Optimization and Control
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
All of arXiv
Thursday 10 September
We investigate mean-variance portfolio selection with an $\ell_0$-penalty to promote sparsity in asset allocations. Uncertainty in the mean return vector is incorporated through an ellipsoidal uncertainty set, yielding a robust sparse optimization framework. We characterize the structure of both local and global minimizers and exploit these properties in the risk minimization and return maximization formulations. Building on this structural insight, we develop a branch-and-bound algorithm tailored to the resulting robust sparse portfolio problems, together with a new pruning rule that can discard exponentially many candidate portfolios in a single step. Extensive computational experiments on real market data, together with comparisons against a mixed-integer second-order cone programming solver, demonstrate the effectiveness and competitiveness of the proposed approach.
Theoretical Economics
Utility-Level-Dependent Ambiguity
Experimental evidence suggests that ambiguity-sensitive choice can vary systematically with the circumstances of a decision. This paper isolates one channel within a stable preference relation: ambiguity weighting may depend on the act's certainty-equivalent level. After the standard Anscombe-Aumann calibration of consequence utility, a set of behavioral axioms yields a unique continuous family of normalized monotone capacities $\{\nu_v\}_{v\in(0,1)}$. Each nonendpoint act is evaluated by the Choquet integral associated with the capacity at its own interior certainty-equivalent level, while nonendpoint acts on the same indifference surface share the same capacity. Binary event comparisons identify local event weights at each elicited level and trace their cross-level variation, providing tests of the fixed-capacity restriction. Local uncertainty aversion is equivalent to convexity of $\nu_v$ and yields an implicit multiple-priors representation with certainty-equivalent-indexed local cores. Certainty translation invariance holds if and only if the capacity is fixed across levels, recovering the maintained nondegenerate fixed-capacity Choquet expected utility benchmark; global mixture-betweenness yields implicit additive utility, and imposing both restrictions recovers full-support subjective expected utility. The capacity schedule is a reduced-form ambiguity weighting whose variation may reflect changes in ambiguity perception, ambiguity attitude, or both.
Read the full abstract
High Energy Physics (Phenomenology)
Precise bubble wall velocity in a specific phase transition pattern in the CxSM and beyond
The bubble wall velocity is a key quantity in cosmological first-order phase transitions, with important implications for electroweak baryogenesis, gravitational wave signals, the dark matter relic density and primordial black holes formed during the phase transition. However, it is often treated as a free input in phenomenological studies, while a self-consistent determination remains challenging. In this work, taking the complex singlet extension of the Standard Model as an example, we investigate the bubble wall dynamics and velocity in a specific electroweak phase transition pattern where both the Higgs field and the coupled singlet scalar experience friction. The microscopic friction arising from particle interactions with the plasma is evaluated using Boltzmann transport equations, while the macroscopic plasma response is described through hydrodynamic analysis. By applying the steady state force balance condition, we numerically determine the bubble wall velocity for different model parameters. We show that the wall velocity is governed by the competition between the driving force from the effective potential and plasma friction, and that its variation can significantly affect the baryon asymmetry. Our study provides a quantitative investigation of bubble wall dynamics in this overlooked phase transition pattern and its implications for early Universe phenomenology.
Read the full abstract
Systems and Control
Construction of Control Lyapunov-Barrier Functions from CLF-CBF Pairs
This paper studies the construction of control Lyapunov-barrier functions (CLBFs) from a given control Lyapunov function (CLF) $V$ and control barrier function (CBF) $h$. We consider functions of the form $W=F(V,h)$ that increase with the CLF value and do not increase with the barrier value, and show that the CLBF decrease condition is completely characterized by a nonnegative scalar weight that governs the relative contributions of the CLF and CBF. Because this weight depends only on $(V,h)$, the same value must satisfy the decrease condition at all states sharing the same CLF and CBF values, which leads to a joint-level-set admissibility condition. We then construct CLBFs from admissible weights through a first-order partial differential equation (PDE) and obtain explicit multiplicative and power-type families as special cases. We further identify an integrability obstruction showing that admissibility alone does not guarantee properness. Two nonlinear examples illustrate the constructions and demonstrate safe stabilization in cases where feedback based on the original CLF violates the safety constraint.
Read the full abstract
Strongly Correlated Electrons
Unraveling the Kagome Antiferromagnetic $3J$ Model and Its Materials: An Integrated Approach
We investigate the ground-state and finite-temperature properties of the kagome antiferromagnetic Heisenberg model with three inequivalent couplings, dubbed the $3J$ model, which is designed for the candidate Dirac quantum spin liquid (QSL) material YCu$_3$(OH)$_6$Br$_2$[Br$_{1-x}$(OH)$_x$] (see, e.g., Zeng et al., 2024). Employing large-scale density-matrix renormalization group (DMRG) supplemented by neural quantum states (NQS) simulations, we identify an intermediate QSL phase between two magnetically ordered phases. We also find that this QSL is separated from the kagome spin liquid ground state at the isotropic limit. To establish a direct comparison with experiments, we compute the specific heat of the model by means of advanced exponential (XTRG) and tangent-space (tanTRG) thermal tensor-network methods. In the magnetically ordered phase, the specific heat over temperature exhibits a shoulder at a temperature that is a fraction of the coupling strength $J_{h}$, which disappears in the QSL phase. These universal behaviors are consistent with the experimentally observed specific heat in $3J$ materials for both ordered and QSL candidate samples. Our work thus connects microscopic models with experimentally measurable signatures, exemplifying an integrated approach to understanding QSL phenomena in frustrated quantum magnets~ (see Meng et al., 2026), with $3J$ materials serving as a representative case and providing a foundation for future studies.
Read the full abstract
Distributed Computing
Building py-kvcache: A Performance Characterization of External KV Caching for vLLM with NVMe SSDs
Prefix caching can reduce the time to first token (TTFT) of long-context LLM requests by reusing previously computed key-value (KV) states, but for short prefixes or fast GPUs, recomputation can be faster than loading from an external cache. We characterize this tradeoff in vLLM across GPU, CPU, and NVMe tiers using synthetic workloads, long-context benchmarks, production traces, and find that cache performance depends on transfer granularity, intermediate memory use, and when transfers enter the request schedule, not only on device bandwidth. These findings motivate py-kvcache, a vLLM KV Offload connector with asynchronous direct I/O, bounded shared staging, and scheduler-aware preloading, which starts disk reads while requests are still waiting, overlapping with compute. At 80k tokens, py-kvcache loading from disk is 2.0x faster than LMCache, with preloading contributing 1.34x. With GPU, CPU, and disk caching enabled, it is 1.23x faster than LMCache and within approximately 4% of the native vLLM KV Offload implementation. LongBench and SCBench show that these benefits extend to irregular prefix chains and multi-turn workloads. Bailian trace replays improve TTFT on a weaker GPU, but on an H100 the average request falls below the break-even point and GPU memory alone retains enough prefixes. External KV caching should therefore be treated as a setup specific admission decision. The py-kvcacheimplementation is available at: https://github.com/atlarge-research/py-kvcache.
Read the full abstract
Plasma Physics
Experimental Plasma Density Profiles Determined Through Measurements of the Magnetosonic Wave Speed
Information on plasma density in laboratory plasmas is commonly acquired using either Langmuir probes or optical diagnostics. Here, we present an alternative approach, inferring the density profile from magnetic measurements of a plasma wave. In particular, during the process of creating a reconnecting current layer for magnetic reconnection experiments in the Big Red Ball, the reconnection drive first launches a large amplitude fast magnetosonic wave. The propagation of the wavefront is measured with high spatial and temporal resolutions by in situ magnetic diagnostics. Given a known uniform background magnetic field strength and the known dispersion relation of the wave, we here show how the characteristics of the wavefront can be applied to determine the initial plasma density profile.
Read the full abstract
Combinatorics
Füredi's Conjecture and a Sharp Strengthening
We prove a strengthening of Füredi's conjecture on strong Bollobás $t$-systems. For nonnegative integers $t$ and $s$, a family of $m\ge2$ pairs of finite sets $(A_i,B_i)$ satisfying $|A_i\cap B_i|\le t$ and $|A_i\cap B_j|>t+s$ for all $i\ne j$ satisfies \[ \sum_{i=1}^{m} \frac{\binom{|B_i|-t+s}{s}} {\binom{|A_i|+|B_i|-2t}{|A_i|-t}}\le1. \] When $s=0$, this is precisely Füredi's conjectured weighted inequality. The proof is based on a local growth inequality for graded exterior ideals, a basis-exchange construction, and a common-section reduction. The same method gives the corresponding inequality for subspaces over arbitrary fields. We also determine a best possible upper bound for the Füredi weight sum, construct equality examples with an arbitrary prescribed number of pairs, and derive further inequalities from two-sided basis exchanges.
Read the full abstract
Quantum Physics
Quantum transport along a tight-binding chain connected to Markovian reservoirs
We consider quantum transport of non-interacting particles in a tight-binding chain coupled to Markovian reservoirs at its boundaries and subject to uniform on-site dephasing. Using the masterequation approach, we derived the exact analytic solution for the mean current along the chain. This analytic solution is obtained in the framework of single-particle quantum mechanics and, thus, equally applies for transport of non-interacting bosons and fermions. In the absence of phase damping, the results are extended to the complete many-body solution for bosonic problem in the form of anti-normally ordered characteristic function. This function allows us to calculate the distribution function for the current at each bond in the chain as well as the inter-bond current correlation functions.
Read the full abstract
Statistics Theory
From Good Starts to Optimal Inference: Generalized Latent Factor Models with Missingness and Implicit Regularization
Generalized latent factor models provide a flexible framework for analyzing high-dimensional non-Gaussian data, but principled estimation and uncertainty quantification under missingness remain substantially less developed. We develop a theory that connects a computationally tractable nonconvex procedure directly to statistical inference for nonlinear latent factor models with exponential-family links and partially observed entries. Our procedure combines a link-aware double-SVD initialization, a unilateral refinement that achieves rowwise consistency, and vanilla gradient descent. We show that the refined initializer enters a region of incoherence and contraction and that gradient descent remains in this region through implicit regularization, contracting rapidly down to the statistical estimation error without explicit incoherence or balancing regularization. Our central result is a uniform rowwise linear approximation for the actual output of gradient descent that isolates the leading score fluctuations from higher-order estimation and optimization errors. These expansions yield asymptotically valid individual and Gaussian multiplier-bootstrap simultaneous inference for latent factors, together with simultaneous confidence bands for missing-entry means, without requiring an additional debiasing step. The resulting estimation rate matches a restricted-class minimax lower bound up to logarithmic factors, while the theory accommodates severe missingness, weak low-rank signals, and diminishing local curvature. Simulations support the theoretical findings, and an application to large language model evaluation illustrates uncertainty-aware estimation and ranking of latent model capabilities.
Read the full abstract
Computation and Language
LOCUS: Task-Aware Low-Rank Post-Training for Token-Efficient Language Generation
Large language model serving costs scale directly with output sequence length, yet standard preference alignment often inflates response verbosity without improving utility. We study whether the parameterization of post-training updates affects generation length: low-rank subspaces alter sequence length without modifying the alignment loss. We present LOCUS, a method that selects a task-aware low-rank adaptation subspace to minimize output-token cost subject to a utility constraint. Within this subspace, post-training retains the native preference objective with a frozen backbone. Across Anthropic HH-RLHF dialogue preferences, we evaluate two $\sim$3B decoder backbones, Pythia-2.8B and Qwen2.5-3B, against protocol-matched full-parameter DPO and DrDPO branches and the released SamPO checkpoint. LOCUS reduces continuation length by up to 39.84% on Pythia-2.8B and by 14.87–17.58% on Qwen2.5-3B while updating only 0.24–0.28% of model parameters, with no material change in the internal preference diagnostic.
Read the full abstract
High Energy Physics (Theory)
Fermion quantum field theory on curved and non-inertial backgrounds in standard-Minkowski form
Quantum field theory on curved and non-inertial backgrounds contains background- and foliation-dependent quantities in the canonical Lagrangian, the hypersurface inner product and bilinear form, as well as in the equal-time anti-commutation relations. In this work, we determine a local fermion-field redefinition that brings these canonical structures into their standard-Minkowski forms, i. e., the forms they assume in Cartesian inertial coordinates on Minkowski spacetime, where the zeroth world coordinate is identified as the coordinate of time. Starting from the generally covariant Dirac action minimally coupled to a spin-1 gauge field, we derive the corresponding Lagrangian, fermionic inner product, and quantization rule in an Arnowitt-Deser-Misner decomposition, formulated in arbitrary world coordinates. We identify the generalized temporal gamma matrix as the common geometric factor governing the canonical temporal structure of all three quantities. Using a field redefinition, we transform this generalized temporal gamma matrix to its standard-Minkowski form, thereby mapping the fermionic inner product and the equal-time anti-commutation relation to their standard-Minkowski expressions, while transferring the explicit background and foliation dependence to the transformed Lagrangian and fermion-field operators. We show that such a field redefinition necessarily consists of a local rescaling and a fixing of the local Lorentz frame. This procedure restores the conventional canonical normalization from standard-Minkowski spacetime used for fermionic mode quantization and occupation-number operators. The transformed Lagrangian consequently assumes a generalized first-order Schrödinger form, leading to the familiar rest-energy term and spacetime-magnetic couplings, as well as to the leading non-relativistic limit, in which temporal derivatives are separated from spatial ones.
Read the full abstract
Multiagent Systems
Organizational Principles Enable Collective Intelligence in Embodied AI
Collective intelligence depends not only on the capabilities of individual members, but also on how those members are organized. Yet artificial multi-agent systems are typically assembled using fixed organizational structures, even when the physical tasks they perform impose fundamentally different coordination requirements. Here we show that principles from human organization theory can be operationalized to organize large, heterogeneous collectives of embodied artificial agents. We introduce ORCH (Organizing Roles and Coordination Hierarchies), which constructs task-specific hierarchical organizations by combining pooled interdependence for work that can proceed concurrently with sequential interdependence for work governed by prerequisite relationships. Across 25 wildfire-response missions spanning reconnaissance, rescue, transportation, resource management, containment and suppression, we evaluated teams of up to 50 heterogeneous agents using eight large language models. Organizations constructed using these principles consistently outperformed four representative embodied multi-agent approaches across mission outcome, execution efficiency, exploration and computational resource use. Human-designed ORCH organizations improved final score by 63.97% and execution efficiency by 74.29% on average relative to the four prior frameworks. Organizations generated automatically by language models improved these measures by 43.63% and 52.53%, respectively. These advantages persisted across missions and underlying language models. Notably, collective performance was not monotonically determined by model scale. Analysis of long-horizon missions showed that hierarchical organization enabled teams to preserve concurrent activity within specialized groups while coordinating ordered transitions between mission phases.
Read the full abstract
Quantum Physics
Learning structural balance of graphs from quantum spectral features
We develop a quantum approach to spectral feature extraction from the density of states (DOS) of a problem-dependent Hamiltonian, and apply it to machine learning on signed graphs. We propose to embed a signed graph as an Ising model instance with positive and negative interactions, and use the standardized moments of the Ising DOS as features for learning. We show that these moments count signed closed walks, are switching-invariant, and are size-free by construction. As a benchmark, we target learning the frustration index, an NP-hard measure of structural balance that can be labeled exactly at moderate size. At zero field, the models can be sampled classically, allowing the quantum extraction procedure to be certified against exact ground truth. We propose DOS-QPE, a phase estimation on a purified maximally mixed probe, which samples the spectral density with orders of magnitude fewer shots than Hadamard test-based trace sampling and feeds the resulting features directly into classically trained models. On $1.4\times10^5$ labeled graphs the exact DOS determines the frustration index, and five moments recover it with a mean error of 0.4, well below one sign flip. Beyond zero field, the underlying trace-estimation problem is DQC1-complete, providing access to spectral features for which no efficient classical sampling method is known. Our work opens routes towards quantum applications in social network balance analysis, spin-glass studies, correlation clustering, and protein-interaction networks.
Read the full abstract
Probability
Tilting Billingsley's model toward a giant prime: two phase transitions
Billingsley's theorem states that the normalized logarithms of the prime factors of a uniform random integer in $[1,x]$ converge to the Poisson–Dirichlet law $PD(1)$, while weighting an integer $n$ by the generalized divisor function $d_\theta(n)$ gives $PD(\theta)$. We ask what remains of this picture when the integer is also rewarded according to its largest prime factor $P^+(n)$. For fixed $\theta,\beta>0$ and $\gamma\ge0$, we sample $N_x=n\le x$ with probability proportional to $d_\theta(n)\exp\{\beta H_\gamma(n)\}$, where $H_\gamma(n)=(\log P^+(n))^\gamma$ for $\gamma>0$, while $H_0(1)=0$ and $H_0(n)=1$ for $n\ge2$. Two phase transitions occur. At $\gamma=0$ the $PD(\theta)$ partition survives, whereas every fixed $\gamma>0$ forces one prime to carry asymptotically all logarithmic mass. The second transition, at $\gamma=1$, concerns the cofactor $R_x=N_x/P^+(N_x)$. With $a_x=\beta\gamma(\log x)^{\gamma-1}$, its law is asymptotic in total variation to $Q_{a_x}(m)=d_\theta(m)m^{-1-a_x}/\zeta(1+a_x)^\theta$. Thus, for $0<\gamma<1$, $a_x\log R_x$ has a $Gamma(\theta,1)$ limit, with shape $\theta$ and rate one, and the normalized logarithmic prime factors of $R_x$ have an independent $PD(\theta)$ limit; at $\gamma=1$, $R_x$ has a nondegenerate discrete limit; and for $\gamma>1$, $R_x=1$ with high probability. We also determine the joint limits involving $N_x/x$ and the normalizing constants, which include the classical Alladi–Erdős asymptotic as a special case.
Read the full abstract
Analysis of PDEs
Global well-posedness of the primitive equations with stochastic wind-driven boundary conditions
Consider the three-dimensional primitive equations subject to Neumann wind stress driven by finitely many Brownian motions. For arbitrary smooth spatial wind profiles, global pathwise existence and uniqueness without assuming a vertical derivative of the initial datum is proved, extending the local theory of Binz, Hieber, Hussein, and Saal: The primitive equations with stochastic wind driven boundary conditions (J. Math. Pures Appl. (9) (2024), 76–101) for this class of data and wind profiles. The proof combines a local maximal $\rL^2$ regularity construction with weighted estimates for the boundary stochastic convolution.
Read the full abstract
Robotics
Reflex-Informed Neuromuscular Reinforcement Learning for Muscle-Driven Locomotion
Muscle-driven locomotion provides a physically grounded approach to generating realistic human movement. However, achieving both physiological plausibility and adaptability to changes in musculoskeletal capacity and external disturbances remains a fundamental challenge. To address this limitation, we propose a Reflex-Informed Neuromuscular Reinforcement Learning framework for muscle-driven locomotion. Within this framework, a fixed phase-dependent reflex controller serves as the underlying neuromuscular control mechanism, while the reinforcement learning policy produces four biomechanically meaningful residual parameters to modulate key reflex gains and thresholds associated with hip swing, knee support, and ankle propulsion according to the current state. Experimental results demonstrate that the proposed framework generates physiologically plausible locomotion with improved kinematic accuracy and dynamic consistency, as well as better bilateral symmetry and stride-to-stride consistency under nominal walking conditions. The learned policy remains robust under muscle weakness and external perturbations without retraining.
Read the full abstract
Mesoscale and Nanoscale Physics
Hilbert-space selected switch of helical edges in an artificial quantum Hall insulator
Quantum Hall effects (QHE) host one-dimensional topologically-protected edge channels, which can serve as an essential ingredient in exotic quantum electronic systems. Yet the manual reconstruction of Landau-level topology, by electrostatic confinement or symmetry breaking, remains experimentally challenging. Here, we show that interfacial charge transfer in between CrOCl and large-angle twisted bilayer graphene offsets the two otherwise decoupled Dirac Landau-level ladders in each graphene layer, creating a new sequence of composite filling configurations. At charge neutrality, the composited $(+2,-2)$ state involves only the zeroth Landau levels and becomes fully insulating, with longitudinal resistance reaching the G$\Omega$ regime. By contrast, higher composite zero-filling quantum Hall states, including $(+6,-6)$ and $(+10,-10)$, retain counter-propagating helical edge channels and exhibit pronounced non-local transport, reaching up to $50\%$ of the local response. We attribute such switching-behavior to the Landau-spinor Hilbert space – as the filling is reduced from $(+6,-6)$ to $(+2,-2)$, the orthogonal $N=\pm1$ orbital components are removed, eliminating the edge-compatible channel and gapping both bulk and boundary transport. The interaction nature of the observed gapped sates was further examined both experimentally and theoretically. Our results suggest that charge transfer provides a direct route to engineer artificial quantum Hall insulators, opening possibilities for wavefunction-selective control of helical edge modes.
Read the full abstract
Dynamical Systems
Classification of Choquet-Deny Lie groups
We characterize connected Lie groups on which all adapted random walks have only trivial bounded harmonic functions. In the nilpotent case, this answers a question of Furstenberg recorded by Guivarc'h in 1973.
Quantum Physics
An exchange-assisted entangling gate between 87Rb and 171Yb Rydberg atoms
Neutral-atom tweezer arrays support scalable quantum information processing. Dual-species $^{87}\mathrm{Rb}$–$^{171}\mathrm{Yb}$ arrays combine long-lived ytterbium nuclear-spin data qubits with fast, species-selective rubidium ancilla control and readout. However, realizing interspecies gates without inducing destructive Stark mixing in divalent atoms remains an outstanding problem. Here, we identify an optically accessible $S{+}S\leftrightarrow P{+}P$ Förster resonance at zero electric field, providing strong dipole-dipole exchange at array pitch. Using a shaped optical pulse under finite control response, we demonstrate a $0.36\,\mu\mathrm{s}$ exchange-assisted controlled-$Z$ gate with an intrinsic fidelity of $99.91\%$, remaining above $99.85\%$ under bounded perturbations. We also identify an auxiliary repulsive van der Waals channel, providing a comprehensive toolbox for hybrid quantum processors.
Read the full abstract
Combinatorics
Spectral bipartiteness in generalized odd graphs of diameter three
For a graph $G$ of order $n$, put $\sigma(G)=(\lambda_1(G)+\lambda_n(G))/n$. We determine the first three largest values of this invariant among nonbipartite distance-regular graphs of diameter three and odd girth at least seven. The unique maximizer is the folded $7$-cube, with value $1/32$; the unique second maximizer is the Odd graph $O_4$, with value $1/35$; and the unique third maximizer is $C_7$, with value $2(1-\cos(\pi/7))/7$. More precisely, every other graph in the class satisfies $\sigma(G)<1/36$. This answers Problem~11 of Abiad, Taranchuk and van Veluw in Electronic Journal of Combinatorics 33(2) (2026), P2.31. The proof combines established local multiplicity and odd-moment bounds: the condition $\sigma(G)\geq1/36$ forces the valency to be at most $182$. An exhaustive certificate using only integer and rational arithmetic then leaves three intersection arrays. The complete certificate is publicly available, and neither a classification of generalized odd graphs nor the $Q$-polynomial property is assumed. The odd-girth theorem gives the same extremal conclusions for connected $\{C_3,C_5\}$-free graphs with at most four distinct adjacency eigenvalues, without assuming regularity.
Read the full abstract
Software Engineering
Reproducibility in the Age of Agentic AI: Context Engineering at the Timescale of a Codebase
Reproducible research practices are context engineering for AI coding agents. I argue that agents lower the cost of maintaining tests, commit histories, repository structure, instructions, and decision records while making their benefits immediate. Researchers remain responsible for verifying these artifacts and the scientific judgments they encode.
Read the full abstract
Geometric Topology
Braided Multisections and Symplectic Four-Manifolds with the Rational Cohomology of $S^2\times S^2$
We construct symplectic four-manifolds by taking mixed fiber sums along explicit cyclic multisections in ruled surfaces. For a connected unbranched degree-$p$ multisection in $\Sigma_g\times S^2$, we determine the first homology and fundamental group of the complement and prove that its boundary is incompressible. It follows that no direct gluing of two such complements can be simply connected; moreover, the first homology of every direct sum retains finite quotients determined by the covering degrees. We classify the mixed sums having Euler characteristic $4$ and signature $0$. Up to interchanging the two summands, exactly three possibilities occur, corresponding to the degree pairs $(2,3)$, $(2,4)$, and $(3,3)$. For each of these cases, suitable adapted product-framed symplectic gluings have the rational cohomology ring of $S^2\times S^2$. Varying the gluing by symplectic transvections produces infinitely many pairwise nondiffeomorphic examples, distinguished by the unbounded orders of their finite first homology groups. We also construct the twisted ruled analogue of the $(2,4)$ case. Explicit finite-holonomy multisections give connected square-zero symplectic surfaces in the classes $2S_3-F_3$ and $4S_2-2F_2$ in the nontrivial $S^2$-bundles over $\Sigma_3$ and $\Sigma_2$, respectively. More generally, for a square-zero degree-$p$ multisection in the nontrivial bundle the complement has first homology $\mathbb Z^{2g}\oplus\mathbb Z/(p/2)$. Suitable gluings in the twisted $(2,4)$ case have $b_1=0$, $b_2=2$, and signature zero, and every such sum is non-spin. Hence they have the rational cohomology ring of $\mathbb CP^2\#\overline{\mathbb CP}^{\,2}$. We compare these constructions with the author's 2006 construction of minimal symplectic four-manifolds having the integral cohomology $S^2\times S^2$, obtained via knot surgery and twisted fiber sums.
Read the full abstract
General Relativity and Quantum Cosmology
From the Test-Mass Limit to Binary Black-Hole Waveforms in Higher-Derivative Gravity
Many higher-derivative theories predict stronger deviations from General Relativity for lower-mass black holes, while their nonlinear field equations often prevent reliable simulations of the full binary evolution. Here we develop a route from controlled black hole perturbation theory based on the modified Teukolsky formalism to comparable-mass waveforms, using parity-even cubic gravity as a representative example. We find that the tidal response of the secondary black hole enters at the same perturbative order as the direct higher-curvature correction and is therefore essential for a consistent leading-order waveform. The resulting strong-field fluxes and conservative dynamics produce an accumulated inspiral dephasing that grows toward merger. Embedding this test-mass information into an effective-one-body model, we construct inspiral-merger-ringdown waveforms for comparable-mass binaries and find coupling-dependent dephasing and waveform-peak shifts. Our results demonstrate how strong-field test-mass calculations can anchor waveform models for higher-derivative gravity when theory-specific numerical-relativity simulations are unavailable.
Read the full abstract
Sound
Continuous-Time Acoustic Modelling with Neural Controlled Differential Equations
Text-to-speech (TTS) models commonly address text–speech alignment by expanding phone-level encoder states to frame-level decoder inputs using predicted durations. While this length-regulation step resolves alignment structurally, this use of duration typically changes only where and how often latent states appear, not the values of the states themselves. This paper proposes a continuous-time mechanism for duration-aware acoustic modelling in TTS using neural controlled differential equations (CDEs). We formulate the phone representation as a temporally parameterised control path and use a neural acoustic vector field to produce a continuous-time hidden state whose values evolve with phonetic content and duration-derived timing. The resulting trajectory can be sampled at discrete points and integrated into a standard acoustic decoder pipeline. Objective results contrast CDEs and typical recurrent models. Subjective results suggest that CDE-based models evaluating one phone per step can improve rank-order agreement between synthesised and reference emotion intensity while maintaining comparable emotion-expression quality to a strong baseline. Additional experiments with half-phone step-sizes suggest that temporal resolution changes the trade-off between style tracking and absolute calibration. These results position CDEs as a promising design space for continuous-time and duration-aware style-sensitive TTS.
Read the full abstract
Computation and Language
The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge
This paper details the Eloquence team's approach to Task 2 of the 2nd MLC-SLM challenge at Interspeech 2026, which involves multilingual Multiple-Choice Question Answering (MCQA) across 21 languages. Three approaches are explored. First, we fine-tune Voxtral-Mini-3B via LoRA with cross-lingual data augmentation, ASR transcript augmentation and timestamp-aware audio cropping, achieving 0.72 macro-accuracy on evaluation Phase 2. Second, we apply multimodal in-context learning (ICL) to the frozen Voxtral-24B model to correct a strong label bias, reaching 0.81, our best result. Third, a training-free retrieval system based on a three-layer voice-anchored memory combining acoustic identity, semantic content, and a knowledge graph achieves 0.68. All three systems substantially outperform the official baseline.
Read the full abstract
Quantum Physics
Lifted surgery: Fast processing with QLDPC codes
Quantum low-density parity-check (QLDPC) codes are a leading candidate for achieving low-overhead fault-tolerant quantum computing. However, the time overhead of logical operations in QLDPC codes remains a key challenge. Code surgery, a space-efficient technique for fault-tolerant logical measurements, incurs this overhead through repeated rounds of syndrome measurement. We introduce lifted surgery, a method for fast and parallel surgery on Abelian group algebra codes that maintains the low physical overhead that makes QLDPC codes attractive. Lifted surgery preserves the symmetries of the underlying code, making searches for large instances tractable and offering a natural route towards efficient hardware implementations. We utilise block decompositions and techniques from commutative algebra to characterise lifted surgery, investigate well-behaved subfamilies, and construct explicit examples. In particular, we present quantum radial codes with parameters $[[90, 8, 10]]$ and $[[198, 8, 16 ]]$ for which surgery is fast, parallel, and addressable, allowing arbitrary sets of independent logical operators of the same Pauli type to be measured in a single round of syndrome extraction. We benchmark lifted surgery under circuit-level depolarising noise and, for the $[[ 90, 8, 10 ]]$ code, find logical performance comparable to standard code surgery while requiring ten times fewer rounds of syndrome measurement. By combining speed and parallelism, lifted surgery offers a practical route towards low-overhead fault-tolerant quantum computing.
Read the full abstract
Computer Vision
Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need
The representation of 3D clothed humans as standardized 2D UV texture and displacement maps over an underlying body model has long been studied. This compact representation is enticing as it enables pretrained image networks to process, generate, and edit 3D avatars, but is only useful if scans are accurately aligned and brought into correspondence via high-fidelity registration. This prerequisite has never been met, which we argue explains the limited quality of prior UV-based methods for clothed humans. Despite its significance, no public method produces high-fidelity SMPL(-X)+D registrations with UV texture from arbitrary clothed scans. We present AvaImg, a multi-stage optimization pipeline, to close this gap: it enforces body-inside-clothing constraint via signed winding numbers, made viable by a three-level efficiency cascade (~10x runtime reduced, ~95% storage saved), and recovers fine surface detail using coarse-to-fine displacement optimization. AvaImg outperforms all baselines in body fitting, shape estimation, and surface registration across six datasets, yielding textured registrations near-indistinguishable from scans (PSNR=34.48dB). For validation of AvaImg's Avatar-as-Image representation as imminently compatible with image foundation models, we auto-encode our UV maps via the frozen FLUX VAE. This achieves only 0.76mm added Chamfer error relative to scan and shows that the resulting maps lie within natural-image distributions, supporting the use of 2D generative priors for 3D avatar generation. Code, data, and Singularity containers will be at https://yuxuan-xue.com/avaimg.
Read the full abstract
Optimization and Control
Verified Linear Programming via Tolerance-Aware Precision Boosting
Linear programming plays a fundamental role in computer science, with applications in optimization, formal verification, SMT solving, and numerous other domains. When exactness guarantees are required, numerical inaccuracies arising from floating-point arithmetic can compromise soundness, whereas exact rational arithmetic often incurs significant computational overhead. In this paper, we investigate the numerical stability of the simplex algorithm and establish conditions under which a precision-boosting floating-point implementation provably produces the same pivot decisions and final basis as an exact rational implementation, from which the final result is reconstructed and certified exactly. Our analysis shows that correctness depends on both arithmetic precision and a careful handling of numerical tolerances. Based on these results, we develop a tolerance-aware, precision-boosting simplex algorithm with formal correctness guarantees. Finally, we introduce a delta-complete termination criterion that allows the algorithm to terminate once certified upper and lower bounds on the optimal objective differ by at most a user-specified threshold delta, providing a certified, user-controlled optimality gap.
Read the full abstract
Quantum Physics
A Geometric Theory of Quantum Entanglement
Entanglement Distance (ED) was originally proposed as a geometric measure of entanglement derived from the Fubini-Study metric on the projective Hilbert space. Independently, the Meyer-Wallach and Scott measures quantify multipartite entanglement via linear entropy. In this work, we demonstrate that these two seemingly distinct frameworks are mathematically identical for pure states of arbitrary finite dimensions. We prove that ED arises naturally as the trace of the Fubini-Study metric tensor over the local subalgebra of observables. Crucially, this geometric unification yields a direct operational interpretation: the global entanglement of a pure state is exactly proportional to the total Quantum Fisher Information (QFI) available for local unitary estimation. This bridges abstract information geometry with quantum metrology, demonstrating that ED dynamically quantifies resourcefulness for distributed quantum sensing, identifying Heisenberg-limited sensitivity in regimes where standard variance-based witnesses fail.