third features a chatbot, which he has given a woman’s name and frequently uses. Brian spent years on the… After all, as Turkle writes in the book, “Chatbots always agree with us and affirm us. They always offer us their full, undivided attention.” And once that happens, things seem to just go from there. People, meanwhile, can be prickly, demanding, and…

4. [4] 2026-09-29 Staged Depth Training: A Representation Curriculum for PINNs

   arXiv:2609.30299v1 Announce Type: new Abstract: Representation quality is a central determinant of PINNs' performance, yet standard training leaves representations to emerge implicitly while fitting the final solution. We introduce textbf{representation curriculum}, an ordered process in which representations are explicitly learned, transferred independently of their predictors, and progressively refined. We realize it with Staged Depth Training (SDT), which trains a shallow…

5. [5] 2026-09-29 Towards Interpretable Damage Detection based on Aerodynamic Pressure Measurements

   arXiv:2605.08187v2 Announce Type: replace-cross Abstract: The increasing flexibility of modern large wind turbine blades necessitates cost-efficient and reliable structural monitoring solutions. For this purpose, we propose to use aerodynamic pressure measurements obtained via Aerosense, a novel, non-intrusive and economical sensing system. In former work [Franz et al., 2025], we investigated the potential of aerodynamic pressure measurements for structural damage detection…

6. [6] 2026-09-29 NeuralCert: certified computational discovery of extremal mathematical constructions

   arXiv:2609.30296v1 Announce Type: new Abstract: Neural networks are becoming popular in solving mathematical problems, but stochastic models do not provide mathematical exactness by themselves. This study introduces a discovery-to-certification framework in which high-dimensional variational trial functions are learned in a compact separable representation, spectrally diagnosed and pruned, and then certified exactly through multimodular evaluation. Exact certification makes the numerical proofs…

7. [7] 2026-09-29 Beyond Quadratic Loss: The Stability Phase Diagram of Adam

   arXiv:2609.18314v2 Announce Type: replace Abstract: Loss spikes are recurrent instabilities in neural-network training and can arise from multiple mechanisms. For Adam in particular, macroscopic loss spikes have been linked to optimizer dynamics, yet how its two momentum timescales govern them remains unclear. We investigate this dependence by mapping training dynamics across the $(beta_1,beta_2)$ plane. Across a range of model–task settings,…

8. [8] 2026-09-29 When Does Advection-Aware Graph Nowcasting Help? A Controlled Study of Distributed Solar Ramp Forecasting with a Self-Supervised Cloud-Motion Estimator

   arXiv:2609.30286v1 Announce Type: new Abstract: Short-term forecasting of cloud-induced power ramps across a network of distributed photovoltaic (PV) or irradiance sensors is a recognised pain point for grid operators. A natural idea is to make the graph neural network (GNN) advection-aware: connect each site to the sites upwind of it, with edge time-lags set by the cloud-motion vector (CMV), so…

9. [9] 2026-09-29 DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecasting

   arXiv:2608.20052v3 Announce Type: replace Abstract: Probabilistic time series forecasting remains challenging, largely because modeling distinct trend and seasonal dynamics requires specialized approaches. Existing methods often fail to capture the unique inner properties of these components, lack interpretability, or suffer from heavy memory and runtime overhead. To address these limitations, we propose DecoVAE, a lightweight interpretable trend-seasonal VAE framework that explicitly…

10. [10] 2026-09-29 ENAS: An Efficient Hardware-Aware Neural Architecture Search Framework for TinyML on Resource-Constrained Microcontrollers

    arXiv:2609.30272v1 Announce Type: new Abstract: We present textbf{ENAS}, a hardware-aware Neural Architecture Search (NAS) framework that combines a static feasibility check, a cell-based search space supporting standard, depthwise-separable, and bottleneck blocks with optional skip connections, and a three-stage hybrid search strategy (random $rightarrow$ top-$K$ $rightarrow$ mutation) with persistent cross-run caching. Unlike many existing NAS frameworks that rely on GPU acceleration,…

11. [11] 2026-09-29 Offline Policy Evaluation as a decision support tool for designing Adaptive Experiments

    arXiv:2609.30273v1 Announce Type: new Abstract: We investigate how historical data from fixed randomized experiments (A/B tests) can be used to inform the deployment of adaptive experiments based on contextual bandits. Given data collected under a static allocation, our goal is to assess which adaptive policies, if any, would have outperformed the original design and under what conditions. To this end,…

12. [12] 2026-09-29 Cosine Similarity Is Not Evidence: Measuring the Noise Floor of Interpretability Transfer Under Quantization

    arXiv:2609.30275v1 Announce Type: new Abstract: A statistic reported without the quantity needed to interpret it is not evidence. We develop that thesis for a concrete practice in AI safety. Interpretability artifacts are calibrated on full-precision weights, deployed on quantized ones, and certified as surviving the change by scale-invariant statistics (cosine similarity, correlation, AUROC) that are reported without their noise floor.…

13. [13] 2026-09-29 Fixed Points Without Fixed Diffusion: Implicit Neural Sheaves for Convergent Test-Time Computation

    arXiv:2609.30277v1 Announce Type: new Abstract: Implicit Graph Neural Networks (IGNNs) define node representations as fixed points of message-passing operators, enabling effectively infinite-depth propagation, iteration-independent parameterization, and flexible test-time computation. Yet these benefits depend on the equilibrium being unique and attainable by fixed-point iteration. Existing constructions often impose constraints on recurrent updates to obtain these guarantees, limiting the transformations available at…

14. [14] 2026-09-29 Seasonal and Quantum-inspired Models for Neutron Monitor Time Series Forecasting

    arXiv:2609.30281v1 Announce Type: new Abstract: We present a focused and reproducible study of multi-horizon forecasting on the Lomnicky Stit neutron monitor (LMKS) time series. Our evaluation suite covers simple seasonal baselines, modern deep sequence models, and functional and quantum-inspired architectures, including Seasonal Naive, Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), N-BEATS, Kolmogorov-Arnold Networks (KAN), and two quantum-inspired variants, QiLSTM…

15. [15] 2026-09-29 Why Clipping Matters in AdaGrad? Toward a High-Probability Theory under Generalized Smoothness

    arXiv:2609.30276v1 Announce Type: new Abstract: We analyze the original same-step coordinate-wise AdaGrad under generalized smoothness and heavy-tailed noise with bounded variance. In this setting, local curvature may grow sub-quadratically with the gradient norm, and stochastic gradients are assumed to have only bounded conditional second moments. We show that unclipped AdaGrad can become emph{anisotropically miscalibrated}: under heavy-tailed noise, the adaptive denominator…

16. [16] 2026-09-29 Neural Ideals and Neural Codes: An Algebraic Framework for Neural Network Classification and Feature Interpretation

    arXiv:2609.30279v1 Announce Type: new Abstract: Understanding the features captured by the hidden layers of neural networks is a fundamental challenge in machine learning, despite their widespread success across various classification problems. In this work, we propose an algebraic framework for examining neural networks that model classification problems. Certain results, such as the correspondence between the neural network and neural ideals,…

17. [17] 2026-09-29 LiD-GLM: Lipschitz-constrained Deep Generalized Linear Models

    arXiv:2608.16340v2 Announce Type: replace-cross Abstract: The combination of traditional statistical models and neural network (NN) components into semi-structured hybrid models is an intriguing approach to construct models that, ideally, combine traditional interpretability with the unprecedented flexibility of NNs. In order to preserve interpretability, it is usually necessary to restrict the NN components to prevent them from dominating the model. However,…

18. [18] 2026-09-29 Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think

    arXiv:2609.30036v2 Announce Type: replace Abstract: Planners built on visual world models commonly score each predicted outcome by its distance to the encoded goal image. We show that this target can limit control even with exact dynamics and globally optimal short-horizon search: reaching a goal may require actions that initially move away from it. With frozen LeWM models, intermediate targets substantially…

19. [19] 2026-09-29 Scaling Density Functional Theory with Gaussian Splatting

    arXiv:2609.31483v1 Announce Type: cross Abstract: Density functional theory (DFT) strikes a practical balance between accuracy and computational cost in many problems of computational chemistry and materials science. However, many DFT calculations are limited by fixed atom-centered basis sets, which dictate how accuracy and cost scale with system size. We propose Gaussian Splatting for Density Functional Theory (GS-DFT), which represents molecular…

20. [20] 2026-09-29 LocUS: Head Selection and Subspace Projection for Targeted Activation Steering

    arXiv:2609.31122v1 Announce Type: cross Abstract: Activation steering is a powerful training-free paradigm for controlling large language models at inference time. However, standard approaches estimate a per-layer steering direction from contrastive data and apply it on the layer's entire representation space, which may couple the intervention to off-target properties present in the contrastive data and degrade unrelated capabilities. To mitigate this…

21. [21] 2026-09-29 Unlocking the Forecasting Economy: A Suite of Datasets for the Full Lifecycle of Prediction Market: [Experiments & Analysis]

    arXiv:2604.20421v2 Announce Type: replace Abstract: Prediction markets are markets for trading claims on universal future events (e.g., presidential elections). Fueled by a meteoric surge with over $50 billion trading volume, they have emerged as a promising forecasting mechanism, where their prices provide continuously updated signals of collective beliefs. In decentralized platforms (e.g., Polymarket), the prediction market lifecycle include six stages:…

22. [22] 2026-09-29 Proper Scoring Rules for Right-Censored Survival Data

    arXiv:2606.06393v2 Announce Type: replace Abstract: Proper scoring rules provide a rigorous theoretical basis for the training and evaluation of probabilistic forecasts. In survival analysis, such forecasts describe the distribution of the time until an event occurs. However, this event time is often only partially observed because follow-up may end before the event occurs, resulting in right censoring. We propose a…

23. [23] 2026-09-29 LapDDPM: Spectral Perturbation Diffusion for Robust Single-Cell Manifold Generation

    arXiv:2506.13344v2 Announce Type: replace Abstract: Generating high-fidelity and biologically plausible synthetic single-cell RNA sequencing (scRNA-seq) data is a critical challenge in computational biology, driven by the need to model high-dimensional, sparse, and non-linear cellular manifolds. Existing generative models often fail to capture the complex topology of cellular differentiation or lack robustness against technical noise and structural variability. We introduce LapDDPM,…

24. [24] 2026-09-29 UniAR: A Unified Framework for Autism Recognition Enhanced by Multi-View Prompt Learning

    arXiv:2609.31298v2 Announce Type: cross Abstract: Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disorder for which early and accurate diagnosis is critical to improving long-term developmental outcomes. However, existing ASD recognition methods are often constrained by the scarcity of diagnostic text data, forcing them to rely mainly on visual analysis and limiting their ability to model clinically meaningful semantic reasoning.…

Sources

1. [1] Introducing Quine: An AI research system designed for the complexity of biology
2. [2] The effects of an “algorithmic monoculture” depend on the details
3. [3] Who we become when we talk to machines
4. [4] Staged Depth Training: A Representation Curriculum for PINNs
5. [5] Towards Interpretable Damage Detection based on Aerodynamic Pressure Measurements
6. [6] NeuralCert: certified computational discovery of extremal mathematical constructions
7. [7] Beyond Quadratic Loss: The Stability Phase Diagram of Adam
8. [8] When Does Advection-Aware Graph Nowcasting Help? A Controlled Study of Distributed Solar Ramp Forecasting with a Self-Supervised Cloud-Motion Estimator
9. [9] DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecasting
10. [10] ENAS: An Efficient Hardware-Aware Neural Architecture Search Framework for TinyML on Resource-Constrained Microcontrollers
11. [11] Offline Policy Evaluation as a decision support tool for designing Adaptive Experiments
12. [12] Cosine Similarity Is Not Evidence: Measuring the Noise Floor of Interpretability Transfer Under Quantization
13. [13] Fixed Points Without Fixed Diffusion: Implicit Neural Sheaves for Convergent Test-Time Computation
14. [14] Seasonal and Quantum-inspired Models for Neutron Monitor Time Series Forecasting
15. [15] Why Clipping Matters in AdaGrad? Toward a High-Probability Theory under Generalized Smoothness
16. [16] Neural Ideals and Neural Codes: An Algebraic Framework for Neural Network Classification and Feature Interpretation
17. [17] LiD-GLM: Lipschitz-constrained Deep Generalized Linear Models
18. [18] Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think
19. [19] Scaling Density Functional Theory with Gaussian Splatting
20. [20] LocUS: Head Selection and Subspace Projection for Targeted Activation Steering
21. [21] Unlocking the Forecasting Economy: A Suite of Datasets for the Full Lifecycle of Prediction Market: [Experiments & Analysis]
22. [22] Proper Scoring Rules for Right-Censored Survival Data
23. [23] LapDDPM: Spectral Perturbation Diffusion for Robust Single-Cell Manifold Generation
24. [24] UniAR: A Unified Framework for Autism Recognition Enhanced by Multi-View Prompt Learning