Search

Low-rank adaptation (LoRA) and its mixture-of-experts (MOE) variants are highly effective parameter-efficient fine-tuning (PEFT) methods. However, they introduce significant latency in multi-tenant settings due to the LoRA modules and MOE routers added to multiple linear modules in the Transformer layer. To address this issue, we propose Mixture of Low-Rank Adaptation (MiLoRA), a novel and efficient LoRA variant. MiLoRA differs from previous MOE-style LoRA methods by considering each LoRA module as an expert and employing a prompt-aware routing mechanism. This mechanism calculates expert routing results once before generating the first new token and reuses these results for subsequent tokens, reducing latency. Extensive experiments and analysis on commonsense reasoning tasks, math reasoning tasks, and widely used LLM evaluation benchmarks demonstrate that MiLoRA consistently outperforms strong PEFT baselines with comparable tunable parameter budgets. Additionally, MiLoRA significantly reduces latency in multi-tenant settings compared to previous LoRA-based methods., Comment: Accepted by EMNLP 2024 Findings. arXiv admin note: substantial text overlap with arXiv:2405.18203

The global symmetry, either invertible or non-invertible, has been extensively studied in two dimensional conformal field theories in recent years. When the theory is defined on a manifold with open boundaries, however, many interesting conformal boundary conditions will fully or partially break such global symmetry. In this work, we study the effect of symmetry-breaking boundaries or interfaces when the system is out of equilibrium. We show that the boundary or interface symmetry-breaking can be detected by the time evolution of string order parameters, which are constructed from the symmetry operators that implement the symmetry transformations. While the string order parameters are independent of time if the symmetry is preserved over the whole system, they evolve in time in a universal way if the boundary or interface breaks the symmetry. More explicitly, in the presence of boundary or interface symmetry-breaking, the string order parameters decay exponentially in time after a global quantum quench, and decay as a power-law in time after a local quantum quench. We also generalize our study to the case when the string order parameters are defined in a subsystem, which are related to the full counting statistics. It is found there are also universal features in the time evolution of string order parameters in this case. We verify our field theory results by studying the time evolution of these two different types of string order parameters in lattice models., Comment: are welcome. 32 pages, many figures

We present constraints on the shape of Kepler-51d, which is a super-puff with a mass $\sim6\,M_\oplus$ and a radius $\sim9\,R_\oplus$, based on detailed modeling of the transit light curve from JWST NIRSpec. The projected shape of this extremely low-density planet is consistent with being spherical, and a projected oblateness $f_\perp>0.2$ can be excluded regardless of the spin obliquity angles. If this is taken as the limit on the true shape of the planet, Kepler-51d is rotating at $\lesssim 50\%$ of its break-up spin rate, or its rotation period is $\gtrsim 33\,$hr. In the more plausible situation that the planetary spin is aligned with its orbital direction to within $30^\circ$, then its oblateness is $<0.08$, which corresponds to a dimensionless spin rate $\lesssim30\%$ of the break-up rotation and a dimensional rotation period $\gtrsim 53\,$hr. This seems to contradict the theoretical expectation that planets with such low masses may be spinning near break-up. We point out the usefulness of the stellar mean density and the orbital eccentricity in constraining the shape of the transiting planet, so planets with well-characterized host and orbital parameters are preferred in the detection of planetary oblateness with the JWST transit method., Comment: 11 pages, 4 figures. Accepted by ApJL

In an earlier work by a subset of the present authors, the method of the so-called neural deflation was introduced towards identifying a complete set of functionally independent conservation laws of a nonlinear dynamical system. Here, we extend by a significant step this proposal. Instead of using the explicit knowledge of the underlying equations of motion, we develop the method directly from system trajectories. This is crucial towards enhancing the practical implementation of the method in scenarios where solely data reflecting discrete snapshots of the system are available. We showcase the results of the method and the number of associated conservation laws obtained in a diverse range of examples including 1D and 2D harmonic oscillators, the Toda lattice, the Fermi-Pasta-Ulam-Tsingou lattice and the Calogero-Moser system.

Deep segmentation networks achieve high performance when trained on specific datasets. However, in clinical practice, it is often desirable that pretrained segmentation models can be dynamically extended to enable segmenting new organs without access to previous training datasets or without training from scratch. This would ensure a much more efficient model development and deployment paradigm accounting for the patient privacy and data storage issues. This clinically preferred process can be viewed as a continual semantic segmentation (CSS) problem. Previous CSS works would either experience catastrophic forgetting or lead to unaffordable memory costs as models expand. In this work, we propose a new continual whole-body organ segmentation model with light-weighted low-rank adaptation (LoRA). We first train and freeze a pyramid vision transformer (PVT) base segmentation model on the initial task, then continually add light-weighted trainable LoRA parameters to the frozen model for each new learning task. Through a holistically exploration of the architecture modification, we identify three most important layers (i.e., patch-embedding, multi-head attention and feed forward layers) that are critical in adapting to the new segmentation tasks, while retaining the majority of the pretrained parameters fixed. Our proposed model continually segments new organs without catastrophic forgetting and meanwhile maintaining a low parameter increasing rate. Continually trained and tested on four datasets covering different body parts of a total of 121 organs, results show that our model achieves high segmentation accuracy, closely reaching the PVT and nnUNet upper bounds, and significantly outperforms other regularization-based CSS methods. When comparing to the leading architecture-based CSS method, our model has a substantial lower parameter increasing rate while achieving comparable performance., Comment: Accepted by Medical Image Computing and Computer Assisted Intervention -- MICCAI 2024

We present spectroscopic and photometric observations of Bernhard-2, which was previously identified as a candidate system to host a misaligned circumbinary disk. Our spectroscopic measurements confirm that Bernhard-2 indeed contains an eccentric ($e=0.69 \pm 0.08$) binary and thus that the periodic variability in the photometric light curve is best explained by the occultation by the misaligned circumbinary disk. By modeling the spectral energy distributions at different phases, we infer the system age to be $\sim 20\,$Myr and the masses of the two binary components to be $\sim 1.1\,M_\odot$ and $\sim 0.9\,M_\odot$, respectively. Our new photometric observations show clear deviations from the model prediction based on the archival data, suggesting ongoing precession of the circumbinary disk. The H$\alpha$ line of Bernhard-2 also shows an inverse P-Cygni profile at epochs close to the pericenter passage, which could be attributed to the pulsed accretion around the pericenter. Bernhard-2 therefore closely resembles the well studied KH 15D system. Further detailed observations and studies of such rare systems can provide useful information about disk physics and evolution., Comment: 10 pages, 4 figures, submitted to AAS Journals, comments welcome

Due to their substantial sizes, large language models (LLMs) are typically deployed within a single-backbone multi-tenant framework. In this setup, a single instance of an LLM backbone must cater to multiple users or tasks through the application of various parameter-efficient fine-tuning (PEFT) models. Despite the availability of numerous effective PEFT techniques such as LoRA, there remains a need for a PEFT approach that achieves both high efficiency during inference and competitive performance on downstream tasks. In this research, we introduce a new and straightforward PEFT methodology named \underline{P}rompt D\underline{E}pen\underline{D}ent \underline{R}epresentation M\underline{O}dification (PEDRO). The proposed method involves integrating a lightweight vector generator into each Transformer layer, which generates vectors contingent upon the input prompts. These vectors then modify the hidden representations created by the LLM through a dot product operation, thereby influencing the semantic output and generated content of the model. Extensive experimentation across a variety of tasks indicates that: (a) PEDRO surpasses recent PEFT benchmarks when using a similar number of tunable parameters. (b) Under the single-backbone multi-tenant deployment model, PEDRO exhibits superior efficiency compared to LoRA, indicating significant industrial potential., Comment: arXiv admin note: text overlap with arXiv:2405.18203

In recent years, large language models (LLMs) have shown great potential in time-series analysis by capturing complex dependencies and improving predictive performance. However, existing approaches often struggle with modality alignment, leading to suboptimal results. To address these challenges, we present a novel framework, TS-TCD, which introduces a comprehensive three-tiered cross-modal knowledge distillation mechanism. Unlike prior work that focuses on isolated alignment techniques, our framework systematically integrates: 1) Dynamic Adaptive Gating for Input Encoding and Alignment}, ensuring coherent alignment between time-series tokens and QR-decomposed textual embeddings; 2) Layer-Wise Contrastive Learning}, aligning intermediate representations across modalities to reduce feature-level discrepancies; and 3) Optimal Transport-Driven Output Alignment}, which ensures consistent output predictions through fine-grained cross-modal alignment. Extensive experiments on benchmark time-series datasets demonstrate that TS-TCD achieves state-of-the-art results, outperforming traditional methods in both accuracy and robustness., Comment: Submitted to ICASSP 2025

In the fields of computer vision and robotics, accurate pixel-level correspondences are essential for enabling advanced tasks such as structure-from-motion and simultaneous localization and mapping. Recent correspondence pruning methods usually focus on learning local consistency through k-nearest neighbors, which makes it difficult to capture robust context for each correspondence. We propose CorrAdaptor, a novel architecture that introduces a dual-branch structure capable of adaptively adjusting local contexts through both explicit and implicit local graph learning. Specifically, the explicit branch uses KNN-based graphs tailored for initial neighborhood identification, while the implicit branch leverages a learnable matrix to softly assign neighbors and adaptively expand the local context scope, significantly enhancing the model's robustness and adaptability to complex image variations. Moreover, we design a motion injection module to integrate motion consistency into the network to suppress the impact of outliers and refine local context learning, resulting in substantial performance improvements. The experimental results on extensive correspondence-based tasks indicate that our CorrAdaptor achieves state-of-the-art performance both qualitatively and quantitatively. The code and pre-trained models are available at https://github.com/TaoWangzj/CorrAdaptor., Comment: 8 pages, 4 figures, accepted by ECAI

Pion condensation is a theoretical prediction, where pions form a special state of matter under certain extreme conditions in heavy ion collisions or neutron stars. However, there is currently no solid experimental evidence confirming the existence of pion condensation. We present a near-direct evidence for the existence of pion condensation. In actively changing galactic processes protons can be accelerated to very high energies and collide with the medium (protons or nuclei). The kinetic energy of the protons is mainly used to produce a large number of pions in the central region via gluons. When the collision energy exceeds a certain threshold, the huge amount of soft gluons condensed in protons pour into the central region, the number of pion increases abruptly to the saturation limit, and almost all the available collision energy is used to make pions, creating a dense, low-temperature pion condensation environment. Due to energy conservation and relativistic covariance, the gamma ray spectra produced by condensed pions exhibit recognizable broken power law with the gluon condensation characteristics. We find that they are already present in many recorded gamma ray spectra. Our findings reveal a novel mechanism for the generation of pion condensation, which is prevalent in the formation of high-energy cosmic rays, and deepen our understanding of related topics in a variety of disciplines, including particle physics, astrophysics, condensed matter physics and nuclear physics., Comment: 27 pages, 12 Figures

In the pursuit of understanding the population of stellar remnants within the Milky Way, we analyze the sample of $\sim 950$ microlensing events observed by the Spitzer Space Telescope between 2014 and 2019. In this study we focus on a sub-sample of nine microlensing events, selected based on their long timescales, small microlensing parallaxes and joint observations by the Gaia mission, to increase the probability that the chosen lenses are massive and the mass is measurable. Among the selected events we identify lensing black holes and neutron star candidates, with potential confirmation through forthcoming release of the Gaia time-series astrometry in 2026. Utilizing Bayesian analysis and Galactic models, along with the Gaia Data Release 3 proper motion data, four good candidates for dark remnants were identified: OGLE-2016-BLG-0293, OGLE-2018-BLG-0483, OGLE-2018-BLG-0662, and OGLE-2015-BLG-0149, with lens masses of $2.98^{+1.75}_{-1.28}~M_{\odot}$, $4.65^{+3.12}_{-2.08}~M_{\odot}$, $3.15^{+0.66}_{-0.64}~M_{\odot}$ and $1.4^{+0.75}_{-0.55}~M_{\odot}$, respectively. Notably, the first two candidates are expected to exhibit astrometric microlensing signals detectable by Gaia, offering the prospect of validating the lens masses. The methodologies developed in this work will be applied to the full Spitzer microlensing sample, populating and analyzing the time-scale ($t_{\rm E}$) vs. parallax ($\pi_{\rm E}$) diagram to derive constraints on the population of lenses in general and massive remnants in particular., Comment: submitted to ApJ

We develop analytical tools and perform three-body simulations to investigate the orbital evolution and dynamical stability of binary planets within star clusters. Our analytical results show that the orbital stability of a planetary-mass binary against passing stars is mainly related to its orbital period. Critical flybys, defined as stellar encounters with energy kicks comparable to the binary binding energy, can efficiently produce a wide range of semimajor axes ($a$) and eccentricities ($e$) from a dominant population of primordially tight JuMBOs. The critical flyby criterion we derived offers an improvement over the commonly used tidal radius criterion, particularly in high-speed stellar encounters. Applying our results to the recently discovered Jupiter-Mass Binary Objects (JuMBOs) by the James Webb Space Telescope (JWST), our simulations suggest that to match the observed $\sim$9% wide binary fraction, an initial semimajor axis of $a_0 \sim$ 10-20 au and a density-weighted residence time of $\chi \gtrsim 10^4$ Myr pc$^{-3}$ are favored. These results imply that the JWST JuMBOs probably formed as tight binaries near the cluster core., Comment: 11 pages, 4 figures, published on ApJL

A Chern insulator hosts topologically protected chiral edge currents with quantized conductance characterized by its Chern number. Switching the chirality of the Chern insulator, namely, the direction of the edge current, is highly challenging due to topologically forbidden backscattering but is of considerable importance for the design of topological devices. Nevertheless, this can be achieved by reversing the sign of the Chern number through a topological phase transition. Here, we report electrically switchable chirality in rhombohedral heptalayer graphene-based Chern insulators. The surface flat band and giant Berry curvature in rhombohedral multilayer graphene provide a highly tunable platform for engineering the topological states. By introducing moire superlattices in rhombohedral heptalayer graphene, we observed a cascade of topological phase transitions at quarter electron filling of a moire band. The Chern number can be continuously tuned from 0, -1, 1 to 2 by electric fields, manifesting as a large anomalous Hall effect and following Streda's formula. Sign reversal and the anomalous Hall effect also occurred at non-integer fillings, suggesting the possibility of electrically tunable topological phase transitions within the regime of fractional Chern insulators. Our work establishes rhombohedral heptalayer graphene moire superlattices as a versatile platform for topological engineering. The realization of switchable chirality enhances the potential application of chiral edge currents in topological circuit interconnects., Comment: 21 pages, 4 figures in main text

Planets may be rotationally flattened, and their oblateness thus provide useful information on their formation and evolution. Here we develop a new algorithm that can compute the transit light curve due to an oblate planet very efficiently and use it to study the detectability of planet oblateness (and spin obliquity) with the James Webb Space Telescope (JWST). Using the Jupiter analog, Kepler-167e, as an example, we show that observations of a single transit with JWST are able to detect a Saturn-like oblateness ($f=0.1$) with high confidence, or set a stringent upper limit on the oblateness parameter, as long as the planetary spin is slightly misaligned ($\gtrsim 20^\circ$) with respect to its orbital direction. Based on known obliquity measurements and theoretical arguments, it is reasonable to believe that this level of misalignment may be common. We estimate the sensitivity limit of JWST in oblateness detections and highlight the importance of better characterizations of cold planets in planning future JWST transit observations. The potential to detect rings, moons, and atmospheric species of the cold giants with JWST is also discussed., Comment: 17 pages, 8 figures. Submitted to Astronomical Journal

The moment quantities associated with the nonlinear Schrodinger equation offer important insights towards the evolution dynamics of such dispersive wave partial differential equation (PDE) models. The effective dynamics of the moment quantities is amenable to both analytical and numerical treatments. In this paper we present a data-driven approach associated with the Sparse Identification of Nonlinear Dynamics (SINDy) to numerically capture the evolution behaviors of such moment quantities. Our method is applied first to some well-known closed systems of ordinary differential equations (ODEs) which describe the evolution dynamics of relevant moment quantities. Our examples are, progressively, of increasing complexity and our findings explore different choices within the SINDy library. We also consider the potential discovery of coordinate transformations that lead to moment system closure. Finally, we extend considerations to settings where a closed analytical form of the moment dynamics is not available.

Large language models (LLMs) have performed remarkably well in various natural language processing tasks by benchmarking, including in the Western medical domain. However, the professional evaluation benchmarks for LLMs have yet to be covered in the traditional Chinese medicine(TCM) domain, which has a profound history and vast influence. To address this research gap, we introduce TCM-Bench, an comprehensive benchmark for evaluating LLM performance in TCM. It comprises the TCM-ED dataset, consisting of 5,473 questions sourced from the TCM Licensing Exam (TCMLE), including 1,300 questions with authoritative analysis. It covers the core components of TCMLE, including TCM basis and clinical practice. To evaluate LLMs beyond accuracy of question answering, we propose TCMScore, a metric tailored for evaluating the quality of answers generated by LLMs for TCM related questions. It comprehensively considers the consistency of TCM semantics and knowledge. After conducting comprehensive experimental analyses from diverse perspectives, we can obtain the following findings: (1) The unsatisfactory performance of LLMs on this benchmark underscores their significant room for improvement in TCM. (2) Introducing domain knowledge can enhance LLMs' performance. However, for in-domain models like ZhongJing-TCM, the quality of generated analysis text has decreased, and we hypothesize that their fine-tuning process affects the basic LLM capabilities. (3) Traditional metrics for text generation quality like Rouge and BertScore are susceptible to text length and surface semantic ambiguity, while domain-specific metrics such as TCMScore can further supplement and explain their evaluation results. These findings highlight the capabilities and limitations of LLMs in the TCM and aim to provide a more profound assistance to medical research., Comment: 20 pages, 15 figures

Soft prompt tuning is a widely studied parameter-efficient fine-tuning method. However, it has a clear drawback: many soft tokens must be inserted into the input sequences to guarantee downstream performance. As a result, soft prompt tuning is less considered than Low-rank adaptation (LoRA) in the large language modeling (LLM) era. In this work, we propose a novel prompt tuning method, Instruction-Aware Prompt Tuning (IAPT), that requires only four soft tokens. First, we install a parameter-efficient soft prompt generator at each Transformer layer to generate idiosyncratic soft prompts for each input instruction. The generated soft prompts can be seen as a semantic summary of the input instructions and can effectively guide the output generation. Second, the soft prompt generators are modules with a bottleneck architecture consisting of a self-attention pooling operation, two linear projections, and an activation function. Pilot experiments show that prompt generators at different Transformer layers require different activation functions. Thus, we propose to learn the idiosyncratic activation functions for prompt generators automatically with the help of rational functions. We have conducted experiments on various tasks, and the experimental results demonstrate that (a) our IAPT method can outperform the recent baselines with comparable tunable parameters. (b) Our IAPT method is more efficient than LoRA under the single-backbone multi-tenant setting., Comment: Accepted by ACL-2024

We present a novel method for training score-based generative models which uses nonlinear noising dynamics to improve learning of structured distributions. Generalizing to a nonlinear drift allows for additional structure to be incorporated into the dynamics, thus making the training better adapted to the data, e.g., in the case of multimodality or (approximate) symmetries. Such structure can be obtained from the data by an inexpensive preprocessing step. The nonlinear dynamics introduces new challenges into training which we address in two ways: 1) we develop a new nonlinear denoising score matching (NDSM) method, 2) we introduce neural control variates in order to reduce the variance of the NDSM training objective. We demonstrate the effectiveness of this method on several examples: a) a collection of low-dimensional examples, motivated by clustering in latent space, b) high-dimensional images, addressing issues with mode collapse, small training sets, and approximate symmetries, the latter being a challenge for methods based on equivariant neural networks, which require exact symmetries., Comment: 14 pages, 8 figures

In this paper, we propose Wasserstein proximals of $\alpha$-divergences as suitable objective functionals for learning heavy-tailed distributions in a stable manner. First, we provide sufficient, and in some cases necessary, relations among data dimension, $\alpha$, and the decay rate of data distributions for the Wasserstein-proximal-regularized divergence to be finite. Finite-sample convergence rates for the estimation in the case of the Wasserstein-1 proximal divergences are then provided under certain tail conditions. Numerical experiments demonstrate stable learning of heavy-tailed distributions -- even those without first or second moment -- without any explicit knowledge of the tail behavior, using suitable generative models such as GANs and flow-based models related to our proposed Wasserstein-proximal-regularized $\alpha$-divergences. Heuristically, $\alpha$-divergences handle the heavy tails and Wasserstein proximals allow non-absolute continuity between distributions and control the velocities of flow-based algorithms as they learn the target distribution deep into the tails., Comment: 23 pages, 7 figures

A recent experiment observes a series of quantum spin Hall effects in transition metal dichalcogenide moir\'e MoTe$_2$ [K. Kang, \textit{et. al}, Nature 628, 522-526 (2024)]. Among them, the filling $\nu=3$ state points to a time-reversal pair of edge states resembling those of the even-denominator fractional Chern insulators (FCIs). Inspired by this discovery, we investigate whether a robust incompressible quantum Hall liquid can be stabilized in the half-filled Chern band of twisted MoTe$_2$ bilayers. We use the continuum model with parameters relevant to twisted MoTe$_2$ bilayers and obtain three consecutive nearly flat Chern bands with the same Chern number. Crucially, when the second moir\'e miniband is half-filled, signatures of non-Abelian states are found via exact diagonalization calculations, including the stable six-fold ground state degeneracy which grows more robust for larger lattice sizes and is consistent with an even-denominator FCI state. We further perform flux insertion simulations to reveal a 1/2 quantized many-body Chern number as direct evidence of topological order. Furthermore, the ground state density structure factors show no sharp peak, indicating no charge density wave order. These evidences signal the potential of realizing the non-Abelian state at zero magnetic field in twisted bilayer MoTe$_2$ at the fractional hole filling 3/2., Comment: a complete undated version with errors corrected

We present the analysis of the microlensing event OGLE-2015-BLG-0845, which was affected by both the microlensing parallax and xallarap effects. The former was detected via the simultaneous observations from the ground and Spitzer, and the latter was caused by the orbital motion of the source star in a relatively close binary. The combination of these two effects led to a mass measurement of the lens object, revealing a low-mass ($0.14 \pm 0.05 M_{\odot}$) M-dwarf at the bulge distance ($7.6 \pm 1.0$ kpc). The source binary consists of a late F-type subgiant and a K-type dwarf of $\sim1.2 M_{\odot}$ and $\sim 0.9 M_{\odot}$, respectively, and the orbital period is $70 \pm 10$ days. OGLE-2015-BLG-0845 is the first single-lens event in which the lens mass is measured via the binarity of the source. Given the abundance of binary systems as potential microlensing sources, the xallarap effect may not be a rare phenomenon. Our work thus highlights the application of the xallarap effect in the mass determination of microlenses, and the same method can be used to identify isolated dark lenses., Comment: New version after the review process. Accepted for publication in Monthly Notices of the Royal Astronomical Society

Materials with in-plane electrical anisotropy have great potential for designing artificial synaptic devices. However, natural materials with strong intrinsic in-plane electrical anisotropy are rare. We introduce a simple strategy to produce extremely large electrical anisotropy via grating gating of a semiconductor two-dimensional electron gas (2DEG) of AlGaN/GaN. We show that periodically modulated electric potential in the 2DEG induces in-plane electrical anisotropy, which is significantly enhanced in a magnetic field, leading to an ultra large electrical anisotropy. This is induced by a giant positive magnetoresistance and a giant negative magnetoresistance under two orthogonally oriented in-plane current flows, respectively. This giant electrical anisotropy is in-situ tunable by tailoring both the grating gate voltage and the magnetic field. Our semiconductor device with controllable giant electrical anisotropy will stimulate new device applications, such as multi-terminal memtransistors and bionic synapses.

Parameter-efficient fine-tuning (PEFT) is widely studied for its effectiveness and efficiency in the era of large language models. Low-rank adaptation (LoRA) has demonstrated commendable performance as a popular and representative method. However, it is implemented with a fixed intrinsic rank that might not be the ideal setting for the downstream tasks. Recognizing the need for more flexible downstream task adaptation, we extend the methodology of LoRA to an innovative approach we call allocating low-rank adaptation (ALoRA) that enables dynamic adjustments to the intrinsic rank during the adaptation process. First, we propose a novel method, AB-LoRA, that can effectively estimate the importance score of each LoRA rank. Second, guided by AB-LoRA, we gradually prune abundant and negatively impacting LoRA ranks and allocate the pruned LoRA budgets to important Transformer modules needing higher ranks. We have conducted experiments on various tasks, and the experimental results demonstrate that our ALoRA method can outperform the recent baselines with comparable tunable parameters., Comment: Accepted by NAACL-2024

We use a newly recognized gluon distribution in the nucleon, which was predicted by a QCD evolution equation to consistently explain several intriguing phenomena associated with gamma-ray bursts. They are the GeV-TeV spectra of GRB 221009A, the remarkably symmetrical explosion cloud in kilonova AT2017gfo, and the absence of a very high-energy gamma-ray signature in GRB 170817A. We find that these occurrences can be attributed to the gluon condensation within nucleons, i.e., a significant number of soft gluons within nucleons are condensed at a critical momentum, resulting in the emergence of a steep and high peak in the gluon distributions. Through this profound connection between microscopic and macroscopic phenomena, we have not only expanded the applications of the hadronic scenario in cosmic gamma-ray emissions but also presented new evidence for the existence of gluon condensation., Comment: 30 pages, 6 figures, submitted to JCAP

Beam misalignment is one of the main challenges for the design of reliable wireless systems in terahertz (THz) bands. This paper investigates how to apply user-centric base station (BS) clustering as a valuable add-on in THz networks. In particular, to reduce the impact of beam misalignment, a user-centric BS clustering design that provides multi-connectivity via BS cooperation is investigated. The coverage probability is derived by leveraging an accurate approximation of the aggregate interference distribution that captures the effect of beam misalignment and THz fading. The numerical results reveal the impact of beam misalignment with respect to crucial link parameters, such as the transmitter's beam width and the serving cluster size, demonstrating that user-centric BS clustering is a promising enabler of THz networks.

Age verification, which is a mandatory legal requirement for delivering certain age-appropriate services or products, has recently been emphasized around the globe to ensure online safety for children. The rapid advancement of artificial intelligence has facilitated the recent development of some cutting-edge age-verification technologies, particularly using biometrics. However, successful deployment and mass acceptance of these technologies are significantly dependent on the corresponding socio-economic and regulatory context. This paper reviews such key dynamics for improvising age-verification technologies in Canada. It is particularly essential for such technologies to be inclusive, transparent, adaptable, privacy-preserving, and secure. Effective collaboration between academia, government, and industry entities can help to meet the growing demands for age-verification services in Canada while maintaining a user-centric approach., Comment: Presented and accepted for publication in the 2023 IEEE International Humanitarian Technologies Conference (IEEE IHTC 2023), November 1 to 3, 2023, Cartagena, Colombia

Continuum of spin excitations observed in inelastic neutron scattering experiments are often considered as a strong evidence of quantum spin liquid formation. When quantum spin liquid is indeed the ground state of a disorder-free magnetic compound, the elementary excitation is no longer the conventional spin waves (magnons). Instead, the magnons fractionalize into spinons, leaving only a two-spinon continuum detectable in inelastic neutron scattering experiments. For a clean ordered antiferromagnet, it was unclear if we can observe a continuous spectrum similar to the ones in a quantum spin liquid state. Here we show that the magnetically ordered state in Na$_2$BaCo(PO$_4$)$_2$ is able to host a spin excitation continuum induced by strong quantum fluctuations. Thus, a second thought is necessary when concluding such continuum as signature of quantum spin liquid in new material explorations., Comment: 22 pages,9 figures

A recent study by Hon et al. reported that a close-in planet around the red clump star, 8 UMi, should have been engulfed during the expansion phase of its parent star's evolution. They explained the survival of this exoplanet through a binary-merger channel for 8 UMi. The key to testing this formation scenario is to derive the true age of this star: is it an old "imposter" resulting from a binary merger, or a genuinely young red clump giant? To accomplish this, we derive kinematic and chemical properties for 8 UMi using astrometric data from {\it Gaia} DR3 and the element-abundance pattern measured from a high-resolution ($R \sim 75,000$) spectrum taken by SOPHIE. Our analysis shows that 8 UMi is a normal thin-disk star with orbital rotation speed of $\it{V}_\mathrm{\phi}=\mathrm{244.96 km s^{-1}}$, and possesses a Solar metallicity ([Fe/H] $= -0.05 \pm 0.07$) and $\alpha$-element abundance ratio ([$\alpha$/Fe] $= +0.01 \pm 0.03$). By adopting well-established relationships between age and space velocities/elemental abundances, we estimate a kinematic age of $3.50^{+3.00}_{-2.00}$ Gyr, and a chemical age of $3.25^{+2.50}_{-1.50}$ Gyr from [C/N] and $3.47 \pm 1.96$ Gyr from [Y/Mg] for 8 UMi, respectively. These estimates are consistent with the isochrone-fitting age ($1.90^{+1.15}_{-0.30}$ Gyr) of 8 UMi, but are all much younger than the timescale required in a binary-merger scenario. This result challenges the binary-merger model; the existence of such a closely orbiting exoplanet around a giant star remains a mystery yet to be resolved., Comment: 16 pages, 5 figures, 2 table; accepted by ApJL

Knowledge of the medical decision process, which can be modeled as medical decision trees (MDTs), is critical to build clinical decision support systems. However, the current MDT construction methods rely heavily on time-consuming and laborious manual annotation. In this work, we propose a novel task, Text2MDT, to explore the automatic extraction of MDTs from medical texts such as medical guidelines and textbooks. We normalize the form of the MDT and create an annotated Text-to-MDT dataset in Chinese with the participation of medical experts. We investigate two different methods for the Text2MDT tasks: (a) an end-to-end framework which only relies on a GPT style large language models (LLM) instruction tuning to generate all the node information and tree structures. (b) The pipeline framework which decomposes the Text2MDT task to three subtasks. Experiments on our Text2MDT dataset demonstrate that: (a) the end-to-end method basd on LLMs (7B parameters or larger) show promising results, and successfully outperform the pipeline methods. (b) The chain-of-thought (COT) prompting method \cite{Wei2022ChainOT} can improve the performance of the fine-tuned LLMs on the Text2MDT test set. (c) the lightweight pipelined method based on encoder-based pretrained models can perform comparably with LLMs with model complexity two magnititudes smaller. Our Text2MDT dataset is open-sourced at \url{https://tianchi.aliyun.com/dataset/95414}, and the source codes are open-sourced at \url{https://github.com/michael-wzhu/text2dt}.

Recent advancements in deep neural networks have markedly enhanced the performance of computer vision tasks, yet the specialized nature of these networks often necessitates extensive data and high computational power. Addressing these requirements, this study presents a novel neural network model adept at optical character recognition (OCR) across diverse domains, leveraging the strengths of multi-task learning to improve efficiency and generalization. The model is designed to achieve rapid adaptation to new domains, maintain a compact size conducive to reduced computational resource demand, ensure high accuracy, retain knowledge from previous learning experiences, and allow for domain-specific performance improvements without the need to retrain entirely. Rigorous evaluation on open datasets has validated the model's ability to significantly lower the number of trainable parameters without sacrificing performance, indicating its potential as a scalable and adaptable solution in the field of computer vision, particularly for applications in optical text recognition.

This paper presents an overview of the PromptCBLUE shared task (http://cips-chip.org.cn/2023/eval1) held in the CHIP-2023 Conference. This shared task reformualtes the CBLUE benchmark, and provide a good testbed for Chinese open-domain or medical-domain large language models (LLMs) in general medical natural language processing. Two different tracks are held: (a) prompt tuning track, investigating the multitask prompt tuning of LLMs, (b) probing the in-context learning capabilities of open-sourced LLMs. Many teams from both the industry and academia participated in the shared tasks, and the top teams achieved amazing test results. This paper describes the tasks, the datasets, evaluation metrics, and the top systems for both tasks. Finally, the paper summarizes the techniques and results of the evaluation of the various approaches explored by the participating teams.

Transformer based Large Language Models (LLMs) have been widely used in many fields, and the efficiency of LLM inference becomes hot topic in real applications. However, LLMs are usually complicatedly designed in model structure with massive operations and perform inference in the auto-regressive mode, making it a challenging task to design a system with high efficiency. In this paper, we propose an efficient LLM inference solution with low latency and high throughput. Firstly, we simplify the LLM decoder layer by fusing data movement and element-wise operations to reduce the memory access frequency and lower system latency. We also propose a segment KV cache policy to keep key/value of the request and response tokens in separate physical memory for effective device memory management, helping enlarge the runtime batch size and improve system throughput. A customized Scaled-Dot-Product-Attention kernel is designed to match our fusion policy based on the segment KV cache solution. We implement our LLM inference solution on Intel GPU and publish it publicly. Compared with the standard HuggingFace implementation, the proposed solution achieves up to 7x lower token latency and 27x higher throughput for some popular LLMs on Intel GPU.

The gravitational microlensing technique is most sensitive to planets in a Jupiter-like orbit and has detected more than 200 planets. However, only a few wide-orbit ($s > 2$) microlensing planets have been discovered, where $s$ is the planet-to-host separation normalized to the angular Einstein ring radius, $\theta_{\rm E}$. Here we present the discovery and analysis of a strong candidate wide-orbit microlensing planet in the event, OGLE-2017-BLG-0448. The whole light curve exhibits long-term residuals to the static binary-lens single-source model, so we investigate the residuals by adding the microlensing parallax, microlensing xallarap, an additional lens, or an additional source. For the first time, we observe a complex degeneracy between all four effects. The wide-orbit models with $s \sim 2.5$ and a planet-to-host mass-ratio of $q \sim 10^{-4}$ are significantly preferred, but we cannot rule out the close models with $s \sim 0.35$ and $q \sim 10^{-3}$. A Bayesian analysis based on a Galactic model indicates that, despite the complicated degeneracy, the surviving wide-orbit models all contain a super-Earth-mass to Neptune-mass planet at a projected planet-host separation of $\sim 6$ au and the surviving close-orbit models all consist of a Jovian-mass planet at $\sim 1$ au. The host star is probably an M or K dwarf. We discuss the implications of this dimension-degeneracy disaster on microlensing light-curve analysis and its potential impact on statistical studies., Comment: submitted to AJ