Search

Scientific discovery relies on scientists generating novel hypotheses that undergo rigorous experimental validation. To augment this process, we introduce an AI co-scientist, a multi-agent system built on Gemini 2.0. The AI co-scientist is intended to help uncover new, original knowledge and to formulate demonstrably novel research hypotheses and proposals, building upon prior evidence and aligned to scientist-provided research objectives and guidance. The system's design incorporates a generate, debate, and evolve approach to hypothesis generation, inspired by the scientific method and accelerated by scaling test-time compute. Key contributions include: (1) a multi-agent architecture with an asynchronous task execution framework for flexible compute scaling; (2) a tournament evolution process for self-improving hypotheses generation. Automated evaluations show continued benefits of test-time compute, improving hypothesis quality. While general purpose, we focus development and validation in three biomedical areas: drug repurposing, novel target discovery, and explaining mechanisms of bacterial evolution and anti-microbial resistance. For drug repurposing, the system proposes candidates with promising validation findings, including candidates for acute myeloid leukemia that show tumor inhibition in vitro at clinically applicable concentrations. For novel target discovery, the AI co-scientist proposed new epigenetic targets for liver fibrosis, validated by anti-fibrotic activity and liver cell regeneration in human hepatic organoids. Finally, the AI co-scientist recapitulated unpublished experimental results via a parallel in silico discovery of a novel gene transfer mechanism in bacterial evolution. These results, detailed in separate, co-timed reports, demonstrate the potential to augment biomedical and scientific discovery and usher an era of AI empowered scientists., Comment: 81 pages in total (main 38 pages, appendix 43 pages), 13 main figures, 40 appendix figures, 1 main table, 2 appendix tables, 143 main references, 7 appendix references

In this paper, we propose a two-stage weighted projection method (TS-WPM) for time-difference-of-arrival (TDOA)-based localization, providing provable improvements in positioning accuracy, particularly under high geometric dilution of precision (GDOP) and low signal-to-noise ratio (SNR) conditions. TS-WPM employs a two-stage iterative refinement approach that dynamically updates both range and position estimates, effectively mitigating residual errors while maintaining computational efficiency. Additionally, we extend TS-WPM to support cooperative localization by leveraging two-way time-of-arrival (TW-TOA) measurements, which enhances positioning accuracy in scenarios with limited anchor availability. To analyze TS-WPM, we derive its error covariance matrix and mean squared error (MSE), establishing conditions for its optimality and robustness. To facilitate rigorous evaluation, we develop a 3rd Generation Partnership Project (3GPP)-compliant analytical framework, incorporating 5G New Radio (NR) physical layer aspects as well as large-scale and small-scale fading. As part of this, we derive a generalized Cram{\'e}r-Rao lower bound (CRLB) for multipath propagation and introduce a novel non-line-of-sight (NLOS) bias model that accounts for propagation conditions and SNR variations. Our evaluations demonstrate that TS-WPM achieves near-CRLB performance and consistently outperforms state-of-the-art weighted nonlinear least squares (WNLS) in high GDOP and low SNR scenarios. Moreover, cooperative localization with TS-WPM significantly enhances accuracy, especially when an insufficient number of anchors (such as 2) are visible. Finally, we analyze the computational complexity of TS-WPM, showing its balanced trade-off between accuracy and efficiency, making it a scalable solution for real-time localization in next-generation networks., Comment: 13 pages, 7 figures

This paper introduces a novel causal framework for multi-stage decision-making in natural language action spaces where outcomes are only observed after a sequence of actions. While recent approaches like Proximal Policy Optimization (PPO) can handle such delayed-reward settings in high-dimensional action spaces, they typically require multiple models (policy, value, and reward) and substantial training data. Our approach employs Q-learning to estimate Dynamic Treatment Regimes (DTR) through a single model, enabling data-efficient policy learning via gradient ascent on language embeddings. A key technical contribution of our approach is a decoding strategy that translates optimized embeddings back into coherent natural language. We evaluate our approach on mental health intervention, hate speech countering, and sentiment transfer tasks, demonstrating significant improvements over competitive baselines across multiple metrics. Notably, our method achieves superior transfer strength while maintaining content preservation and fluency, as validated through human evaluation. Our work provides a practical foundation for learning optimal policies in complex language tasks where training data is limited.

GLEAM-X J1627-52 was discovered as a periodic (~18 min) radio signal over a duration of three months in 2018. It is an enigmatic example of a growing population of 'long-period radio transients' consistent with Galactic origins. Their nature is uncertain, and leading models invoke magnetic neutron stars or white dwarfs, potentially in close binary systems, to power them. GLEAM-X J1627-52 resides in the Galactic plane with a comparatively coarse localisation (~2 arcsecond). Here we study the localisation region to search for spectrophotometric signatures of a counterpart using time-domain searches in optical and near-infrared imaging, and MUSE integral field spectroscopy. No sources in the localisation display clear white dwarf spectral signatures, although at the expected distance we can only provide modest limits on their presence directly. We rule out the presence of hot sub-dwarfs in the vicinity. We found no candidate within our search for variability or periodic behaviour in the light curves. Radial velocity curves additionally show only weak evidence of variation, requiring any realistic underlying system to have very low orbital inclination (i < 5 deg). Two Balmer emission line sources are reminiscent of white dwarf pulsar systems, but their characteristics fall within expected M-dwarf chromospheric activity with no signs of being in a close binary. Currently the white dwarf pulsar scenario is not supported, although longer baseline data and data contemporaneous with a radio active epoch are required before stronger statements. Isolated magnetars, or compact binaries remain viable. Our limits highlight the difficulty of these searches in dense environments at the limits of ground-based data., Comment: Accepted to MNRAS, 18 pages, 12 figures

We introduce and study a fractional variant of the linear birth-death process, namely, the generalized fractional linear birth-death process (GFLBDP) which is defined by taking the regularized Hilfer-Prabhakar derivative in the system of differential equations that governs the state probabilities of linear birth-death process. For a particular choice of parameters, the GFLBDP reduces to the fractional linear birth-death process that involves the Caputo derivative. Its time-changed representation is obtained and utilized to derive the explicit expressions of its state probabilities. The explicit expressions for its mean and variance are derived. In a particular case, it is observed that the limiting distribution of the time changing process coincides to that of an inverse stable subordinator. A relation between the extinction probability of GFLBDP and the density of inter arrival times of a generalized fractional Poisson process is obtained. Later, we study some integrals of the GFLBDP and discuss the asymptotic distributional characteristics for a particular integral process. Also, an application of the path integral at random time to a genetic population with an upper bound is discussed.

Interest in the use of the low earth orbit (LEO) in space - from $160 \text{ km}$ to $2000 \text{ km}$ - has skyrocketed; this is evident by the fact that National Aeronautics and Space Administration (NASA) has partnered with various commercial platforms like Axiom Space, Blue Origin, SpaceX, Sierra Space, Starlab Space, ThinkOrbital, and Vast Space to deploy satellites. %and platforms like Northrop Grumman and Boeing to transport cargo and crew. The most apparent advantage of satellites in LEO over satellites in Geostationary (GEO) and medium earth orbit (MEO) is their closeness to the earth; hence, signals from LEOs encounter lower propagation losses and reduced propagation delay, opening up the possibility of using these LEO satellites for localization. This article reviews the existing signal processing algorithms for localization using LEO satellites, introduces the basics of estimation theory, connects estimation theory to model identifiability with Fisher Information Matrix (FIM), and with the FIM, provides conditions that allow for $9$D localization of a terrestrial receiver using signals from multiple LEOs (unsynchronized in time and frequency) across multiple time slots and multiple receive antennas. We also compare the structure of the information available in LEO satellites with the structure of the information available in the Global Positioning System (GPS).

There has been substantial work on developing variants of the multiple signal classification (MUSIC) algorithms that take advantage of the information present in the near-field propagation regime. However, it is not always easy to determine the correct propagation regime, which opens the possibility of incorrectly applying simpler algorithms (meant for far-field) in the near-field regime. Inspired by this, we use simulation results to investigate the performance drop when there is a mismatch between the signal model in the MUSIC algorithm and the propagation regime. For direction of arrival (DOA) estimation, we consider the cases when the receiver is in the near-field region but uses i) the near-field model, ii) the approximate near-field model (ANM) model, and iii) the far-field model to design the beamforming matrix in the MUSIC algorithm. We also consider the case when the receiver is in the far-field region, and we use the correct far-field model to design the beamforming matrix in the MUSIC algorithm. One contribution is that in the near-field, we have quantified the loss in performance when the ANM and the far-field model are used to create the beamforming matrix for the MUSIC algorithm, causing a reduction in estimation accuracy compared to the case when the correct near-field model is used to design the beamforming matrix. Another result is that in the near-field, when we incorrectly assume that the receiver is in the far-field and subsequently use the far-field beamforming matrix, we underestimate the DOA estimation error. Finally, we show that the MUSIC algorithm can provide very accurate range estimates for distances less than the Fraunhofer distance. This estimate gradually becomes inaccurate as the distances exceed the Fraunhofer distance.

Constructing a no-fly zone (NFZ) is a straightforward and effective way to facilitate the coexistence of unmanned aerial vehicles (drones) and existing systems (typically satellite systems). However, there has been little work on understanding the optimal design of such NFZs. In the absence of this design, one invariably ends up overestimating this region, hence significantly limiting the allowed airspace for the drones. To optimize the volume of the NFZ, we formulate this task as a variational problem and utilize the calculus of variations to rigorously obtain the NFZ as a function of the antenna pattern of victim receivers and the spatial distribution of drones. This approach parallels the matched filter design in the sense that the NFZ extends in directions where the antenna gain and/or the density of drones is high. Numerical simulations demonstrate the effectiveness of our optimal design compared to the known baselines in reducing the volume of the NFZ without compromising the protective performance., Comment: 5 pages, 3 figures, correspondence articles

In this paper, we introduce drifted versions of the generalized counting process (GCP) with a deterministic drift and a random drift. The composition of stable subordinator with an independent inverse stable subordinator is taken as the random drift. We derive the probability law and its governing fractional differential equations for these drifted versions. Also, we study the GCP time-changed with different Brownian clocks, for example, the Brownian first passage-time with or without drift, elastic Brownian motion, Brownian sojourn time on positive half-line and the Bessel times. For these time-changed processes, we obtain the governing system of differential equation of their state probabilities, probability generating function, etc. Further, we consider a time-changed GCP where the time-change is done by subordinators linked to incomplete gamma function. Later, we study the fractional integral of GCP and its time-changed variant.

Many modern wireless devices with accurate positioning needs also have access to vision sensors, such as a camera, radar, and Light Detection and Ranging (LiDAR). In scenarios where wireless-based positioning is either inaccurate or unavailable, using information from vision sensors becomes highly desirable for determining the precise location of the wireless device. Specifically, vision data can be used to estimate distances between the target (where the sensors are mounted) and nearby landmarks. However, a significant challenge in positioning using these measurements is the inability to uniquely identify which specific landmark is visible in the data. For instance, when the target is located close to a lamppost, it becomes challenging to precisely identify the specific lamppost (among several in the region) that is near the target. This work proposes a new framework for target localization using range measurements to multiple proximate landmarks. The geometric constraints introduced by these measurements are utilized to narrow down candidate landmark combinations corresponding to the range measurements and, consequently, the target's location on a map. By modeling landmarks as a marked Poisson point process (PPP), we show that three noise-free range measurements are sufficient to uniquely determine the correct combination of landmarks in a two-dimensional plane. For noisy measurements, we provide a mathematical characterization of the probability of correctly identifying the observed landmark combination based on a novel joint distribution of key random variables. Our results demonstrate that the landmark combination can be identified using ranges, even when individual landmarks are visually indistinguishable., Comment: 14 pages

We report follow-up observations of three poorly studied AM CVn-type binaries: CRTS CSS150211 J091017-200813, NSV1440, and SDSSJ183131.63+420220.2. Analysing time-series photometry obtained with a range of ground-based facilities as well as with TESS, we determine the superhump period of CRTSJ0910-2008 as P_sh=29.700+-0.004min and the orbital period of NSV1440 as Porb=36.56+-0.03min. We also confirm a photometric period of P=23.026+-0.097min in SDSSJ1831+4202, which is most likely the superhump period. We also report the first optical spectroscopy of CRTSJ0910-2008 and NSV1440 which unambiguously confirms both as AM CVn systems. We briefly discuss the distribution in the Hertzsprung-Russell diagram of the currently known sample of 63 AM CVn stars with known periods and Gaia data., Comment: Accepted for publication in MNRAS

White dwarfs are often found in close binaries with stellar or even substellar companions. It is generally thought that these compact binaries form via common envelope evolution, triggered by the progenitor of the white dwarf expanding after it evolved off the main-sequence and engulfing its companion. To date, a handful of white dwarfs in compact binaries with substellar companions have been found, typically with masses greater than around 50 M$_\mathrm{Jup}$. Here we report the discovery of two eclipsing white dwarf plus brown dwarf binaries containing very low mass brown dwarfs. ZTF J1828+2308 consists of a hot ($15900\pm75$ K) $0.610\pm0.004$ M$_{\odot}$ white dwarf in a 2.7 hour binary with a $0.0186\pm0.0008$ M$_{\odot}$ ($19.5\pm0.8$ M$_\mathrm{Jup}$) brown dwarf. ZTF J1230$-$2655 contains a cool ($10000\pm110$ K) $0.65\pm0.02$ M$_{\odot}$ white dwarf in a 5.7 hour binary with a companion that has a mass of less than 0.0211 M$_{\odot}$ (22.1 M$_\mathrm{Jup}$). While the brown dwarf in ZTF J1828+2308 has a radius consistent with its mass and age, ZTF J1230$-$2655 contains a roughly 20 per cent overinflated brown dwarf for its age. We are only able to reconstruct the common envelope phase for either system if it occurred after the first thermal pulse, when the white dwarf progenitor had already lost a significant fraction of its original mass. This is true even for very high common envelope ejection efficiencies ($\alpha_\mathrm{CE}\sim 1$), unless both systems have extremely low metallicities. It may be that the lowest mass companions can only survive a common envelope phase if it occurs at this very late stage., Comment: 15 pages, 13 figures. Accepted for publication in MNRAS

We prove a monoidal equivalence between spectral and automorphic realizations of the universal affine Hecke category, thereby proving the tamely ramified local Betti geometric Langlands correspondence, as conjectured by Ben-Zvi--Nadler [BZN07, BZN18]. Specializing to the case of unipotent monodromy, this provides another argument for a fundamental theorem of Bezrukavnikov [B16].

We identify equivariant quasicoherent sheaves on the Grothendieck alteration of a reductive group $\mathsf{G}$ with universal monodromic Iwahori--Whittaker sheaves on the enhanced affine flag variety of the Langlands dual group $G$. This extends a similar result for equivariant quasicoherent sheaves on the Springer resolution due to Arkhipov--Bezrukavnikov. We further give a monoidal identification between adjoint equivariant coherent sheaves on the group $\mathsf{G}$ itself and bi-Iwahori--Whittaker sheaves on the loop group of $G$. These results are used in the sequel to this paper to prove the tame local Betti geometric Langlands conjecture of Ben-Zvi--Nadler. Our proof of fully faithfulness provides an alternative to the argument of Arkhipov--Bezrukavnikov. Namely, while they localize in unipotent directions, we localize in semi-simple directions, thereby reducing fully faithfulness to an order of vanishing calculation in semi-simple rank one.

In this paper, we introduce the elephant random walk (ERW) with memory consisting of randomly selected steps from its history. It is a time-changed variant of the standard elephant random walk with memory consisting of its full history. At each time point, the time changing component is the composition of two uniformly distributed independent random variables with support over all the past steps. Several conditional distributional properties including the conditional mean increments and conditional displacement of ERW with random memory are obtained. Using these conditional results, we derive the recursive and explicit expressions for the mean increments and mean displacement of the walk.

Dwarf novae are a crucial astrophysical laboratory for probing the nature of accretion, binary mass transfer, and binary evolution -- yet their diverse observational characteristics continue to challenge our theoretical understanding. We here present the discovery of, and subsequent observing campaign on GOTO065054+593624 (hereafter GOTO0650), a dwarf nova of the WZ Sge type, discovered in real-time by citizen scientists via the Kilonova Seekers citizen science project. An extensive dataset charts the photometric and spectroscopic evolution of this object, covering the first two months of its 2024 superoutburst. GOTO0650 shows a complete absence of visible emission lines during the high state, strong H and barely-detected He~II emission, and high-amplitude echo outbursts with a rapidly decreasing timescale that together do not neatly fit in with our current view of cataclysmic variables. The comprehensive dataset presented here not only underscores the uniqueness of this dwarf nova and marks it as a candidate period bouncer, but also highlights the important contribution that citizen scientists can make to the study of Galactic transients., Comment: 14 pages, 14 figures. Submitted to A&A

Van der Waals heterostructures have promised the realisation of artificial materials with multiple physical phenomena such as giant optical nonlinearities, spin-to-charge interconversion in spintronics and topological carrier protection, in a single layered device through an infinitely diverse set of quantum materials. However, most efforts have only focused on exfoliated material that inherently limits both the dimensions of the materials and the scalability for applications. Here, we show the epitaxial growth of large area heterostructures of topological insulators (Bi2Se3), transition metal dichalcogenides (TMDs, WSe2) and ferromagnets (Co), resulting in the combination of functionalities including tuneable optical nonlinearities, spin-to-charge conversion and magnetic proximity effects. This is demonstrated through coherent phase resolved terahertz currents, bringing novel functionalities beyond those achievable in simple homostructures. In particular, we show the role of different TMD polymorphs, with the simple change of one atomic monolayer of the artificial material stack entirely changing its optical, electrical and magnetic properties. This epitaxial integration of diverse two-dimensional materials offers foundational steps towards diverse perspectives in quantum material engineering, where the material polymorph can be controlled at technological relevant scales for coupling applications in, for example, van der Waals nonlinear optics, optoelectronics, spintronics, multiferroics and coherent current control.

It is generally thought that AGN optical variability is produced, at least in part, by reprocessing of central X-rays by a surrounding accretion disc, resulting in wavelength-dependent lags between bands. Any good model of AGN optical variability should explain not only these lags, but also the overall pattern of variability as quantified by the power spectral density (PSD). Here we present $\sim$daily g'-band monitoring of the low-mass AGN NGC\,4395 over 3 years. Together with previous TESS and GTC/HiPERCAM observations we produce an optical PSD covering an unprecedented frequency range of $\sim7$ decades allowing excellent determination of PSD parameters. The PSD is well fitted by a bending power law with low-frequency slope $\alpha_{L} = 1.0 \pm 0.2$, high-frequency slope $2.1^{+0.2}_{-0.4}$ and bend timescale $3.0^{+6.6}_{-1.7}\,$\,d. This timescale is close to that derived previously from a damped random walk (DRW) model fitted to just the TESS observations, although $\alpha_{L}$ is too steep to be consistent with a DRW. We compare the observed PSD with one made from light curves synthesized assuming reprocessing of X-rays, as observed by \xmm and Swift, in a disc defined by the observed lags. The simulated PSD is also well described by a bending power law but with a bend two decades higher in frequency. We conclude that the large-amplitude optical variations seen on long-timescales are not due to disc reprocessing but require a second source of variability whose origin is unknown but could be propagating disc accretion rate variations.

The diversity of 2D materials and their van der Waals (vdW) stacking presents a fertile ground for engineering novel multifunctional materials and quantum states of matter. This permits unique opportunities to tailor the electronic properties of vdW heterostructures by the insertion of only a single 2D material layer. However, such vdW materials engineering at the atomic scale has yet to be investigated for spin-charge interconversion phenomena. Here, we report on the control of these effects at the monolayer level, where drastic increase in intensity and change in sign of THz spintronic emission are demonstrated by inserting a single layer of MoSe$_2$ between PtSe$_2$ and graphene in a fully epitaxial, large area stacked structure. By using a combination of spin and angle resolved photoemission and density functional theory to reveal the electronic and spin structures, we illustrate two different mechanisms relying on charge transfer and electronic hybridization for the formation of Rashba states, which are responsible for spin-charge conversion and hence the THz spintronic emission. These findings open new pathways to design, at the atomic scale, efficient THz spintronic emitters made of 2D materials and other spintronic devices based on spin-charge interconversion phenomena., Comment: 16 pages, 4 figures

Spintronic Terahertz emitters, based on optically triggered spin-to-charge interconversion processes, have recently emerged as novel route towards compact and efficient THz sources. Yet, the next challenge for further technologically-relevant devices remains to modulate the emission, with low-energy consumption operation. To this aim, ferroelectric materials coupled to active spin-orbit layers such as two-dimensional transition metal dichalcogenides are suitable candidates. In this work, we present the realization of a large area heterostructure of CoFeB/PtSe2/MoSe2 on a bi-domain LiNbO3 substrate. Using THz time-domain spectroscopy, we show that the ferroelectric polarization direction induces a sizeable modulation of the THz emission. We rationalise these experimental results by using band structure and spin accumulation calculations that are consistent with an interfacial spin-to-charge conversion mediated by inverse Rashba-Edelstein effect at the MoSe2/PtSe2 interface and being tuned by ferroelectricity in the adjacent LiNbO3 surface. This work points out the relevance of field effect spin-orbit architectures for novel THz technologies., Comment: 13 pages, 4 figures, 35 references

Traditional recommender systems based on utility maximization and revealed preferences often fail to capture users' dual-self nature, where consumption choices are driven by both long-term benefits (enrichment) and desire for instant gratification (temptation). Consequently, these systems may generate recommendations that fail to provide long-lasting satisfaction to users. To address this issue, we propose a novel user model that accounts for this dual-self behavior and develop an optimal recommendation strategy to maximize enrichment from consumption. We highlight the limitations of historical consumption data in implementing this strategy and present an estimation framework that makes minimal assumptions and leverages explicit user feedback and implicit choice data to overcome these constraints. We evaluate our approach through both synthetic simulations and simulations based on real-world data from the MovieLens dataset. Results demonstrate that our proposed recommender can deliver superior enrichment compared to several competitive baseline algorithms that assume a single utility type and rely solely on revealed preferences. Our work emphasizes the critical importance of optimizing for enrichment in recommender systems, particularly in temptation-laden consumption contexts. Our findings have significant implications for content platforms, user experience design, and the development of responsible AI systems, paving the way for more nuanced and user-centric recommendation approaches.

Let $X$ be a smooth geometrically connected projective curve of genus at least 2 over a field of characteristic zero. We compute the essential dimension of the moduli stack of symplectic bundles over $X$. Unlike the case of vector bundles, we are able to precisely compute the essential dimension as the generic gerbe of the moduli stack has period 2 over it's moduli space.

Type Ia supernovae, critical for studying cosmic expansion, arise from thermonuclear explosions of white dwarfs, but their precise progenitor pathways remain unclear. Growing evidence supports the ``double-degenerate'' scenario, where two white dwarfs interact. The absence of other companion types capable of explaining the observed Ia rate, along with observations of hyper-velocity white dwarfs interpreted as surviving companions of such systems provide compelling evidence in favor of this scenario. Upcoming millihertz gravitational wave observatories like the Laser Interferometer Space Antenna (LISA) are expected to detect thousands of double-degenerate systems, though the most compact known candidate Ia progenitors produce only marginally detectable gravitational wave signals. Here, we report observations of ATLAS J1138-5139, a binary white dwarf system with an orbital period of 28 minutes. Our analysis reveals a 1 solar mass carbon-oxygen white dwarf accreting from a helium-core white dwarf. Given its mass, the accreting carbon-oxygen white dwarf is poised to trigger a typical-luminosity Type Ia supernova within a few million years, or to evolve into a stably mass-transferring AM CVn system. ATLAS J1138-5139 provides a rare opportunity to calibrate binary evolution models by directly comparing observed orbital parameters and mass transfer rates closer to merger than any previously identified candidate Type Ia progenitor. Its compact orbit ensures detectability by LISA, demonstrating the potential of millihertz gravitational wave observatories to reveal a population of Type Ia progenitors on a Galactic scale, paving the way for multi-messenger studies offering insights into the origins of these cosmologically significant explosions., Comment: 40 pages, 7 figures, 2 tables

The origin(s) of Fast Radio Bursts (FRBs), mysterious radio bursts coming from extragalactic distances, remains unknown. Multi-wavelength observations are arguably the only way to answer this question unambiguously. We attempt to detect hard X-ray/soft gamma-ray counterparts to one of the most active FRB sources, FRB20121102, as well as improve understanding of burst properties in radio through a long-term monitoring campaign using the Nan\c{c}ay Radio Telescope (NRT). Multi-wavelength campaigns involving the International Gamma-ray Astrophysics Laboratory (INTEGRAL) satellite, the Nan\c{c}ay Radio Observatory, the optical telescopes at the Observatoire de Haute Provence as well as Arecibo were conducted between 2017 and 2019. In 2017, the telescopes were scheduled to observe simultaneously between Sept 24-29. We specifically used the Fast Response Enhanced CCDs for the optical observations to ensure a high time resolution. In 2019, we changed the strategy to instead conduct ToO observations on INTEGRAL and other available facilities upon positive detection triggers from the NRT. In the 2017 campaign, FRB20121102 was not in its burst activity window. We obtain a 5-sigma optical flux limit of 12 mJy ms using the GASP and a 3-sigma limit from OHP T120cm R-band image of R=22.2 mag of any potential persistent emission not associated to radio bursts. In the 2019 campaign, we have simultaneous INTEGRAL data with 11 radio bursts from the NRT and Arecibo. We obtain a 5-sigma upper limit of 2.7e-7 erg/cm2 in the 25-400 keV energy range for contemporary radio and high energy bursts, and a 5-sigma upper limit of 3.8e-11 erg/cm2 for permanent emission in the 25-100 keV energy range. In addition, we report on the regular observations from NRT between 2016-2020, which accounts for 119 additional radio bursts from FRB20121102. We present an updated fit of the periodic active window of 154+/-2 days., Comment: Submitted to A&A

We report the discovery of three ultracompact binary white dwarf systems hosting accretion disks, with orbital periods of 7.95, 8.68, and 13.15 minutes. This significantly augments the population of mass-transferring binaries at the shortest periods, and provides the first evidence that accretors in ultracompacts can be dense enough to host accretion disks even below 10 minutes (where previously only direct-impact accretors were known). In the two shortest-period systems, we measured changes in the orbital periods driven by the combined effect of gravitational wave emission and mass transfer; we find $\dot{P}$ is negative in one case, and positive in the other. This is only the second system measured with a positive $\dot{P}$, and it the most compact binary known that has survived a period minimum. Using these systems as examples, we show how the measurement of $\dot{P}$ is a powerful tool in constraining the physical properties of binaries, e.g. the mass and mass-radius relation of the donor stars. We find that the chirp masses of ultracompact binaries at these periods seem to cluster around $\mathcal{M}_c \sim 0.3 M_\odot$, perhaps suggesting a common origin for these systems or a selection bias in electromagnetic discoveries. Our new systems are among the highest-amplitude known gravitational wave sources in the millihertz regime, providing exquisite opportunity for multi-messenger study with future space-based observatories such as \textit{LISA} and TianQin; we discuss how such systems provide fascinating laboratories to study the unique regime where the accretion process is mediated by gravitational waves., Comment: Accepted for publication in ApJ

In this paper, we study the composition of two independent GCPs which we call the iterated generalized counting process (IGCP). Its distributional properties such as the transition probabilities, probability generating function, state probabilities and its corresponding L\'evy measure are obtained. We study some integrals of the IGCP. Also, we study some of its extensions, for example, the compound IGCP, the multivariate IGCP and the $q$-iterated GCP. It is shown that the IGCP and the compound IGCP are identically distributed to a compound GCP which leads to their martingale characterizations. Later, a time-changed version of the IGCP is considered where the time is changed by an inverse stable subordinator. Using its covariance structure, we establish that the time-changed IGCP exhibits long-range dependence property. Moreover, we show that its increment process exhibits short-range dependence property. Also, it is shown that its one-dimensional distributions are not infinitely divisible. Initially, some of its potential real life applications are discussed.

Transformers have had tremendous impact for several sequence related tasks, largely due to their ability to retrieve from any part of the sequence via softmax based dot-product attention. This mechanism plays a crucial role in Transformer's performance. We analyze the gradients backpropagated through the softmax operation in the attention mechanism and observe that these gradients can often be small. This poor gradient signal backpropagation can lead to inefficient learning of parameters preceeding the attention operations. To this end, we introduce a new attention mechanism called LASER, which we analytically show to admit a larger gradient signal. We show that LASER Attention can be implemented by making small modifications to existing attention implementations. We conduct experiments on autoregressive large language models (LLMs) with upto 2.2 billion parameters where we show upto 3.38% and an average of ~1% improvement over standard attention on downstream evaluations. Using LASER gives the following relative improvements in generalization performance across a variety of tasks (vision, text and speech): 4.67% accuracy in Vision Transformer (ViT) on Imagenet, 2.25% error rate in Conformer on the Librispeech speech-to-text and 0.93% fraction of incorrect predictions in BERT with 2.2 billion parameters., Comment: 15 pages, under review in ICLR 2025

Large language models (LLMs) have shown remarkable progress in encoding clinical knowledge and responding to complex medical queries with appropriate clinical reasoning. However, their applicability in subspecialist or complex medical settings remains underexplored. In this work, we probe the performance of AMIE, a research conversational diagnostic AI system, in the subspecialist domain of breast oncology care without specific fine-tuning to this challenging domain. To perform this evaluation, we curated a set of 50 synthetic breast cancer vignettes representing a range of treatment-naive and treatment-refractory cases and mirroring the key information available to a multidisciplinary tumor board for decision-making (openly released with this work). We developed a detailed clinical rubric for evaluating management plans, including axes such as the quality of case summarization, safety of the proposed care plan, and recommendations for chemotherapy, radiotherapy, surgery and hormonal therapy. To improve performance, we enhanced AMIE with the inference-time ability to perform web search retrieval to gather relevant and up-to-date clinical knowledge and refine its responses with a multi-stage self-critique pipeline. We compare response quality of AMIE with internal medicine trainees, oncology fellows, and general oncology attendings under both automated and specialist clinician evaluations. In our evaluations, AMIE outperformed trainees and fellows demonstrating the potential of the system in this challenging and important domain. We further demonstrate through qualitative examples, how systems such as AMIE might facilitate conversational interactions to assist clinicians in their decision making. However, AMIE's performance was overall inferior to attending oncologists suggesting that further research is needed prior to consideration of prospective uses.

We present the analysis of optical data of a bright and extremely-rapidly evolving transient, AT2024wpp, whose properties are similar to the enigmatic AT2018cow (aka the Cow). AT2024wpp rose to a peak brightness of c=-21.9mag in 4.3d and remained above the half-maximum brightness for only 6.7d. The blackbody fits to the multi-band photometry show that the event remained persistently hot (T>20000K) with a rapidly receding photosphere (v~11500km/s) until the end of the photometric dataset at +16.1d post-discovery. This behaviour mimics that of AT2018cow, albeit with a several times larger photosphere. The spectra are consistent with blackbody emission throughout our spectral sequence ending at +21.9d, showing a tentative, very broad emission feature at 5500{\AA} -- implying that the optical photosphere is likely within a near-relativistic outflow. Furthermore, reports of strong X-ray and radio emission cement the nature of AT2024wpp as a likely Cow-like transient. AT2024wpp is only the second event of the class with optical polarimetry. Our BVRI observations obtained from +6.1 to +14.4d show a low polarisation of P<0.5% across all bands, similar to AT2018cow that was consistent with P~0% during the same outflow-driven phase. In the absence of evidence for a preferential viewing angle, it is unlikely that both events would have shown low polarisation in the case that their photospheres were aspherical. As such, we conclude that the near-relativistic outflows launched in these events are likely highly spherical, but polarimetric observations of further events are crucial to constrain their ejecta geometry and stratification in detail., Comment: 13 pages, 7 figures. Accepted to MNRAS

JWST, despite not being designed to observe astrophysical phenomena that vary on rapid time scales, can be an unparalleled tool for such studies. If timing systematics can be controlled, JWST will be able to open up the sub-second infrared timescale regime. Rapid time-domain studies, such as lag measurements in accreting compact objects and Solar System stellar occultations, require both precise inter-frame timing and knowing when a time series begins to an absolute accuracy significantly below 1s. In this work we present two long-duration observations of the deeply eclipsing double white dwarf system ZTF J153932.16+502738.8, which we use as a natural timing calibrator to measure the absolute timing accuracy of JWST's clock. From our two epochs, we measure an average clock accuracy of $0.12\pm0.06$s, implying that JWST can be used for sub-second time-resolution studies down to the $\sim100$ms level, a factor $\sim5$ improvement upon the pre-launch clock accuracy requirement. We also find an asymmetric eclipse profile in the F322W2 band, which we suggest has a physical origin., Comment: 16 pages, 13 figures, accepted for publication in AJ

Inverse rendering pipelines are gaining prominence in realizing photo-realistic reconstruction of real-world objects for emulating them in virtual reality scenes. Apart from material reflectances, spectral rendering and in-scene illuminants' spectral power distributions (SPDs) play important roles in producing photo-realistic images. We present a simple, low-cost technique to capture and reconstruct the SPD of uniform illuminants. Instead of requiring a costly spectrometer for such measurements, our method uses a diffractive compact disk (CD-ROM) and a machine learning approach for accurate estimation. We show our method to work well with spotlights under simulations and few real-world examples. Presented results clearly demonstrate the reliability of our approach through quantitative and qualitative evaluations, especially in spectral rendering of iridescent materials., Comment: 3 pages, 3 Figures, Submitted as a Tiny Paper at ICVGIP'24, Bangalore, India

Supervised fine-tuning (SFT) and alignment of large language models (LLMs) are key steps in providing a good user experience. However, the concept of an appropriate alignment is inherently application-dependent, and current methods often rely on heuristic choices to drive the optimization. In this work, we formulate SFT and alignment as a constrained optimization problem, where the LLM is trained on a task while being required to meet application-specific requirements, without resorting to heuristics. To solve this, we propose Lagrange Large Language Models (L3Ms), which employ logarithmic barriers to enforce the constraints. This approach allows for the customization of L3Ms across diverse applications while avoiding heuristic-driven processes. We demonstrate experimentally the versatility and efficacy of L3Ms in achieving tailored alignments for various applications.

Low-rank adaption (LoRA) is a widely used parameter-efficient finetuning method for LLM that reduces memory requirements. However, current LoRA optimizers lack transformation invariance, meaning the actual updates to the weights depends on how the two LoRA factors are scaled or rotated. This deficiency leads to inefficient learning and sub-optimal solutions in practice. This paper introduces LoRA-RITE, a novel adaptive matrix preconditioning method for LoRA optimization, which can achieve transformation invariance and remain computationally efficient. We provide theoretical analysis to demonstrate the benefit of our method and conduct experiments on various LLM tasks with different models including Gemma 2B, 7B, and mT5-XXL. The results demonstrate consistent improvements against existing optimizers. For example, replacing Adam with LoRA-RITE during LoRA fine-tuning of Gemma-2B yielded 4.6\% accuracy gain on Super-Natural Instructions and 3.5\% accuracy gain across other four LLM benchmarks (HellaSwag, ArcChallenge, GSM8K, OpenBookQA).

For a reductive group $G$, we introduce a notion of singular support for cocomplete dualizable DG-categories equipped with a strong $G$-action. This is done by considering the singular support of the sheaves of matrix coefficients arising from the action. We focus particularly on dualizable $G$-categories whose singular support lies in the nilpotent cone of $\mathfrak{g}^*$ and refer to these as nilpotent $G$-categories. For such categories, we give a characterization of the singular support in terms of the vanishing of its generalized Whittaker models. We study parabolic induction and restriction functors of nilpotent $G$-categories and show that they interact with singular support in a desired way. We prove that if an orbit is maximal in the singular support of a nilpotent $G$-category $\mathcal{C}$, the Hochschild homology of the generalized Whittaker model of $\mathcal{C}$ coincides with the microstalk of the character sheaf of $\mathcal{C}$ at that orbit. This should be considered a categorified analogue of a result of Moeglin-Waldspurger that the dimension of the generalized Whittaker model of a smooth admissible representation of a reductive group over a non-Archimedean local field of characteristic zero coincides with the Fourier coefficient in the wave-front set of that orbit. As a consequence, we give another proof of a theorem of Bezrukavnikov-Losev, classifying finite-dimensional modules for $W$-algebras with fixed regular central character. More precisely, we realize the (rationalized) Grothendieck group of this category as a certain subrepresentation of the Springer representation. Along the way, we show that the Springer action of the Weyl group on the twisted Grothendieck--Springer sheaves is the categorical trace of the wall crossing functors, extending an observation of Zhu for integral central characters., Comment: Minor updates to the introduction

The integration of non-terrestrial networks (NTN) into 5G new radio (NR) has opened up the possibility of developing a new positioning infrastructure using NR signals from Low-Earth Orbit (LEO) satellites. LEO-based cellular positioning offers several advantages, such as a superior link budget, higher operating bandwidth, and large forthcoming constellations. Due to these factors, LEO-based positioning, navigation, and timing (PNT) is a potential enhancement for NTN in 6G cellular networks. However, extending the existing terrestrial cellular positioning methods to LEO-based NTN positioning requires considering key fundamental enhancements. These include creating broad positioning beams orthogonal to conventional communication beams, time-domain processing at the user equipment (UE) to resolve large delay and Doppler uncertainties, and efficiently accommodating positioning reference signals (PRS) from multiple satellites within the communication resource grid. In this paper, we present the first set of design insights by incorporating these enhancements and thoroughly evaluating LEO-based positioning, considering the constraints and capabilities of the NR-NTN physical layer. To evaluate the performance of LEO-based NTN positioning, we develop a comprehensive NR-compliant simulation framework, including LEO orbit simulation, transmission (Tx) and receiver (Rx) architectures, and a positioning engine incorporating the necessary enhancements. Our findings suggest that LEO-based NTN positioning could serve as a complementary infrastructure to existing Global Navigation Satellite Systems (GNSS) and, with appropriate enhancements, may also offer a viable alternative., Comment: 7 pages, 6 figures, submitted to IEEE Communications Magazine

Interband Cascade Lasers (ICLs) are semiconductor lasers emitting in the mid-wave infrared (MWIR 3-6 {\mu}m) and can operate as frequency combs (FCs). These demonstrations are based on double section cavities that can reduce dispersion and/or are adapted for radio-frequency operation. Here we show that ICLs FCs at long wavelengths, where the refractive index dispersion reduces, can be realized in a single long section cavity. We show FC generation for ICLs operating at {\lambda} ~ 4.2 {\mu}m, demonstrating narrow electrical beatnotes over a large current range. We also reconstruct the ultrafast temporal response through a modified SWIFT spectroscopy setup with two fast MWIR detectors, which shows a frequency modulated response in free-running operation. Further, we show that, through active modelocking, the ICL can be forced to generate short pulses on the order of 3 ps. This temporal response is in agreement with Maxwell Bloch simulations, highlighting that these devices possess long dynamics (~100ps) and potentially makes them appropriate for the generation of large peak powers in the MWIR., Comment: 11 pages, 6 figures

SN 2023tsz is a Type Ibn supernova (SNe Ibn) discovered in an extremely low-mass host. SNe Ibn are an uncommon subtype of stripped-envelope core-collapse SNe. They are characterised by narrow helium emission lines in their spectra and are believed to originate from the collapse of massive Wolf-Rayet (WR) stars, though their progenitor systems still remain poorly understood. In terms of energetics and spectrophotometric evolution, SN 2023tsz is largely a typical example of the class, although line profile asymmetries in the nebular phase are seen, which may indicate the presence of dust formation or unshocked circumstellar material. Intriguingly, SN 2023tsz is located in an extraordinarily low-mass host galaxy that is in the 2nd percentile for SESN host masses and star formation rates (SFR). The host has a radius of 1.0 kpc, a $g$-band absolute magnitude of $-12.73$, and an estimated metallicity of $\log(Z_{*}/Z_{\odot}$) = $-1.56$. The SFR and metallicity of the host galaxy raise questions about the progenitor of SN 2023tsz. The low SFR suggests that a star with sufficient mass to evolve into a WR would be uncommon in this galaxy. Further, the very low-metallicity is a challenge for single stellar evolution to enable H and He stripping of the progenitor and produce a SN Ibn explosion. The host galaxy of SN 2023tsz adds another piece to the ongoing puzzle of SNe Ibn progenitors, and demonstrates that they can occur in hosts too faint to be observed in contemporary sky surveys at a more typical SN Ibn redshift., Comment: 14 pages, 10 figures, submitted to MNRAS

CXOU J110926.4-650224 is a candidate transitional millisecond pulsar (tMSP) with X-ray and radio emission properties reminiscent of those observed in confirmed tMSPs in their X-ray 'subluminous' disc state. We present the results of observing campaigns that, for the first time, characterise the optical and near-infrared variability of this source and establish a connection with the mode-switching phenomenon observed in X-rays. The optical emission exhibited flickering activity, frequent dipping episodes where it appeared redder, and a multi-peaked flare where it was bluer. The variability pattern was strongly correlated with that of the X-ray emission. Each dip matched an X-ray low-mode episode, indicating that a significant portion of the optical emission originates from nearly the same region as the X-ray emission. The near-infrared emission also displayed remarkable variability, including a dip of 20 min in length during which it nearly vanished. Time-resolved optical spectroscopic observations reveal significant changes in the properties of emission lines from the disc and help infer the spectral type of the companion star to be between K0 and K5. We compare the properties of CXOU J110926.4-650224 with those of other tMSPs in the X-ray subluminous disc state and discuss our findings within the context of a recently proposed scenario that explains the phenomenology exhibited by the prototypical tMSP PSR J1023+0038., Comment: 12 pages, 7 figures, 2 tables. Accepted for publication on Astronomy & Astrophysics

Despite significant algorithmic advances in vision-based positioning, a comprehensive probabilistic framework to study its performance has remained unexplored. The main objective of this paper is to develop such a framework using ideas from stochastic geometry. Due to limitations in sensor resolution, the level of detail in prior information, and computational resources, we may not be able to differentiate between landmarks with similar appearances in the vision data, such as trees, lampposts, and bus stops. While one cannot accurately determine the absolute target position using a single indistinguishable landmark, obtaining an approximate position fix is possible if the target can see multiple landmarks whose geometric placement on the map is unique. Modeling the locations of these indistinguishable landmarks as a Poisson point process (PPP) $\Phi$ on $\mathbb{R}^2$, we develop a new approach to analyze the localizability in this setting. From the target location $\mathbb{x}$, the measurements are obtained from landmarks within the visibility region. These measurements, including ranges and angles to the landmarks, denoted as $f(\mathbb{x})$, can be treated as mappings from the target location. We are interested in understanding the probability that the measurements $f(\mathbb{x})$ are sufficiently distinct from the measurement $f(\mathbb{x}_0)$ at the given location, which we term localizability. Expressions of localizability probability are derived for specific vision-inspired measurements, such as ranges to landmarks and snapshots of their locations. Our analysis reveals that the localizability probability approaches one when the landmark intensity tends to infinity, which means that error-free localization is achievable in this limiting regime., Comment: 23 pages, 7 figures