An observatory detected the first radio signal from the interstellar object 3I/Atlas. An image of the interstellar comet 3I/Atlas, captured by the Hubble telescope on July 21, 2025. More evidence has emerged to support the natural origin of comet 3I/Atlas . After several weeks of conspiracy theories, social media debates, and speculation on popular podcasts such as Joe Rogan's, this interstellar object is still a comet . The most recent confirmation came from an observatory in South Africa that detected the first radio signal from 3I/Atlas.

Micro aerial vehicles are becoming increasingly important in search and rescue operations due to their agility, speed, and ability to access confined spaces o r hazardous areas. However, designing lightweight aerial systems presents significant structural, aerodynamic, and computational challenges. This work addresses two key limitations in many low - cost aerial systems under two kilograms: their lack of structural durability during flight through rough terrains and inability to replan paths dynamically when new victims or obstacles are detected. We present a fully customised drone built from scratch using only commonly available components and materials, emphasising modularity, low cost, and ease of assembly. The structural frame is reinforced with lightweight yet durable materials to withstand impact, while the onboard control system is powered entirely by free, open - source software solutions. The proposed system demonstrates real - time perception and adaptive navigation capabilities without relying on expensive hardware accelerators by offering an affordable and practical solution for real - world search and rescue missions.

It is assumed that sparse autoencoders (SAEs) decompose polysemantic activations into interpretable linear directions, as long as the activations are composed of sparse linear combinations of underlying features. However, we find that if an SAE is more narrow than the number of underlying "true features" on which it is trained, and there is correlation between features, the SAE will merge components of correlated features together, thus destroying monosemanticity. In LLM SAEs, these two conditions are almost certainly true. This phenomenon, which we call feature hedging, is caused by SAE reconstruction loss, and is more severe the narrower the SAE. In this work, we introduce the problem of feature hedging and study it both theoretically in toy models and empirically in SAEs trained on LLMs. We suspect that feature hedging may be one of the core reasons that SAEs consistently underperform supervised baselines. Finally, we use our understanding of feature hedging to propose an improved variant of matryoshka SAEs. Importantly, our work shows that SAE width is not a neutral hyperparameter: narrower SAEs suffer more from hedging than wider SAEs. As large language models (LLMs) are deployed in real-world applications, it is increasingly important to understand their internal workings. SAEs have the advantage of operating completely unsupervised, and can easily be scaled to millions of neurons in its hidden layer (hereafter called "latents" While SAEs showed promising results, recent work has cast doubt on the performance of SAEs relative to baseline techniques. Wu et al. (2025) show that SAEs underperform on both concept steering and detection relative to baselines, and Kantamneni et al. (2025) show that SAEs underperform simple linear probes on both in-domain and out-of-domain detection, even when the probes have very few training samples. The question, then, is why do SAEs underperform relative to other techniques? And if we can identify the problems holding back SAEs, can we then fix those problems?

Sparse autoencoders (SAEs) are a popular technique for interpreting language model activations, and there is extensive recent work on improving SAE effectiveness. However, most prior work evaluates progress using unsupervised proxy metrics with unclear practical relevance. We introduce SAEBench, a comprehensive evaluation suite that measures SAE performance across eight diverse metrics, spanning interpretability, feature disentanglement and practical applications like unlearning. To enable systematic comparison, we open-source a suite of over 200 SAEs across eight recently proposed SAE architectures and training algorithms. Our evaluation reveals that gains on proxy metrics do not reliably translate to better practical performance. For instance, while Matryoshka SAEs slightly underperform on existing proxy metrics, they substantially outperform other architectures on feature disentanglement metrics; moreover, this advantage grows with SAE scale. By providing a standardized framework for measuring progress in SAE development, SAEBench enables researchers to study scaling trends and make nuanced comparisons between different SAE architectures and training methodologies. Our interactive interface enables researchers to flexibly visualize relationships between metrics across hundreds of open-source SAEs at: www.neuronpedia.org/sae-bench

Recently, the wearable and non-invasive blood glucose estimation approach has been proposed. However, due to the unreliability of the acquisition device, the presence of the noise and the variations of the acquisition environments, the obtained features and the reference blood glucose values are highly unreliable. To address this issue, this paper proposes a polynomial fitting approach to smooth the obtained features or the reference blood glucose values. First, the blood glucose values are estimated based on the individual optimization approaches. Second, the absolute difference values between the estimated blood glucose values and the actual blood glucose values based on each optimization approach are computed. Third, these absolute difference values for each optimization approach are sorted in the ascending order. Fourth, for each sorted blood glucose value, the optimization method corresponding to the minimum absolute difference value is selected. Fifth, the accumulate probability of each selected optimization method is computed. If the accumulate probability of any selected optimization method at a point is greater than a threshold value, then the accumulate probabilities of these three selected optimization methods at that point are reset to zero. A range of the sorted blood glucose values are defined as that with the corresponding boundaries points being the previous reset point and this reset point. Hence, after performing the above procedures for all the sorted reference blood glucose values in the validation set, the regions of the sorted reference blood glucose values and the corresponding optimization methods in these regions are determined. The computer numerical simulation results show that our proposed method yields the mean absolute relative deviation (MARD) at 0.0930 and the percentage of the test data falling in the zone A of the Clarke error grid at 94.1176%.

Sparse autoencoders (SAEs) extract human-interpretable features from deep neural networks by transforming their activations into a sparse, higher dimensional latent space, and then reconstructing the activations from these latents. Transcoders are similar to SAEs, but they are trained to reconstruct the output of a component of a deep network given its input. In this work, we compare the features found by transcoders and SAEs trained on the same model and data, finding that transcoder features are significantly more interpretable. We also propose skip transcoders, which add an affine skip connection to the transcoder architecture, and show that these achieve lower reconstruction loss with no effect on interpretability.

Phonon-assisted optical absorption in semiconductors is crucial for understanding and optimizing optoelectronic devices, yet its accurate simulation remains a significant challenge in computational materials science. We present an efficient approach that combines deep learning tight-binding (TB) and potential models to efficiently calculate the phonon-assisted optical absorption in semiconductors with $ab$ $initio$ accuracy. Our strategy enables efficient sampling of atomic configurations through molecular dynamics and rapid computation of electronic structure and optical properties from the TB models. We demonstrate its efficacy by calculating the temperature-dependent optical absorption spectra and band gap renormalization of Si and GaAs due to electron-phonon coupling over a temperature range of 100-400 K. Our results show excellent agreement with experimental data, capturing both indirect and direct absorption processes, including subtle features like the Urbach tail. This approach offers a powerful tool for studying complex materials with high accuracy and efficiency, paving the way for high-throughput screening of optoelectronic materials.

This paper presents a novel method for mapping spectral features of the Moon using machine learning-based clustering of hyperspectral data from the Moon Mineral Mapper (M3) imaging spectrometer. The method uses a convolutional variational autoencoder to reduce the dimensionality of the spectral data and extract features of the spectra. Then, a k-means algorithm is applied to cluster the latent variables into five distinct groups, corresponding to dominant spectral features, which are related to the mineral composition of the Moon's surface. The resulting global spectral cluster map shows the distribution of the five clusters on the Moon, which consist of a mixture of, among others, plagioclase, pyroxene, olivine, and Fe-bearing minerals across the Moon's surface. The clusters are compared to the mineral maps from the Kaguya mission, which showed that the locations of the clusters overlap with the locations of high wt% of minerals such as plagioclase, clinopyroxene, and olivine. The paper demonstrates the usefulness of unbiased unsupervised learning for lunar mineral exploration and provides a comprehensive analysis of lunar mineralogy.

X-Ray specs and invisibility cloaks are the stuff of sci-fi and fantasy, but sometimes science is just stranger than fiction. A food dye that helps give certain sodas and snacks their hallmark orange hue renders mouse skin almost completely see-through in a reversible, potentially non-toxic research method that could transform medical and scientific imaging. Because of a counterintuitive fundamental physics principle, Tartrazine, also known as Yellow 5, can temporarily turn biological tissue transparent to the naked eye, as described in a study published September 5 in the journal Science. So far, the scientists behind the new discovery have used the method to see the organs in a mouse's intact abdomen, glimpse the pulsing vessels surrounding a rodent skull, and to get an exceptionally clear view of muscle tissue through a microscope. With further safety and efficacy research, the method may spur new scientific findings, boost microscopy advances, and improve medical diagnostic strategies and treatments.

This research introduces an innovative application of physics-informed neural networks (PINNs) to tackle the intricate challenges of radiative transfer (RT) modeling in exoplanetary atmospheres, with a special focus on efficiently handling scattering phenomena. Traditional RT models often simplify scattering as absorption, leading to inaccuracies. Our approach utilizes PINNs, noted for their ability to incorporate the governing differential equations of RT directly into their loss function, thus offering a more precise yet potentially fast modeling technique. The core of our method involves the development of a parameterized PINN tailored for a modified RT equation, enhancing its adaptability to various atmospheric scenarios. We focus on RT in transiting exoplanet atmospheres using a simplified 1D isothermal model with pressure-dependent coefficients for absorption and Rayleigh scattering. In scenarios of pure absorption, the PINN demonstrates its effectiveness in predicting transmission spectra for diverse absorption profiles. For Rayleigh scattering, the network successfully computes the RT equation, addressing both direct and diffuse stellar light components. While our preliminary results with simplified models are promising, indicating the potential of PINNs in improving RT calculations, we acknowledge the errors stemming from our approximations as well as the challenges in applying this technique to more complex atmospheric conditions. Specifically, extending our approach to atmospheres with intricate temperature-pressure profiles and varying scattering properties, such as those introduced by clouds and hazes, remains a significant area for future development.