Search

Described is the Parenting Program for the Prevention of Child Abuse which employs home visits to upgrade home environments and to prevent physical abuse of children up to 6 years of age. The program is noted to focus on four major areas: psychological support of the parent; obtaining social services (including health services, educational programs, and financial assistance) that are needed; resolution of inner conflicts which contribute to the danger of child abuse; and parent education in the area of parenting skills. Also explained are factors considered when making referrals to the Parenting Program, specific evaluation and treatment functions, and training of therapists. (SBH)

The Pandora Software Development Kit and algorithm libraries perform reconstruction of neutrino interactions in liquid argon time projection chamber detectors. Pandora is the primary event reconstruction software used at the Deep Underground Neutrino Experiment, which will operate four large-scale liquid argon time projection chambers at the far detector site in South Dakota, producing high-resolution images of charged particles emerging from neutrino interactions. While these high-resolution images provide excellent opportunities for physics, the complex topologies require sophisticated pattern recognition capabilities to interpret signals from the detectors as physically meaningful objects that form the inputs to physics analyses. A critical component is the identification of the neutrino interaction vertex. Subsequent reconstruction algorithms use this location to identify the individual primary particles and ensure they each result in a separate reconstructed particle. A new vertex-finding procedure described in this article integrates a U-ResNet neural network performing hit-level classification into the multi-algorithm approach used by Pandora to identify the neutrino interaction vertex. The machine learning solution is seamlessly integrated into a chain of pattern-recognition algorithms. The technique substantially outperforms the previous BDT-based solution, with a more than 20\% increase in the efficiency of sub-1\,cm vertex reconstruction across all neutrino flavours., Comment: 32 pages, 18 figures

Continuous gravitational waves (CWs) emission from neutron stars carries information about their internal structure and equation of state, and it can provide tests of General Relativity. We present a search for CWs from a set of 45 known pulsars in the first part of the fourth LIGO--Virgo--KAGRA observing run, known as O4a. We conducted a targeted search for each pulsar using three independent analysis methods considering the single-harmonic and the dual-harmonic emission models. We find no evidence of a CW signal in O4a data for both models and set upper limits on the signal amplitude and on the ellipticity, which quantifies the asymmetry in the neutron star mass distribution. For the single-harmonic emission model, 29 targets have the upper limit on the amplitude below the theoretical spin-down limit. The lowest upper limit on the amplitude is $6.4\!\times\!10^{-27}$ for the young energetic pulsar J0537-6910, while the lowest constraint on the ellipticity is $8.8\!\times\!10^{-9}$ for the bright nearby millisecond pulsar J0437-4715. Additionally, for a subset of 16 targets we performed a narrowband search that is more robust regarding the emission model, with no evidence of a signal. We also found no evidence of non-standard polarizations as predicted by the Brans-Dicke theory., Comment: main paper: 12 pages, 6 figures, 4 tables

Ultrafast optical excitation of quantum materials has opened new frontiers for transiently inducing novel phases of matter, including magnetism, charge density waves, ferroelectricity, and superconductivity beyond the constraints of equilibrium thermodynamics. Triggering a transient topological order in a trivial semiconductor represents a key milestone, as it could provide an on-demand route to topological functionality for device applications. However, achieving a topologically nontrivial phase from a large-gap (~ 1 eV) semiconductor remains a major challenge, as substantial energy modification is required to invert the band gap. Here, we report the discovery of a thermally inaccessible, transient topological crystalline order in a sizable-gap (~ 0.8 eV) layered semiconductor, SnSe, through femtosecond above-gap excitation. Time- and angle-resolved photoemission spectroscopy reveals a Dirac-like linear dispersion forming within the band gap on a subpicosecond timescale. This transient state shows hallmark features of a reflection-invariant topological crystalline insulator, including a high Fermi velocity (2.5x10^5 m/s), multiple Dirac points located away from high-symmetry momenta, and independence from probe photon energy, persisting for several picoseconds even at room temperature. Our findings establish a nonequilibrium pathway to ultrafast topological order in a semiconductor, opening new avenues for optically driven spintronic and quantum information technologies., Comment: 24 pages, 4 figures

We analyze the Drinfeld-Sokolob-Wilson system, which features a dispersive, KdV type evolution with a dispersionless conservation law. We establish well-posedness with low regularity initial data $L^2({\mathbb T})\times L^2({\mathbb T})$ for the Cauchy problem on periodic background, which is then extrapolated to global solutions, due to $L^2$ conservation law. We also establish a dynamically more relevant result, namely a global persistence of solutions with (large) initial data in $H^1({\mathbb T})\times L^2({\mathbb T})$. This is obtained by following a more sophisticated approach, specifically the method of normal forms. Finally, for a fixed period $L$, we construct an explicit one parameter family of periodic waves, see \eqref{2.16} below. We show that they are all spectrally unstable with respect to co-periodic perturbations. Specifically, we show that the Hamiltonian instability index is equal to one, which identifies the instability as a single positive growing mode.

Self-awareness, i.e., the ability to assess and correct one's own generation, is a fundamental aspect of human intelligence, making its replication in large language models (LLMs) an important yet challenging task. Previous works tackle this by employing extensive reinforcement learning or rather relying on large external verifiers. In this work, we propose Refine via Intrinsic Self-Verification (ReVISE), an efficient and effective framework that enables LLMs to self-correct their outputs through self-verification. The core idea of ReVISE is to enable LLMs to verify their reasoning processes and continually rethink reasoning trajectories based on its verification. We introduce a structured curriculum based upon online preference learning to implement this efficiently. Specifically, as ReVISE involves two challenging tasks (i.e., self-verification and reasoning correction), we tackle each task sequentially using curriculum learning, collecting both failed and successful reasoning paths to construct preference pairs for efficient training. During inference, our approach enjoys natural test-time scaling by integrating self-verification and correction capabilities, further enhanced by our proposed confidence-aware decoding mechanism. Our experiments on various reasoning tasks demonstrate that ReVISE achieves efficient self-correction and significantly improves reasoning performance.

Lab tests are fundamental for diagnosing diseases and monitoring patient conditions. However, frequent testing can be burdensome for patients, and test results may not always be immediately available. To address these challenges, we propose LabTOP, a unified model that predicts lab test outcomes by leveraging a language modeling approach on EHR data. Unlike conventional methods that estimate only a subset of lab tests or classify discrete value ranges, LabTOP performs continuous numerical predictions for a diverse range of lab items. We evaluate LabTOP on three publicly available EHR datasets and demonstrate that it outperforms existing methods, including traditional machine learning models and state-of-the-art large language models. We also conduct extensive ablation studies to confirm the effectiveness of our design choices. We believe that LabTOP will serve as an accurate and generalizable framework for lab test outcome prediction, with potential applications in clinical decision support and early detection of critical conditions., Comment: 11 pages for main text, 4 pages for appendix

Large Language Models (LLMs) have recently emerged as promising tools for recommendation thanks to their advanced textual understanding ability and context-awareness. Despite the current practice of training and evaluating LLM-based recommendation (LLM4Rec) models under a sequential recommendation scenario, we found that whether these models understand the sequential information inherent in users' item interaction sequences has been largely overlooked. In this paper, we first demonstrate through a series of experiments that existing LLM4Rec models do not fully capture sequential information both during training and inference. Then, we propose a simple yet effective LLM-based sequential recommender, called LLM-SRec, a method that enhances the integration of sequential information into LLMs by distilling the user representations extracted from a pre-trained CF-SRec model into LLMs. Our extensive experiments show that LLM-SRec enhances LLMs' ability to understand users' item interaction sequences, ultimately leading to improved recommendation performance. Furthermore, unlike existing LLM4Rec models that require fine-tuning of LLMs, LLM-SRec achieves state-of-the-art performance by training only a few lightweight MLPs, highlighting its practicality in real-world applications. Our code is available at https://github.com/Sein-Kim/LLM-SRec.

Altermagnets exhibit characteristics akin to antiferromagnets, with spin-split anisotropic bands in momentum space. RuO$_2$ has been considered as a prototype altermagnet; however, recent reports have questioned altermagnetic ground state in this material. In this study, we provide direct experimental evidence of altermagnetic characteristics in RuO$_2$ films by demonstrating spin-dependent tunneling magnetoresistance (TMR) in RuO$_2$-based magnetic tunnel junctions. Our results show the spin-splitted anisotropic band structure of RuO$_2$, with the observed TMR determined by the direction of the N\'eel vector of RuO$_2$. These results reflect the altermagnetic nature of RuO$_2$ and highlight its potential for spintronic applications, leveraging the combined strengths of ferromagnetic and antiferromagnetic systems.

The Hopf index equates the multiplicity of a zero of a section of a vector bundle with a winding number. We give eight analogues for isotropic sections of bundles with quadratic form. There are applications to cosection localised virtual cycles and to DT$^4$ virtual cycles., Comment: 27 pages

We present efficient classical algorithms to approximate expectation values and probability amplitudes in linear optical circuits. Specifically, our classical algorithm efficiently approximates the expectation values of observables in linear optical circuits for arbitrary product input states within an additive error under a mild condition. This result suggests that certain applications of linear optical circuits relying on expectation value estimation, such as photonic variational algorithms, may face challenges in achieving quantum advantage. In addition, the (marginal) output probabilities of boson sampling with arbitrary product input states can be efficiently approximated using our algorithm, implying that boson sampling can be efficiently simulated if its output probability distribution is polynomially sparse. Moreover, our method generalizes Gurvits's algorithm, originally designed to approximate the permanent, to also approximate the hafnian of complex symmetric matrices with an additive error. The algorithm also solves a molecular vibronic spectra problem for arbitrary product input states as precisely as boson samplers. Finally, our method extends to near-Clifford circuits, enabling the classical approximation of their expectation values of any observables and (marginal) output probabilities., Comment: 7+7 pages, 1 figure

Achieving successful scan matching is essential for LiDAR odometry. However, in challenging environments with adverse weather conditions or repetitive geometric patterns, LiDAR odometry performance is degraded due to incorrect scan matching. Recently, the emergence of frequency-modulated continuous wave 4D LiDAR and 4D radar technologies has provided the potential to address these unfavorable conditions. The term 4D refers to point cloud data characterized by range, azimuth, and elevation along with Doppler velocity. Although 4D data is available, most scan matching methods for 4D LiDAR and 4D radar still establish correspondence by repeatedly identifying the closest points between consecutive scans, overlooking the Doppler information. This paper introduces, for the first time, a simple Doppler velocity-based correspondence -- Doppler Correspondence -- that is invariant to translation and small rotation of the sensor, with its geometric and kinematic foundations. Extensive experiments demonstrate that the proposed method enables the direct matching of consecutive point clouds without an iterative process, making it computationally efficient. Additionally, it provides a more robust correspondence estimation in environments with repetitive geometric patterns.

With a new joint-deconvolution pipeline, we combine the single-dish and interferometric atomic hydrogen (HI) data of M51 observed by the FAST (FEASTS program) and VLA (THINGS). The product data cube has a typical line width of $13\,\text{km}\,\text{s}^{-1}$ and a $2\sigma$ line-of-sight (LOS) sensitivity of HI column density $N_\text{HI}\sim3.2\times10^{18}\,\text{cm}^{-2}$ at a spatial resolution of ${\sim}18''$ (${\sim}0.7\,\text{kpc}$). Among the HI-detected LOSs extending to ${\sim}50\,\text{kpc}$, ${\sim}89\%$ consist of diffuse HI only, which is missed by previous VLA observations. The distribution of dense HI is reproduced by previous hydrodynamical simulations of this system, but the diffuse component is not, likely due to unresolved physics related to the interaction between the circumgalactic and interstellar media. With simple models, we find that these low-$N_\text{HI}$ structures could survive the background ultraviolet photoionization, but are susceptible to the thermal evaporation. We find a positive correlation between LOS velocity dispersion ($\sigma_v$) and $N_\text{HI}$ with a logarithmic index of ${\sim}0.5$. Based on existing turbulent mixing layer (TML) theories and simulations, we propose a scenario of hot gas cooling and accreting onto the disk through a TML, which could reproduce the observed power index of ${\sim}0.5$. We estimate the related cooling and accretion rates to be roughly $1/3$ to $2/3$ of the star-formation rate. A typical column density of diffuse HI (${\sim}10^{19}\,\text{cm}^{-2}$) can be accreted within $300\,\text{Myr}$, the interaction time scale previously estimated for the system. Such a gas accretion channel has been overlooked before, and may be important for gas-rich interacting systems and for high redshift galaxy evolution., Comment: 16 pages of main text, 7 pages of appendices, 27 pages in total; 18 figures, 1 table; accepted for publication in ApJ

In \cite{Oh22}, the second author defined a complex of groups decomposition of the fundamental group of a finitely generated 2-dimensional special group, called an \emph{intersection complex}, which is a quasi-isometry invariant. In this paper, using the theory of intersection complexes, we classify the class of 2-braid groups over graphs with circumference $\leq 1$ up to quasi-isometry. Moreover, we find a sufficient condition when such a graph 2-braid group is quasi-isometric to a right-angled Artin group or not. Finally, by applying the same method, we also find that there is an algorithm to determine whether two 4-braid groups over trees are quasi-isometric or not., Comment: 69 pages. Comments are welcome

In this paper, we consider combinatorial reinforcement learning with preference feedback, where a learning agent sequentially offers an action--an assortment of multiple items to--a user, whose preference feedback follows a multinomial logistic (MNL) model. This framework allows us to model real-world scenarios, particularly those involving long-term user engagement, such as in recommender systems and online advertising. However, this framework faces two main challenges: (1) the unknown value of each item, unlike traditional MNL bandits that only address single-step preference feedback, and (2) the difficulty of ensuring optimism while maintaining tractable assortment selection in the combinatorial action space with unknown values. In this paper, we assume a contextual MNL preference model, where the mean utilities are linear, and the value of each item is approximated by a general function. We propose an algorithm, MNL-VQL, that addresses these challenges, making it both computationally and statistically efficient. As a special case, for linear MDPs (with the MNL preference feedback), we establish the first regret lower bound in this framework and show that MNL-VQL achieves nearly minimax-optimal regret. To the best of our knowledge, this is the first work to provide statistical guarantees in combinatorial RL with preference feedback., Comment: Preprint. Under review

In this paper, we propose an improved online confidence bound for multinomial logistic (MNL) models and apply this result to MNL bandits, achieving variance-dependent optimal regret. Recently, Lee & Oh (2024) established an online confidence bound for MNL models and achieved nearly minimax-optimal regret in MNL bandits. However, their results still depend on the norm-boundedness of the unknown parameter $B$ and the maximum size of possible outcomes $K$. To address this, we first derive an online confidence bound of $O\left(\sqrt{d \log t} + B \right)$, which is a significant improvement over the previous bound of $O (B \sqrt{d} \log t \log K )$ (Lee & Oh, 2024). This is mainly achieved by establishing tighter self-concordant properties of the MNL loss and introducing a novel intermediary term to bound the estimation error. Using this new online confidence bound, we propose a constant-time algorithm, OFU-MNL++, which achieves a variance-dependent regret bound of $O \Big( d \log T \sqrt{ \smash[b]{\sum_{t=1}^T} \sigma_t^2 } \Big) $ for sufficiently large $T$, where $\sigma_t^2$ denotes the variance of the rewards at round $t$, $d$ is the dimension of the contexts, and $T$ is the total number of rounds. Furthermore, we introduce a Maximum Likelihood Estimation (MLE)-based algorithm, OFU-MN$^2$L, which achieves an anytime poly(B)-free regret of $O \Big( d \log (BT) \sqrt{ \smash[b]{\sum_{t=1}^T} \sigma_t^2 } \Big) $., Comment: Preprint. Under review

Time series modeling and analysis has become critical in various domains. Conventional methods such as RNNs and Transformers, while effective for discrete-time and regularly sampled data, face significant challenges in capturing the continuous dynamics and irregular sampling patterns inherent in real-world scenarios. Neural Differential Equations (NDEs) represent a paradigm shift by combining the flexibility of neural networks with the mathematical rigor of differential equations. This paper presents a comprehensive review of NDE-based methods for time series analysis, including neural ordinary differential equations, neural controlled differential equations, and neural stochastic differential equations. We provide a detailed discussion of their mathematical formulations, numerical methods, and applications, highlighting their ability to model continuous-time dynamics. Furthermore, we address key challenges and future research directions. This survey serves as a foundation for researchers and practitioners seeking to leverage NDEs for advanced time series analysis.

We establish the asymptotic stability of solutions to the inflow problem for the one-dimensional barotropic Navier-Stokes equations in half space. When the boundary value is located at the subsonic regime, all the possible thirteen asymptotic patterns are classified in \cite{M01}. We consider the most complicated pattern, the superposition of the boundary layer solution, the 1-rarefaction wave, and the viscous 2-shock waves. In this superposition, the boundary layer is degenerate and large. We prove that, if the strengths of the rarefaction wave and shock wave are small, and if the initial data is a small perturbation of the superposition, then the solution asymptotically converges to the superposition up to a dynamical shift for the shock. As a corollary, our result implies the asymptotic stability for the simpler case where the superposition consists of the degenerate boundary layer solution and the viscous 2-shock. Therefore, we complete the study of the asymptotic stability of the inflow problem for the 1D barotropic Navier-Stokes equations for subsonic boundary values.

Text-to-image diffusion models have recently enabled the creation of visually compelling, detailed images from textual prompts. However, their ability to accurately represent various cultural nuances remains an open question. In our work, we introduce CultDiff benchmark, evaluating state-of-the-art diffusion models whether they can generate culturally specific images spanning ten countries. We show that these models often fail to generate cultural artifacts in architecture, clothing, and food, especially for underrepresented country regions, by conducting a fine-grained analysis of different similarity aspects, revealing significant disparities in cultural relevance, description fidelity, and realism compared to real-world reference images. With the collected human evaluations, we develop a neural-based image-image similarity metric, namely, CultDiff-S, to predict human judgment on real and generated images with cultural artifacts. Our work highlights the need for more inclusive generative AI systems and equitable dataset representation over a wide range of cultures., Comment: 17 pages, 17 figures, 3 tables

Ultrafast light-matter interactions inspire potential functionalities in picosecond optoelectronic applications. However, achieving directional carrier dynamics in metals remains challenging due to strong carrier scattering within a multiband environment, typically expected to isotropic carrier relaxation. In this study, we demonstrate epitaxial RuO2/TiO2 (110) heterostructures grown by hybrid molecular beam epitaxy to engineer polarization-selectivity of ultrafast light-matter interactions via anisotropic strain engineering. Combining spectroscopic ellipsometry, X-ray absorption spectroscopy, and optical pump-probe spectroscopy, we revealed the strong anisotropic transient optoelectronic response of strain-engineered RuO2/TiO2 (110) heterostructures along both in-plane [001] and [1-10] crystallographic directions. Theoretical analysis identifies strain-induced modifications in band nesting as the underlying mechanism for enhanced anisotropic carrier relaxation. These findings establish epitaxial strain engineering as a powerful tool for tuning anisotropic optoelectronic responses in metallic systems, paving the way for next-generation polarization-sensitive ultrafast optoelectronic devices., Comment: 18 pages

Recent advancements in quantum technologies have opened new horizons for exploring the physical world in ways once deemed impossible. Central to these breakthroughs is the concept of quantum advantage, where quantum systems outperform their classical counterparts in solving specific tasks. While much attention has been devoted to computational speedups, quantum advantage in learning physical systems remains a largely untapped frontier. Here, we present a photonic implementation of a quantum-enhanced protocol for learning the probability distribution of a multimode bosonic displacement process. By harnessing the unique properties of continuous-variable quantum entanglement, we obtain a massive advantage in sample complexity with respect to conventional methods without entangled resources. With approximately 5 dB of two-mode squeezing -- corresponding to imperfect Einstein--Podolsky--Rosen (EPR) entanglement -- we learn a 100-mode bosonic displacement process using 11.8 orders of magnitude fewer samples than a conventional scheme. Our results demonstrate that even with non-ideal, noisy entanglement, a significant quantum advantage can be realized in continuous-variable quantum systems. This marks an important step towards practical quantum-enhanced learning protocols with implications for quantum metrology, certification, and machine learning., Comment: 8+23 pages, 3+10 figures

Model fingerprinting has emerged as a powerful tool for model owners to identify their shared model given API access. However, to lower false discovery rate, fight fingerprint leakage, and defend against coalitions of model users attempting to bypass detection, we argue that {\em scalability} is critical, i.e., scaling up the number of fingerprints one can embed into a model. Hence, we pose scalability as a crucial requirement for fingerprinting schemes. We experiment with fingerprint design at a scale significantly larger than previously considered, and introduce a new method, dubbed Perinucleus sampling, to generate scalable, persistent, and harmless fingerprints. We demonstrate that this scheme can add 24,576 fingerprints to a Llama-3.1-8B model -- two orders of magnitude more than existing schemes -- without degrading the model's utility. Our inserted fingerprints persist even after supervised fine-tuning on standard post-training data. We further address security risks for fingerprinting, and theoretically and empirically show how a scalable fingerprinting scheme like ours can mitigate these risks., Comment: 23 pages 15 figures

Progress in AI has relied on human-generated data, from annotator marketplaces to the wider Internet. However, the widespread use of large language models now threatens the quality and integrity of human-generated data on these very platforms. We argue that this issue goes beyond the immediate challenge of filtering AI-generated content--it reveals deeper flaws in how data collection systems are designed. Existing systems often prioritize speed, scale, and efficiency at the cost of intrinsic human motivation, leading to declining engagement and data quality. We propose that rethinking data collection systems to align with contributors' intrinsic motivations--rather than relying solely on external incentives--can help sustain high-quality data sourcing at scale while maintaining contributor trust and long-term participation.

Electronic flat bands associated with quenched kinetic energy and heavy electron mass have attracted great interest for promoting strong electronic correlations and emergent phenomena such as high-temperature charge fractionalization and superconductivity. Intense experimental and theoretical research has been devoted to establishing the rich non-trivial metallic and heavy fermion phases intertwined with such localized electronic states. Here, we investigate the transition metal oxide spinel LiV2O4, an enigmatic heavy fermion compound lacking localized f orbital states. We use angle-resolved photoemission spectroscopy and dynamical mean field theory to reveal a new kind of correlation-induced flat band with suppressed inter-atomic electron hopping arising from intra-atomic Hund coupling. The appearance of heavy quasiparticles is ascribed to a proximate orbital-selective Mott state characterized by fluctuating local moments as evidenced by complementary magnetotransport measurements. The spectroscopic fingerprints of long-lived quasiparticles and their disappearance with increasing temperature further support the emergence of a high-temperature bad metal state observed in transport data. This work resolves a long-standing puzzle on the origin of heavy fermion behavior and unconventional transport in LiV2O4. Simultaneously, it opens a new path to achieving flat bands through electronic interactions in d-orbital systems with geometrical frustration, potentially enabling the realization of exotic phases of matter such as the fractionalized Fermi liquids., Comment: 21 pages, 4 figures

Depth completion, predicting dense depth maps from sparse depth measurements, is an ill-posed problem requiring prior knowledge. Recent methods adopt learning-based approaches to implicitly capture priors, but the priors primarily fit in-domain data and do not generalize well to out-of-domain scenarios. To address this, we propose a zero-shot depth completion method composed of an affine-invariant depth diffusion model and test-time alignment. We use pre-trained depth diffusion models as depth prior knowledge, which implicitly understand how to fill in depth for scenes. Our approach aligns the affine-invariant depth prior with metric-scale sparse measurements, enforcing them as hard constraints via an optimization loop at test-time. Our zero-shot depth completion method demonstrates generalization across various domain datasets, achieving up to a 21\% average performance improvement over the previous state-of-the-art methods while enhancing spatial understanding by sharpening scene details. We demonstrate that aligning a monocular affine-invariant depth prior with sparse metric measurements is a proven strategy to achieve domain-generalizable depth completion without relying on extensive training data. Project page: https://hyoseok1223.github.io/zero-shot-depth-completion/., Comment: AAAI 2025, Project page: https://hyoseok1223.github.io/zero-shot-depth-completion/

The implementation of Hyperdimensional Computing (HDC) on In-Memory Computing (IMC) architectures faces significant challenges due to the mismatch between highdimensional vectors and IMC array sizes, leading to inefficient memory utilization and increased computation cycles. This paper presents MEMHD, a Memory-Efficient Multi-centroid HDC framework designed to address these challenges. MEMHD introduces a clustering-based initialization method and quantization aware iterative learning for multi-centroid associative memory. Through these approaches and its overall architecture, MEMHD achieves a significant reduction in memory requirements while maintaining or improving classification accuracy. Our approach achieves full utilization of IMC arrays and enables one-shot (or few-shot) associative search. Experimental results demonstrate that MEMHD outperforms state-of-the-art binary HDC models, achieving up to 13.69% higher accuracy with the same memory usage, or 13.25x more memory efficiency at the same accuracy level. Moreover, MEMHD reduces computation cycles by up to 80x and array usage by up to 71x compared to baseline IMC mapping methods when mapped to 128x128 IMC arrays, while significantly improving energy and computation cycle efficiency., Comment: Accepted to appear at DATE 2025

The viability of adiabatic quantum computation depends on the slow evolution of the Hamiltonian. The adiabatic switching theorem provides an asymptotic series for error estimates in $1/T$, based on the lowest non-zero derivative of the Hamiltonian and its eigenvalues at the endpoints. Modifications at the endpoints in practical implementations can modify this scaling behavior, suggesting opportunities for error reduction by altering endpoint behavior while keeping intermediate evolution largely unchanged. Such modifications can significantly reduce errors for long evolution times, but they may also require exceedingly long timescales to reach the hyperadiabatic regime, limiting their practicality. This paper explores the transition between the adiabatic and hyperadiabatic regimes in simple low-dimensional Hamiltonians, highlighting the impact of modifications of the endpoints on approaching the asymptotic behavior described by the switching theorem., Comment: 9 pages, 10 figures

We introduce a novel linear bandit problem with partially observable features, resulting in partial reward information and spurious estimates. Without proper address for latent part, regret possibly grows linearly in decision horizon $T$, as their influence on rewards are unknown. To tackle this, we propose a novel analysis to handle the latent features and an algorithm that achieves sublinear regret. The core of our algorithm involves (i) augmenting basis vectors orthogonal to the observed feature space, and (ii) introducing an efficient doubly robust estimator. Our approach achieves a regret bound of $\tilde{O}(\sqrt{(d + d_h)T})$, where $d$ is the dimension of observed features, and $d_h$ is the unknown dimension of the subspace of the unobserved features. Notably, our algorithm requires no prior knowledge of the unobserved feature space, which may expand as more features become hidden. Numerical experiments confirm that our algorithm outperforms both non-contextual multi-armed bandits and linear bandit algorithms depending solely on observed features.

Recent advances in quadrupedal robots have demonstrated impressive agility and the ability to traverse diverse terrains. However, hardware issues, such as motor overheating or joint locking, may occur during long-distance walking or traversing through rough terrains leading to locomotion failures. Although several studies have proposed fault-tolerant control methods for quadrupedal robots, there are still challenges in traversing unstructured terrains. In this paper, we propose DreamFLEX, a robust fault-tolerant locomotion controller that enables a quadrupedal robot to traverse complex environments even under joint failure conditions. DreamFLEX integrates an explicit failure estimation and modulation network that jointly estimates the robot's joint fault vector and utilizes this information to adapt the locomotion pattern to faulty conditions in real-time, enabling quadrupedal robots to maintain stability and performance in rough terrains. Experimental results demonstrate that DreamFLEX outperforms existing methods in both simulation and real-world scenarios, effectively managing hardware failures while maintaining robust locomotion performance., Comment: Accepted for ICRA 2025. Project site is available at https://dreamflex.github.io/

In this letter, we propose an online scalar field estimation algorithm of unknown environments using a distributed Gaussian process (DGP) framework in wireless sensor networks (WSNs). While the kernel-based Gaussian process (GP) has been widely employed for estimating unknown scalar fields, its centralized nature is not well-suited for handling a large amount of data from WSNs. To overcome the limitations of the kernel-based GP, recent advancements in GP research focus on approximating kernel functions as products of E-dimensional nonlinear basis functions, which can handle large WSNs more efficiently in a distributed manner. However, this approach requires a large number of basis functions for accurate approximation, leading to increased computational and communication complexities. To address these complexity issues, the paper proposes a distributed GP framework by incorporating a Kalman filter scheme (termed as K-DGP), which scales linearly with the number of nonlinear basis functions. Moreover, we propose a new consensus protocol designed to handle the unique data transmission requirement residing in the proposed K-DGP framework. This protocol preserves the inherent elements in the form of a certain column in the nonlinear function matrix of the communicated message; it enables wireless sensors to cooperatively estimate the environment and reach the global consensus through distributed learning with faster convergence than the widely-used average consensus protocol. Simulation results demonstrate rapid consensus convergence and outstanding estimation accuracy achieved by the proposed K-DGP algorithm. The scalability and efficiency of the proposed approach are further demonstrated by online dynamic environment estimation using WSNs.

CLIP (Contrastive Language-Image Pretraining) has become a popular choice for various downstream tasks. However, recent studies have questioned its ability to represent compositional concepts effectively. These works suggest that CLIP often acts like a bag-of-words (BoW) model, interpreting images and text as sets of individual concepts without grasping the structural relationships. In particular, CLIP struggles to correctly bind attributes to their corresponding objects when multiple objects are present in an image or text. In this work, we investigate why CLIP exhibits this BoW-like behavior. We find that the correct attribute-object binding information is already present in individual text and image modalities. Instead, the issue lies in the cross-modal alignment, which relies on cosine similarity. To address this, we propose Linear Attribute Binding CLIP or LABCLIP. It applies a linear transformation to text embeddings before computing cosine similarity. This approach significantly improves CLIP's ability to bind attributes to correct objects, thereby enhancing its compositional understanding. The code is available at https://github.com/kdariina/CLIP-not-BoW-unimodally.

This paper introduces a learning-based visual planner for agile drone flight in cluttered environments. The proposed planner generates collision-free waypoints in milliseconds, enabling drones to perform agile maneuvers in complex environments without building separate perception, mapping, and planning modules. Learning-based methods, such as behavior cloning (BC) and reinforcement learning (RL), demonstrate promising performance in visual navigation but still face inherent limitations. BC is susceptible to compounding errors due to limited expert imitation, while RL struggles with reward function design and sample inefficiency. To address these limitations, this paper proposes an inverse reinforcement learning (IRL)-based framework for high-speed visual navigation. By leveraging IRL, it is possible to reduce the number of interactions with simulation environments and improve capability to deal with high-dimensional spaces while preserving the robustness of RL policies. A motion primitive-based path planning algorithm collects an expert dataset with privileged map data from diverse environments, ensuring comprehensive scenario coverage. By leveraging both the acquired expert and learner dataset gathered from the agent's interactions with the simulation environments, a robust reward function and policy are learned across diverse states. While the proposed method is trained in a simulation environment only, it can be directly applied to real-world scenarios without additional training or tuning. The performance of the proposed method is validated in both simulation and real-world environments, including forests and various structures. The trained policy achieves an average speed of 7 m/s and a maximum speed of 8.8 m/s in real flight experiments. To the best of our knowledge, this is the first work to successfully apply an IRL framework for high-speed visual navigation of drones., Comment: 18 pages, 11 figures, 58 references, and appendix is included

Designing Transformer architectures with the optimal layer normalization (LN) strategy that ensures large-scale training stability and expedite convergence has remained elusive, even in this era of large language models (LLMs). To this end, we present a comprehensive analytical foundation for understanding how different LN strategies influence training dynamics in large-scale Transformer training. Until recently, Pre-LN and Post-LN have long dominated standard practices despite their limitations in large-scale training. However, several open-source large-scale models have recently begun silently adopting a third strategy without much explanation. This strategy places layer normalization (LN) peripherally around sublayers, a design we term Peri-LN. While Peri-LN has demonstrated promising empirical performance, its precise mechanisms and benefits remain almost unexplored. Our in-depth analysis shows that Peri-LN strikes an ideal balance in variance growth -- unlike Pre-LN and Post-LN, which are prone to vanishing gradients and ``massive activations.'' To validate our theoretical insight, we conduct large-scale experiments on Transformers up to 3.2B parameters, showing that Peri-LN consistently achieves more balanced variance growth, steadier gradient flow, and convergence stability. Our results suggest that Peri-LN warrants broader consideration for large-scale Transformer architectures, providing renewed insights into the optimal placement and application of LN., Comment: Preprint

Plasticity loss, a critical challenge in neural network training, limits a model's ability to adapt to new tasks or shifts in data distribution. This paper introduces AID (Activation by Interval-wise Dropout), a novel method inspired by Dropout, designed to address plasticity loss. Unlike Dropout, AID generates subnetworks by applying Dropout with different probabilities on each preactivation interval. Theoretical analysis reveals that AID regularizes the network, promoting behavior analogous to that of deep linear networks, which do not suffer from plasticity loss. We validate the effectiveness of AID in maintaining plasticity across various benchmarks, including continual learning tasks on standard image classification datasets such as CIFAR10, CIFAR100, and TinyImageNet. Furthermore, we show that AID enhances reinforcement learning performance in the Arcade Learning Environment benchmark.

Despite the significant advances in neural machine translation, performance remains subpar for low-resource language pairs. Ensembling multiple systems is a widely adopted technique to enhance performance, often accomplished by combining probability distributions. However, the previous approaches face the challenge of high computational costs for training multiple models. Furthermore, for black-box models, averaging token-level probabilities at each decoding step is not feasible. To address the problems of multi-model ensemble methods, we present a pivot-based single model ensemble. The proposed strategy consists of two steps: pivot-based candidate generation and post-hoc aggregation. In the first step, we generate candidates through pivot translation. This can be achieved with only a single model and facilitates knowledge transfer from high-resource pivot languages, resulting in candidates that are not only diverse but also more accurate. Next, in the aggregation step, we select k high-quality candidates from the generated candidates and merge them to generate a final translation that outperforms the existing candidates. Our experimental results show that our method produces translations of superior quality by leveraging candidates from pivot translation to capture the subtle nuances of the source sentence.

Ferromagnetism (FM) and superconductivity (SC) are two of the most famous macroscopic quantum phenomena. However, nature normally does not allow SC and FM to coexist without significant degradation. Here, we introduce the first fully iron-based SC/FM heterostructures, composed of Fe(Te,Se) and Fe3GeTe2, and show that in this platform strong FM and high-temperature SC robustly coexist. We subsequently discover that chemical proximity effect from neighboring layers can universally drive the otherwise non-superconducting FeTe films into a SC state. This suggests that the ground state of FeTe is so close to the SC state that it could be driven in and out of the SC state with various other perturbations. Altogether, this shows that Fe-Te-based heterostructures provide a unique opportunity to manipulate magnetism, superconductivity and topological physics, paving the way toward new superconducting technologies.

$\chi$-separation is an advanced quantitative susceptibility mapping (QSM) method that is designed to generate paramagnetic ($\chi_{para}$) and diamagnetic ($|\chi_{dia}|$) susceptibility maps, reflecting the distribution of iron and myelin in the brain. However, vessels have shown artifacts, interfering with the accurate quantification of iron and myelin in applications. To address this challenge, a new vessel segmentation method for $\chi$-separation is developed. The method comprises three steps: 1) Seed generation from $\textit{R}_2^*$ and the product of $\chi_{para}$ and $|\chi_{dia}|$ maps; 2) Region growing, guided by vessel geometry, creating a vessel mask; 3) Refinement of the vessel mask by excluding non-vessel structures. The performance of the method was compared to conventional vessel segmentation methods both qualitatively and quantitatively. To demonstrate the utility of the method, it was tested in two applications: quantitative evaluation of a neural network-based $\chi$-separation reconstruction method ($\chi$-sepnet-$\textit{R}_2^*$) and population-averaged region of interest (ROI) analysis. The proposed method demonstrates superior performance to the conventional vessel segmentation methods, effectively excluding the non-vessel structures, achieving the highest Dice score coefficient. For the applications, applying vessel masks report notable improvements for the quantitative evaluation of $\chi$-sepnet-$\textit{R}_2^*$ and statistically significant differences in population-averaged ROI analysis. These applications suggest excluding vessels when analyzing the $\chi$-separation maps provide more accurate evaluations. The proposed method has the potential to facilitate various applications, offering reliable analysis through the generation of a high-quality vessel mask.

Music is a deeply personal experience and our aim is to enhance this with a fully-automated pipeline for personalized music video generation. Our work allows listeners to not just be consumers but co-creators in the music video generation process by creating personalized, consistent and context-driven visuals based on lyrics, rhythm and emotion in the music. The pipeline combines multimodal translation and generation techniques and utilizes low-rank adaptation on listeners' images to create immersive music videos that reflect both the music and the individual. To ensure the ethical use of users' identity, we also introduce CHARCHA (patent pending), a facial identity verification protocol that protects people against unauthorized use of their face while at the same time collecting authorized images from users for personalizing their videos. This paper thus provides a secure and innovative framework for creating deeply personalized music videos., Comment: NeurIPS 2024 Creative AI Track

Accurate time synchronization between heterogeneous sensors is crucial for ensuring robust state estimation in multi-sensor fusion systems. Sensor delays often cause discrepancies between the actual time when the event was captured and the time of sensor measurement, leading to temporal misalignment (time offset) between sensor measurement streams. In this paper, we propose an extended Kalman filter (EKF)-based radar-inertial odometry (RIO) framework that estimates the time offset online. The radar ego-velocity measurement model, estimated from a single radar scan, is formulated to include the time offset for the update. By leveraging temporal calibration, the proposed RIO enables accurate propagation and measurement updates based on a common time stream. Experiments on multiple datasets demonstrated the accurate time offset estimation of the proposed method and its impact on RIO performance, validating the importance of sensor time synchronization. Our implementation of the EKF-RIO with online temporal calibration is available at https://github.com/spearwin/EKF-RIO-TC., Comment: 9 pages, 4 figures, 4 tables

Ensuring fairness in medical image segmentation is critical due to biases in imbalanced clinical data acquisition caused by demographic attributes (e.g., age, sex, race) and clinical factors (e.g., disease severity). To address these challenges, we introduce Distribution-aware Mixture of Experts (dMoE), inspired by optimal control theory. We provide a comprehensive analysis of its underlying mechanisms and clarify dMoE's role in adapting to heterogeneous distributions in medical image segmentation. Furthermore, we integrate dMoE into multiple network architectures, demonstrating its broad applicability across diverse medical image analysis tasks. By incorporating demographic and clinical factors, dMoE achieves state-of-the-art performance on two 2D benchmark datasets and a 3D in-house dataset. Our results highlight the effectiveness of dMoE in mitigating biases from imbalanced distributions, offering a promising approach to bridging control theory and medical image segmentation within fairness learning paradigms. The source code will be made available., Comment: 12 pages, 3 figures, 9 tables

Recent advancements in machine learning have significantly improved speech recognition, but recognizing speech from non-fluent or accented speakers remains a challenge. Previous efforts, relying on rule-based pronunciation patterns, have struggled to fully capture non-native errors. We propose two data-driven approaches using speech corpora to automatically detect mispronunciation patterns. By aligning non-native phones with their native counterparts using attention maps, we achieved a 5.7% improvement in speech recognition on native English datasets and a 12.8% improvement for non-native English speakers, particularly Korean speakers. Our method offers practical advancements for robust Automatic Speech Recognition (ASR) systems particularly for situations where prior linguistic knowledge is not applicable., Comment: Accepted to ICASSP 2025

Multimodal large language models (MLLMs) have shown promising capabilities but struggle under distribution shifts, where evaluation data differ from instruction tuning distributions. Although previous works have provided empirical evaluations, we argue that establishing a formal framework that can characterize and quantify the risk of MLLMs is necessary to ensure the safe and reliable application of MLLMs in the real world. By taking an information-theoretic perspective, we propose the first theoretical framework that enables the quantification of the maximum risk of MLLMs under distribution shifts. Central to our framework is the introduction of Effective Mutual Information (EMI), a principled metric that quantifies the relevance between input queries and model responses. We derive an upper bound for the EMI difference between in-distribution (ID) and out-of-distribution (OOD) data, connecting it to visual and textual distributional discrepancies. Extensive experiments on real benchmark datasets, spanning 61 shift scenarios empirically validate our theoretical insights.

We present new multi-wavelength observations of two ultraluminous X-ray sources (ULXs) hosted by globular clusters (GCs) in the giant elliptical NGC 1399, focusing on CXO J0338318-352604 (GCU7), only the second GC ULX known to have luminous optical emission lines. Notably, only NII and OIII emission is observed in the optical spectra, suggesting H-poor material. Previous work suggested the possibility that the properties of GCU7 could be explained by the tidal disruption of a horizontal branch star by an intermediate-mass black hole. We use new data to show that the lack of evolution in the X-ray or optical properties of the source over the last 20 years rules out this scenario. Instead, we use CLOUDY simulations to demonstrate that the optical emission lines are consistent with an outflow from an ultra-compact X-ray binary where a compact object - likely a neutron star (NS) - is accreting above the Eddington limit from a helium white dwarf (He WD). This binary would have dynamically formed from a direct collision between a NS and a red giant, or else via an exchange interaction. The ULX is predicted to evolve to lower mass transfer rates over time and eventually become a doppelganger to the well-studied ultra-compact X-ray binaries in Galactic GCs such as 4U 1820-30. These results show the utility of using extragalactic GCs to study short-lived phases in dynamical binary evolution that occur too rarely to be observed in Galactic clusters., Comment: 11 pages, 9 figures, 4 tables. Accepted for publication in MNRAS