Multimedia
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
All of arXiv
Tuesday 15 September
Emergency vehicle detection in autonomous driving is a safety-critical perception task that demands robustness under diverse and adverse real-world conditions. Existing approaches rely on a single modality, either audio or video, which leads to systematic failure when that modality is degraded: microphone-based systems fail in noisy urban environments, and camera-based systems fail at night or under occlusion. This report presents AVNet, a multimodal audio-visual transformer that classifies emergency vehicles (ambulance, fire engine, police car) and road background using both audio and video, while gracefully handling the absence of either modality at inference time. AVNet introduces three key contributions: (1) a temporally aligned cross-modal fusion module that performs second-level cross-attention between audio spectrogram tokens and video frame tokens, exploiting their exact temporal correspondence without any learned alignment mechanism; (2) learned null embeddings that substitute for missing modality tokens, enabling a single unified model to operate in audio-only, video-only, or joint audio-visual mode without retraining; and (3) a knowledge distillation training strategy in which specialist unimodal teacher models transfer inter-class dark knowledge into the multimodal student fusion branch via soft probability targets. Evaluated on 281 clips from the Google AudioSet dataset, AVNet achieves 66.6% overall accuracy in audio-visual mode, outperforming the audio-only branch by +10.4% and the video-only branch by +15.0%. The largest per-class gain is observed for the hardest class, Ambulance, where fusion achieves +29.5% over either unimodal branch alone, demonstrating that the two modalities provide complementary information that the aligned cross attention mechanism successfully exploits.
General Relativity and Quantum Cosmology
Bridging Between Statistical Mechanics and Black Hole Evolution: Theoretical Formalism
Black holes in the Universe span nearly ten orders of magnitude in mass over a large cosmic timescale, dating back to at least the Universe's early history, when it was only a few hundred million years old. The formation and evolution of these objects remain a mystery because no direct probe can trace each black hole across the full mass range and cosmic time. This work shows, for the first time, a statistical mechanical description of black hole evolution. I show that though each black hole and its evolution are governed by stochastic processes, one can make a macroscopic description of the distribution function of black holes in the Universe, and its evolution over the entire mass range and cosmic time can be expressed in terms of the Kramers-Moyal expansion. This bridging between statistical mechanics and black hole evolution in terms of the Kramers-Moyal expansion enables the discovery of the underlying physical processes that play a role in the evolution of black holes. In the future, the application of this technique to data accessible from different messengers, such as gravitational waves and electromagnetic waves, which probe black holes in the Universe, can lead to a data-driven understanding of the underlying physical processes by this statistical mechanics technique despite the ignorance of the underlying microscopic stochastic processes.
Read the full abstract
Combinatorics
Billiard Orbits in Young Diagrams: Medial Links, Bicycle Spaces, and Domino Tilings
We study diagonal billiard trajectories inside the Young diagram of an integer partition $\lambda$. A trajectory has slope $\pm 1$, passes straight through sides shared by adjacent cells, and reflects from the exterior boundary until it closes. Let $\sigma(\lambda)$ be the number of closed orbits. This extends the mirror-curve model of Chokwe sona sand drawings studied by Gerdes from rectangular grids to arbitrary Young diagrams. Let $G_\lambda$ be the cell-adjacency graph of $\lambda$, with its natural planar embedding. We identify the billiard orbits with the components of the medial link of $G_\lambda$, and deduce that $\sigma(\lambda) = 1 + \dim \mathcal{B}(G_\lambda) = \mathrm{nullity}\, L(G_\lambda)$ over $\mathbb{F}_2$, where $\mathcal{B}$ is the binary bicycle space and $L$ the mod-2 Laplacian. Writing $\lambda^\square$ for the diagram obtained by deleting the first row and column of $\lambda$, we further prove $\sigma(\lambda) = 1 + \mathrm{nullity}_{\mathbb{F}_2} A(G_{\lambda^\square})$. For rectangles this recovers Gerdes' formula $\sigma(n^m) = \gcd(m,n)$ via identities for Fibonacci polynomials over $\mathbb{F}_2$, and in general it gives the characterization: $\sigma(\lambda) = 1$ if and only if $\lambda^\square$ has an odd number of domino tilings. Using the checkerboard bipartition of $\lambda^\square$, we decompose $\sigma(\lambda) - 1$ into a color-imbalance term, related to the BG-rank of Berkovich-Garvan, and an even rank-deficiency term. This yields parity restrictions and lower bounds for the orbit number, and shows that for any fixed $d$, asymptotically all partitions have more than $d$ orbits. We also prove that $\sigma(\lambda)$ is at most the Durfee length of $\lambda$, determine $\sigma(n, n-1, \ldots, 1) = \lceil n/2 \rceil$ for staircase partitions, and show that the adjacency-nullity formula is independent of the ground field.
Read the full abstract
Computation and Language
Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data
Continued pretraining (CPT) with data augmentation such as paraphrasing can store inside a large language model (LLM) the knowledge of a small source corpus. The stored knowledge, however, is not always retrieved correctly. We study the eliciting side rather than the storing side: we use preference optimization, which learns from pairs of a preferred (chosen) and a dispreferred (rejected) response, so that the model elicits its stored knowledge more accurately. One proposed approach takes the model's own erroneous response as rejected and the gold answer as chosen, so as to suppress the error. When the target knowledge is partially known, however, most of these rejected responses are factually correct. Using direct preference optimization (DPO) then pushes down rejected responses that contain correct knowledge and differ from the chosen answer only in style, such as length and wording. We propose style-debiased DPO (SD-DPO), which scores whether the rejected response of each pair is factually correct, inverts the preference of such pairs, and weights them so that the learning signal due to differences in style cancels out as a whole. We first test whether, on top of EntiGraph, a representative storing-side method that runs CPT on text synthesized from the corpus, our method adds accuracy efficiently. On QuALITY, the reading-comprehension QA benchmark on which EntiGraph was evaluated, SD-DPO exceeds a baseline we CPT on EntiGraph's synthetic data from the same base model and evaluate with the same procedure. The training tokens this requires are a few dozen times fewer than the additional CPT needed for the same gain. For knowledge updating, the main goal of this work, we use AToKE, a knowledge-editing benchmark for facts that change over time. There, SD-DPO reaches an overall accuracy of 0.982 and answers with the new or the old fact according to the queried period.
Read the full abstract
Distributed Computing
XMPIaaS: Towards Cloud Native MPI via Cooperative Process Migration
Message Passing Interface (MPI) has been the dominant programming model for High Performance Computing (HPC) for three decades, and as HPC workloads increasingly migrate to cloud infrastructure for scalability and cost efficiency, MPI applications must contend with an execution environment fundamentally unlike traditional supercomputers: ephemeral resources, dynamic pricing and preemptable instances. In such a volatile setting, the ability to relocate running MPI processes between nodes without restarting the job is a necessity for cost-effective, resilient execution. Existing approaches either require restarting the entire job from a global checkpoint, or transparently intercepting the full MPI stack at prohibitive complexity. To address these challenges, we propose \name, a cooperative migration system for MPI that enables selective process group migration on-the-fly. When a cloud instance is scheduled for preemption, only the affected ranks are relocated while the remaining processes briefly quiesce and resume in place, avoiding the cost of a full-job checkpoint. \name tackles this through a cooperative protocol between the MPI process management runtime and rank processes. We expose an XMPI\_quiesce interface built atop the MPI Sessions API that allows applications to mark safe migration points, and we extend the Hydra process manager to orchestrate the full migration lifecycle: rank quiescence, CRIU checkpoint/restore, proxy relaunch on the target node, and seamless rank reconnection. We evaluate and show that the cooperative quiesce phase accounts for less than 1.4% of total migration downtime, and that this downtime is governed by the migrating node's rank count alone, independent of job size, and the instrumentation introduces no measurable overhead during normal execution.
Read the full abstract
Materials Science
Orbital-resolved superexchange and topological magnon bands in MXene Fe$_2$C
Magnetic MXenes are promising candidates for future spintronics due to their intriguing properties. Nevertheless, the topological properties of magnon bands and superexchange mechanism remain relatively underexplored. In this work, we have calculated the spin wave dispersions for MXene Fe$_2$C using the linear spin wave method, with the exchange coupling parameters obtained from first-principles calculations. Owing to the staggered stacking of two Fe sub-lattices, the interlayer exchange coupling lifts the degeneracy of the ferromagnetic magnon modes. A Dirac point is identified in the magnon bands at the $K$ point. The topological properties of magnon bands, including Berry curvature, valley Chern number and edge states, are further computed by means of a two-band model. We also derive an effective Hamiltonian to explain the magnonic topology, which is protected by the $C_{3v}$ rotational symmetry. To understand the microscopic origin of the exchange couplings that govern the magnon bands, we then construct a refined model integrating perturbation theory and the tight-binding approach. The ferromagnetic superexchange coupling is mediated by the virtual hopping between the d orbitals of two distinct Fe sites via a pair of orthogonal p orbitals at the bridging C site. In detail, the intralayer exchange coupling is governed by the in-plane $p_x$ and $p_y$ orbitals, while the out-of-plane $p_z$ orbital is responsible for the interlayer exchange coupling. Our results establish a direct link between the orbital-resolved anisotropic superexchange and topological properties of the magnon bands in magnetic MXene Fe$_2$C, providing theoretical guidance for future spintronics applications.
Read the full abstract
High Energy Physics (Phenomenology)
Dark Matter Inelastic Scattering with Nuclei for Direct Detection
We investigate the nuclear responses for the WIMP-nucleus scattering in the dark matter direct detection with particular emphasis on the inelastic channel for the $^{129}$Xe and $^{131}$Xe isotopes. Our generalization incorporates both the elastic and inelastic scattering channels. With multipole expansion of the effective operators, the angular momentum, parity and time-reversal selection rules can effectively determine the allowed transitions. Instead of the nuclear shell model, we use the state-of-the-art relativistic configuration-interaction density functional theory, which is more suitable for heavy nuclei such as xenon isotopes, to calculate the nuclear response functions. For certain interaction operators, the inelastic contribution can be comparable as its elastic counterpart and some can even dominate by up to three orders of magnitude. Additionally, the higher excited nuclear states can have comparable signal rate as the first excited states. We compare our results with the nuclear shell model calculation. The differences would have significant effects for interpreting the dark matter direct detection searches.
Read the full abstract
Machine Learning
FlowATC: Aircraft Trajectory Prediction via Flow Matching
Building accurate decision-support tools for next-generation air traffic control requires robust trajectory prediction models. We present a flow-matching architecture trained exclusively on historical aircraft trajectories, with no route labels or chart supervision. Trained on 1.15 million Automatic Dependent Surveillance-Broadcast trajectory windows collected over the San Francisco Bay Area, the model generates aircraft trajectory distributions that closely match historical traffic, reproducing known airspace structure around San Francisco Airport such as the shape of SFO's published NIITE FOUR departure procedure. Our model is trained directly on the native, irregular ADS-B sampling interval. Trajectory prediction is cast as sequence inpainting using a block-causal Transformer that denoises future state tokens conditioned on the observed history using Conditional Flow Matching or Denoising Diffusion Probabilistic Models. We compare our architecture against constant-velocity, deterministic-Long Short Term Memory, and Conditional Variational Autoencoders baselines. At matched parameter count, CFM outperforms DDPM by 11-26% in minADE@20, and both generative objectives surpass the CVAE baseline by 31-41%. We further show that the error degrades gracefully with prediction horizon, and the architecture remains effective when retrained on temporally decimated feeds. Lastly, we sample $K$ independent completions, yielding spatial probabilistic occupancy estimates that can serve as input to downstream conflict-risk estimation.
Read the full abstract
Chemical Physics
QALPA: Property-guided diffusion modeling for efficient exploration of chemical spaces of flexible molecules
Exploring the chemical space of flexible molecules remains challenging because the vast number of possible compounds and conformations, together with the increasing cost and limited generalization of 3D generative models for larger and more complex molecules, restrict access to unexplored chemistry. Here, we introduce QALPA ("Quantum-Aware Learning for Property-space Augmentation"), a property-guided generative framework that combines an E(3)-equivariant diffusion model with active learning and efficient quantum-mechanical (QM) methods to iteratively explore targeted QM property manifolds. By coupling generation with physics-based evaluation, QALPA improves molecular sampling and model reliability in sparsely populated regions of chemical space. Our results show that training on complementary QM datasets spanning both small (QM7-X) and large (Aquamarine) drug-like compounds enables accurate molecular generation across a broad size range, improving transferability beyond the training distribution for complex property manifolds involving both extensive and intensive properties. As a proof of concept, QALPA coupled with the machine learning-augmented tight-binding method EquiDTB efficiently augments alloQM, a QM dataset introduced in this work, comprising 6,253 conformers of allosteric drug molecules, by populating sparse regions of the property landscape defined by the many-body dispersion energy and HOMO-LUMO energy gap. These results demonstrate that the integration of generative AI with efficient ML/QM methods offers a practical pathway toward augmenting sparse QM datasets and sustainably expanding the exploration of chemical space for molecular discovery.
Read the full abstract
Materials Science
Symbolic Ensemble Learning Enables Discovery of Fast Accurate Physics-Based Interatomic Potentials
Machine learning has transformed materials simulation by delivering force fields with ab initio accuracy, yet bridging the gap between high-dimensional regression and physical interpretability remains a grand challenge. Conventional analytical potentials offer transparency but often fail to capture the complexity of far-from-ground state regimes. Here, we introduce a hybrid symbolic-neural framework that unifies the interpretability of the Embedded Atom Method (EAM) with the adaptability of data-driven learning. Using Equation Learner Neural Networks (EqNNs) trained on density functional theory (DFT) data, we obtain interpretable models for aluminum through three distinct training protocols: random initialization trained via Monte Carlo Tree Search (MCTS) and gradient descent, and two transfer-learning strategies initialized from a copper potential - one employing MCTS followed by gradient descent, and the other using gradient descent only. We find that while all three resulting symbolic models achieve sub-10 meV/atom accuracy, they occupy distinct local minima in the functional landscape, exhibiting complementary trade-offs across phonon dispersion, surface energetics, and elastic response. By integrating these diverse functional forms through a weighted symbolic ensemble, we derive a composite potential that surpasses the fidelity of its constituent models. The resulting ensemble effectively mitigates individual biases, delivering superior consistency with DFT benchmarks across equation-of-state curvature, phonon spectra, and melting dynamics. This approach demonstrates that combining transfer learning with ensemble symbolic regression yields compact, transparent potentials capable of robust prediction across equilibrium and non-equilibrium states.
Read the full abstract
Numerical Analysis
Structure-Informed Data-Driven Reduced-Order Modeling of Scalar Hyperbolic Conservation Laws via Kinetic Defect Measure
Reduced-order modeling of transport-dominated systems remains challenging because moving fronts and shocks are poorly represented by low-dimensional linear subspaces. We develop a structure-informed data-driven reduced-order model(ROM) for scalar hyperbolic conservation laws based on the kinetic defect formulation. This formulation separates the nonlinear dynamics into known characteristic transport and a kinetic entropy defect localized on the shock manifold. We exploit this structure by first removing the known transport from the solution snapshots. We then extract and register the remaining defect-driven dynamics in a shock-attached coordinate system. Separate ROMs are used to evolve the shock geometry and the registered defect-driven source. During prediction, the predicted shock geometry is used to inverse-register the learned defect-driven source, which advances the kinetic state and recovers the physical solution. Numerical examples in one and two spatial dimensions demonstrate accurate reconstruction and prediction of nonlinear transport with shocks, including evolution beyond the training interval, while accurately capturing the mass and entropy-dissipation behavior of the reference solution.
Read the full abstract
Optimization and Control
Master Equations for Mean Field Game of Controls: A Unification of Weak Solution Notions
In this manuscript, we study the master equation for mean field game of controls, assuming only that the data are Lipschitz continuous in the measure variable. Accordingly, we propose a weaker notion of solution called weak solutions for the master equation. We establish the global well-posedness of the master equation for such solution under the Lasry-Lions monotonicity and displacement $\lambda$-monotonicity conditions, respectively. The arguments rely on the analysis of the associated Pontryagin forward-backward stochastic differential equation system, especially the stability in the measure variable. Finally, we review several existing notions of non-smooth solution from the literature, namely good solutions, weak viscosity solutions, Lipschitz solutions, monotone solutions, and examine their relationship with our weak solution. We show that under appropriate assumptions all of them are equivalent by their definitions, and thus our manuscript provides a unification of weak solution notions for the master equations derived from mean field game of controls.
Read the full abstract
Systems and Control
On Delay-robustness of Extremum Seeking of Nonlinear Static Maps with Small Disturbance
Extremum seeking (ES) is a real-time optimization strategy, thus transmission delays in the feedback loop of ES have big impact on its stability. How big delay that ES control systems are able to withstand? This paper provides a potential answer to this problem. We focus on gradient-based ES for nonlinear static maps subject to known constant delays plus a small time-varying delay uncertainty. We also consider the measurement to be subject to a small disturbance. Different from a majority of existing literature addressing quadratic maps with delays by predictor feedback, this paper deals with a wider class of non-quadratic maps without any predictor or observer for delay compensation. Dither signals in modulation and demodulation are carefully designed to handle constant delays and time-varying delay uncertainties. When the nonlinear map is unknown, we offer a rigorously analytical framework of ES convergence and delay-robustness. When some a prior knowledge of nonlinear maps is available, we are able to provide a quantitative estimation on upper bounds of time delay and dither periods to keep ES systems to remain stable. A suitable choice of ES parameters guarantees practical stability for any large known constant delay.
Read the full abstract
Game Theory
Auction Design with ROI-Constrained Bidders: Truthfulness and Revenue Maximization
The return-on-investment (ROI) constraint is central to many auctions, particularly in online advertising, where a bidder is unwilling to pay more than a fixed fraction of the value obtained. We study truthful and revenue-maximizing auctions for ROI-constrained bidders. We first characterize truthful auctions when both valuations and ROI constraints are private, showing that the allocation rule uniquely determines the payment rule. Building on this characterization, for multiple bidders we introduce $\sigma$-increment mechanisms that resemble Myerson's optimal mechanism~\cite{journals/mor/Myerson81}; as $\sigma$ vanishes, these mechanisms become asymptotically optimal among deterministic truthful mechanisms, and their revenue approaches at least a $1/\bar r$ fraction of the optimal expected revenue over all truthful mechanisms, where $\bar r$ is the largest possible ROI constraint. In the single-bidder setting, we prove that every truthful auction can be replaced by a convex pricing function with weakly higher payments for every type, and we derive the optimal pricing functions when either the valuation or the ROI constraint is public.
Read the full abstract
Atmospheric and Oceanic Physics
A common warming-dependent decline emerges from divergent projections of tropical cyclone frequency
How global tropical cyclone frequency will respond to climate warming remains uncertain, with projections spanning both increases and decreases. Here we use an environment-dependent probabilistic tropical cyclone model driven by 14 CMIP6 models under intermediate- and high-emissions scenarios to identify a common response across these divergent projections. Initially weak global changes evolve into a clearer late-century decline, driven by increasingly negative changes in the Southern Hemisphere and diminishing positive changes in the Northern Hemisphere. The long-term decline is stronger under higher emissions. Counterfactual decomposition shows that this stronger decline cannot be explained by the sum of the individual predictor contributions, which largely offset one another, but is instead dominated by negative non-additive joint effects among absolute vorticity, vertical wind shear, relative humidity and potential intensity. Across 28 model-scenario projections, the global tropical cyclone frequency trend scales linearly with the level of global warming. Applying the fitted warming-frequency relationship at 2 degree C of warming relative to 1980-2014 narrows the 95% confidence interval for the projected frequency change from [-21.9%, +10.3%] to [-9.1%, -2.5%]. These results reconcile divergent projections through a common warming-dependent decline and identify the joint reorganization of large-scale environmental conditions as its primary driver.
Read the full abstract
Quantum Physics
Truncated hybrid tensor networks for distributed quantum simulation
Simulation of quantum many-body systems is a principal application of quantum computing, but available devices remain limited by the number of qubits and cannot accommodate systems of the desired size. One approach is to host a large evolution across several modest distributed systems that exchange classical information alone. Current protocols such as circuit knitting incur a quasi-probability sampling cost that grows exponentially with the number of remote gates across the cut, even when physical correlations across the cut are actually bounded. In this work, we present a truncated hybrid tensor network (THTN) framework in which a remote two-body gate is applied as a sum of local unitaries on the subsystems, linked by a classical connecting tensor, and an interface truncation retains Schmidt modes across the cut. Remote gates between the same subsystems can be merged on one connector, so non-one-dimensional models, such as layered partitions with strong intra-layer and weaker interlayer couplings, may be cast onto a one-dimensional cut. The retained non-negative Schmidt coefficients also define a sampling rule for local observables. We validate this distributed protocol by classical simulation against time-evolving block decimation (TEBD) at the same bond dimension. The truncated dynamics track the TEBD references on chains and ladders, with the clearest gain on a layered model.
Read the full abstract
Artificial Intelligence
AquiLLM: Evaluating Faithfulness in Open-Weight RAG-LLM Systems for Scientific Research
Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrieval-augmented generation (RAG) systems that provide natural language access to scientific knowledge and research workflows. Researchers are exploring the viability of these systems as natural language interfaces for document search and for generating analysis code and pipeline components. At the same time, concerns about data privacy and control over research infrastructure have motivated interest in open-weight models and open-source deployments hosted within research institutions. In astronomy, this development follows a long history of computational infrastructure development, from archival databases and Structured Query Language (SQL)-based systems to large language model (LLM)-assisted research tools. This paper presents a domain-expert evaluation of faithfulness for AquiLLM, an open-weight, offline RAG-LLM platform designed to support scientific research groups in the use and preservation of tacit and formal knowledge. We define faithfulness as the extent to which generated responses remain grounded in retrieved scientific context without unsupported claims or omissions. We report results from an astronomy case study evaluating AquiLLM across retrieval and scientific analysis tasks. AquiLLM performs most reliably on explicit retrieval-oriented questions grounded in the RAG collection, while faithfulness degrades for queries requiring synthesis or ambiguity resolution. These results highlight both the promise and limitations of open-weight RAG-LLM systems for scientific research and demonstrate the importance of domain-expert evaluation beyond standard benchmark leaderboards.
Read the full abstract
Human-Computer Interaction
Beyond Gestures: Estimating Full Hand Pose and Contact Forces from Wrist-Worn Pressure Sensor Array
Capturing hand motion and interaction forces is critical for interactive computing, VR, and high-fidelity tactile demonstrations for robot learning. We introduce a wrist-worn pressure-sensing wristband that recovers continuous full-hand pose and distributed contact force on a single wearable. The system consists of flexible capacitive sensor arrays around the wrist, which require no electrical skin contact, and a recurrent network that maps the resulting pressure signal to hand state. Our key insight is that muscle contraction and tendon displacement produce pressure patterns, which correlate strongly with hand pose and interaction force. To validate this, we collect synchronized recordings of wrist pressure, optical motion-capture hand pose, and tactile-glove interaction force, covering isolated finger motion, fingertip-force stress tests, and natural hand-object manipulation. On isolated single-user motion the wristband attains $4.6^\circ$ mean finger-joint MAE, and across four users manipulating everyday objects it estimates per-finger contact force at $R^2=0.57$, which an external pose signal brings up to $0.75$. We see the wristband as one node in a constellation of everyday wearables – e.g. paired with an egocentric camera – adding the contact force that vision cannot observe and taking over when the hand is occluded.
Read the full abstract
Computation and Language
Competence-Preserving Resume Perturbations Expose Presentation Sensitivity in LLM Screening
Resume screeners must infer job-relevant competence from resumes whose presentation can vary substantially in wording, structure, stylistic polish, and document extraction quality. Ideally, such surface variation should not change decisions when the underlying qualification evidence is unchanged. We introduce a controlled audit of this property, constructing occupation-grounded candidate profiles at controlled competence levels and rendering each profile into multiple resume presentations. A deterministic validation gate excludes variants that alter the underlying evidence before scoring. Across six open instruction-tuned LLM conditions, we find a clear disconnect between screening validity and presentation stability. Llama-3.1-8B with its native chat template achieves the strongest validity ($0.781$) yet reverses $29.6\%$ of matched pairwise decisions under competence-preserving presentation changes; Mistral-7B-v0.3 reaches validity $0.644$ with a $41.4\%$ flip rate. Native chat formatting improves validity for several chat-tuned models but does not remove this instability. These results show that resume-screening evaluations should assess not only whether a system identifies stronger candidates, but also whether those decisions remain stable when the same competence evidence is presented differently.
Read the full abstract
Analysis of PDEs
Symmetry, monotonicity, and asymptotics of singular solutions to semilinear elliptic equations
In this paper, we study singular positive solutions to the semilinear elliptic equation $$ - \Delta u = f(u) ~~~~~~ \textmd{in} ~ \Omega \setminus \Gamma, $$ where $\Omega \subset \R^n$ is a bounded or unbounded domain, and $\Gamma \subset \Omega$ is a singular closed set with zero Newtonian capacity. When $\Omega = \R^n$ and $\Gamma \subset \{ x_1 = 0 \}$, we establish the symmetry of singular solutions with respect to the hyperplane $\{ x_1 = 0 \}$ and their monotonicity in the $x_1$-direction. For the case where $\Omega \subset \R^n$ and $\Gamma$ is a smooth closed manifold of dimension $\leq n - 2$, we show the asymptotic symmetry of singular solutions with respect to the normal direction of $\Gamma$. These results significantly improve those of Chen-Lin (Duke Math. J. 1995; Ann. Scuola Norm. Sup. Pisa Cl. Sci. 2001), Li (Invent. Math. 1996) and Sciunzi (J. Math. Pures Appl. 2017). Unlike their proofs, we employ an improved version of the moving sphere method, which also simplifies the analysis and extends its applicability.
Read the full abstract
Probability
Mixing time under monotone censoring
We prove the conjecture of Ding and Mossel~\cite{DM}: the lazy random walk on the discrete cube, censored to any increasing set of fixed positive density, mixes in time $O(n\log n)$. More precisely, for every nonempty increasing set $A\subseteq\{0,1\}^n$, with $a=\mu(A)$ and $\mu$ uniform on the cube, we prove $$ t_{\mathrm{mix}}(P)\le C_a n\log(en), $$ where $C_a$ depends only on $a$. The proof uses hypercontractivity on the ambient cube to strengthen the Poincaré inequality on coordinate sections. An optimal stopping time occupation inequality for increasing sets converts the resulting local bound into a uniform bound on hitting times of large sets. An appendix by Y.~Peres improves the density dependence to $C_a=13a^{-1}\log(e/a)$, within a logarithmic factor of the conjectured $a^{-1}$ dependence.
Read the full abstract
Audio and Speech Processing
The Evolving Bottleneck in Speech Generation: Interface Co-design and Staged Alignment from CosyVoice to Qwen-Audio-3.0-TTS
Speech synthesis systems are commonly narrated as a sequence of larger models, better tokenizers, and broader data. This technical retrospective offers a different account of the CosyVoice lineage, from CosyVoice through CosyVoice 2 and CosyVoice 3 to Qwen-Audio-3.0-TTS: progress came from repeatedly relocating the system's dominant bottleneck. Across the lineage, a stable decomposition separates an autoregressive language model that plans speech from a flow-matching model that renders acoustics. What changes is the contract between them. CosyVoice establishes supervised semantic tokens as a content-aligned interface; CosyVoice 2 makes that interface causally available for streaming and removes the utterance-level speaker embedding from the language model; CosyVoice 3 improves the learnability and coverage of the interface through multitask supervision, scaling, and differentiable reward optimization; and Qwen-Audio-3.0-TTS reduces token rate, conditions its renderer on continuous language-model hidden states instead of token embeddings, and progressively aligns the coupled system. We formalize this history through four interface dimensions—representation, ownership, availability, and gradient reach—and separate within-paper evidence from cross-paper comparison. The resulting synthesis connects discrete autoregressive, continuous non-autoregressive, hybrid, and continuous autoregressive speech-generation paradigms, and yields practical principles for diagnosing and training modular speech generators.
Read the full abstract
Systems and Control
Congestion Structure and Exceedance Bounds for Locational Marginal Emissions
Locational marginal emissions (LMEs) give the sensitivity of total operating carbon emissions to nodal power demand. We show that this vector with $n$ entries has a much smaller intrinsic dimension under DC optimal power flow. Within a fixed active constraint set, the LME vector lies in the span of the uniform vector and the power transfer distribution factor rows of the binding lines. Its rank $r$ is therefore at most one more than the number of binding/congested lines. This structure makes $r$ independent scalar observations necessary and sufficient for exact recovery. Across ten systems with nonzero operating emissions, from 14 to 1,354 buses, $r$ ranges from 2 to 15. For instance, on a 300 bus system, 24 dispatch simulations recover all 300 LMEs. We also derive an emissions exceedance bound under uncertain demand. The bound separates variation while the nominal active set remains unchanged, the probability of an active set change, and estimation error. Numerical results show that its usable forecast error range depends on local active set geometry.
Read the full abstract
Chemical Physics
Discovering Kinetically Significant Reaction Mechanisms Beyond Chemical Intuition in Condensed-Phase Radiolysis
Many important chemical systems, from radiation-driven processes to condensed-phase photochemistry, involve reaction mechanisms that are so complex it is a challenge to characterize them experimentally or predict them from chemical intuition. Existing computational approaches to mechanism discovery typically assess pathway importance through thermodynamic favorability alone, which does not provide time-dependent kinetics or inform how to model spatial inhomogeneities. Here we describe an integrated workflow that discovers complex reaction mechanisms without prescribing them and connects molecular-scale reactivity to spatiotemporal observables. The workflow combines high-throughput DFT, automated reaction network construction with chemical plausibility filtering, stochastic pathway sampling to identify reactions which are likely to occur, and spatially resolved reaction-diffusion kinetics simulations with explicit tracking of species in space and time. To demonstrate the workflow on a system of high complexity, we apply it to radiolytic chemistry in an extreme ultraviolet (EUV) organic polymer thin film photoresist, where a single 92 eV photon initiates cascades of radical ions, fragments, and low-energy electrons across a nanoscale radiolytic spur. Starting from over 3,300 species and millions of candidate reactions, the workflow identifies the most likely reaction pathways and produces spatiotemporal maps that resolve product formation on femtosecond-to-nanosecond timescales across a 15.5-nm domain. The simulations predict products detected experimentally and reveal that the identity of the initially photoionized species profoundly shapes the downstream product distribution through multi-step pathways governing the balance between deprotection and crosslinking reactions. The methodology is broadly applicable to complex condensed-phase reactive systems.
Read the full abstract
Analysis of PDEs
A Gauge-Covariant Semiclassical Limit from the magnetic Hartree–Fock equation to the magnetic Vlasov–Poisson equation
We study the semiclassical limit from the magnetic Hartree–Fock equation to the magnetic Vlasov–Poisson equation in three spatial dimensions in the presence of a nonuniform, purely space-dependent magnetic field. We first establish propagation of regularity for solutions of the magnetic Vlasov–Poisson equation under exponentially weighted assumptions. Building on this result and a gauge-covariant magnetic Weyl quantization framework, we then derive explicit convergence bounds for the semiclassical limit in semiclassical Schatten norms. In particular, the estimates are formulated in terms of the magnetic field rather than a particular choice of vector potential and are therefore gauge covariant. The resulting semiclassical convergence holds for a suitable class of initial data on any fixed finite time interval.
Read the full abstract
Statistical Methodology
Causal Path Analysis from Perturbational and Population-Scale Single-Cell Data with Multiscale Confounding and Measurement Error
Single-cell perturbation experiments provide causal information on gene regulation, whereas population-scale single-cell studies characterize gene expression and phenotypes in human populations. We develop a framework that integrates these complementary data sources for causal path analysis. Rather than assuming that a perturbational gene network transfers directly to the target population, we use externally learned ancestral relationships to constrain the network topology and re-estimate its direct edges and effects from population data. To address latent heterogeneity and measurement error in multiscale single-cell measurements, we develop a surrogate-variable procedure operating at both the cell and subject levels, combined with errors-in-variables correction for network and outcome regressions. We establish theoretical guarantees for confounder recovery and high-dimensional estimation of network and gene-outcome effects. Simulations demonstrate the importance of jointly correcting confounding and measurement error. An application to acute myeloid leukemia identifies distinct regulatory pathways linking transcriptional regulators to blast count.
Read the full abstract
Statistics Applications
Anthropogenic Forcing, Climate Change, and the Shape of Warming: Statistical Inference for Distributional Cointegration
Anthropogenic forcing components follow different long-run paths, while persistent temperature change can involve distributional changes beyond the mean. Scalar regressions aggregate these components and retain only mean temperature, obscuring how distinct forcing paths relate to persistent distributional change. We develop new testing, estimation, and inference methods for long-run relations between an integrated predictor vector and a density-valued response. These comprise a residual-based test of between-cointegration (whether predictor trends account for all stochastic trends in the response density), a fully modified least-squares estimator of predictor-specific functional responses, and simulation-based inference for interpretable projections. We apply the methods to densities of observed local temperature anomalies and anthropogenic effective radiative forcing divided into CO$_2$ and non-CO$_2$ portfolios. The test results are consistent with persistent movements in these portfolios statistically accounting for the persistent evolution of the anomaly distribution, with no additional stochastic trend detected in the residual. A joint test rejects the common-response restriction imposed by aggregating the two portfolios. The fitted CO$_2$ response mainly shifts mass toward warmer anomalies and increases central concentration, whereas the non-CO$_2$ response produces a smaller shift but greater dispersion and off-center reshaping. Positive fitted mean responses for both portfolios conceal these contrasts, demonstrating the information lost through scalar aggregation.
Read the full abstract
Hardware Architecture
ScaleLUT: A Fully-Parallel Configurable LUT-Based Accelerator for Real-Time Multi-Scale Super-Resolution
Real-time super-resolution (SR) remains challenging for edge devices because deep-learning-based methods require substantial multiply-accumulate (MAC) operations, resources, and power. Lookup-table (LUT)-based SR reduces computation by replacing convolutional inference with table queries, but existing methods still suffer from limited speed, large storage overhead, and poor scalability across upsampling factors. We present ScaleLUT, a hardware-oriented LUT design framework and fully parallel reconfigurable accelerator for real-time multi-scale SR. ScaleLUT combines a hardware-friendly YUV-domain strategy with power-of-two kernels and rotation ensemble to improve receptive-field coverage while reducing LUT dimensionality; division operations are replaced by shifts. These designs reduce memory by 18.4% over state-of-the-art LUT-based SR methods. ScaleLUT supports arbitrary input resolutions and configurable x2^n upsampling factors using a deeply pipelined, massively parallel architecture. Implemented on a Xilinx ZCU102 FPGA, it achieves real-time 4K SR at 95.3 FPS for x2 upscaling at 300 MHz. Compared with existing SR accelerators, ScaleLUT uses at least 58.6% fewer LUTs, 41.1% fewer flip-flops, zero DSPs, and 42.0% lower power, while delivering 10x and 1.2x speedups over the best CPU-based SR implementation and prior FPGA-based SR accelerators, respectively. These results demonstrate the effectiveness of joint LUT algorithm-hardware co-design for practical and energy-efficient edge SR deployment.
Read the full abstract
Quantum Physics
Exact Ionization Amplitudes for a Delta-Function Well in an Arbitrary-Strength DC Electric Field
We investigate finite-time field-induced ionization from a one-dimensional attractive delta-function well in a uniform dc electric field of arbitrary strength. Our aim is to determine the physical bound-state survival amplitude \(a_b(t)\) at any observation time without constructing the complete time-dependent propagator or wavefunction. In the gauge-equivalent Kramers–Henneberger representation, the field appears as motion of the contact point, and the resulting dynamics reduces to a closed Volterra equation. Exact endpoint-phase factorization organizes the full chronological rescattering history into a relative-time convolution hierarchy and an exact resolvent. By introducing the accumulated bound-state amplitude and reorganizing its two-time domain in relative and complementary center times, the final contact contribution becomes an explicit boundary integral. All spatial integrations are carried out analytically. The field-driven contact-free term is obtained in closed form using the Faddeeva function, while the direct and repeated-rescattering terms are expressed as explicitly evaluable time integrals. The result applies at arbitrary dc-field strength and finite time, with no weak-field expansion, rescattering truncation, or asymptotic-time approximation. It is verified through the exact field-free limit and an independent numerical solution of the original physical Volterra equation. The formulation gives an exact nonperturbative solution of a fundamental ionization model and reveals otherwise hidden analytical structure in driven quantum dynamics.
Read the full abstract
Statistical Mechanics
Unsupervised Machine Learning of the Contact Process
We investigate how unsupervised machine-learning methods can characterize the active-absorbing phase transition in the contact process in one and two spatial dimensions. Our analysis focuses on principal component analysis (PCA) and variational autoencoders (VAEs), and we show that direct applications of these methods encounter a central difficulty: contact process configurations are intrinsically positive-definite. In the PCA case, standard centering procedures fail to isolate the order parameter in the leading component. To address this, we augment the data with sign-reversed configurations, creating a balanced dataset with zero mean while preserving the density information required to describe the transition. This preprocessing allows the dominant principal component to recover the order parameter and reproduce the expected finite-size scaling near criticality. For VAEs, we find a related limitation: a fixed Gaussian prior does not provide sufficient latent regularization across the full range of control parameters and system sizes for positive-definite data. We overcome this by adopting a heteroscedastic Gaussian prior that adapts to the control parameter, leading to a substantial improvement in the finite-size scaling of reconstruction-based observables near the critical threshold. Taken together, these results highlight a key lesson: the success of machine learning in phase-transition problems does not rely on algorithmic complexity alone, but on tailoring the representation to respect the physical structure of the system, including its intrinsic constraints and symmetries.