Information Retrieval
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
All of arXiv
Tuesday 15 September
How and why does a recommender system fail the users it serves? Oftentimes, practitioners are left to improve their algorithms based on a combination of feedback from stakeholder teams, domain expertise, and insights from data analyses. Yet the nuances of how and where recommendations perform well or poorly for end users are difficult to discern from aggregate quantitative metrics. Whereas these metrics provide a high-level and incomplete picture, further granularity into the quality of recommendations and their patterns requires reasoning with domain understanding and objectivity, at scale. We contemplate this complex conundrum and describe a method and implementation that uses the latest AI agentic advances to provide actionable diagnoses and improvements for production recommender systems. We present AURA (Agentic Understanding and Refinement of recommender Algorithms), an end-to-end agentic system that performs qualitative evaluation at scale and can then generate improvements to our algorithms at the code level. Specialized agents read production engagement logs, from thousands of sessions to millions, and surface patterns and examples of how the recommender fails real users. The next step uses those diagnoses and context about the recommender's own code, data, and training pipeline to propose and implement refinements grounded in that codebase. We report the system design, initial tests on production data from two large consumer platforms at a major media-streaming company, safeguards, operational learnings, and early results toward a self-improving recommender system. Finally, the diagnostic gap AURA closes is not specific to streaming. The architecture is built to transfer: every domain-specific element enters through the configuration layer that already ported it between our two platforms. We map it concretely to e-commerce and online-retail recommendation.
Analysis of PDEs
Existence and Asymptotic Stability of Traveling Waves of Two-species Lotka-Volterra Competition-Diffusion Systems via Geometric Singular Perturbations
We consider the two-species Lotka-Volterra competition-diffusion system where one species has a small diffusion rate relative to the other species and has a small competition coefficient. By the geometric singular perturbation theory, we prove the existence of the wavefront connecting the coexistence state to the trivial state, with traveling speed greater than the minimal speed. For such wavefronts, we show that the profiles of both species are monotone. Finally, we use the geometric singular perturbation theory to estimate the associated Evans function, and give the related stability results.
Read the full abstract
Optics
Terahertz two-dimensional coherent spectroscopy: unlocking coherent quantum intraband nonlinear dynamics
Quantum materials host a rich spectrum of low-energy collective excitations- phonons, magnons, plasmons, polaritons, and Higgs modes- that fundamentally govern their emergent properties, but remain inaccessible to conventional linear THz spectroscopy when nonlinear pathways overlap or non-perturbative dynamics emerge. Terahertz two-dimensional coherent spectroscopy (THz-2DCS), realized through phase-stable high-field THz pulse sequences, directly resolves this challenge by delivering phase-resolved multidimensional spectra that uniquely disentangle coherent intraband nonlinear quantum dynamics from incoherent backgrounds. Here, we establish a unified theoretical framework by using density-matrix formalism combined with the optical Bloch equations, from which nonlinear pathways are systematically derived and visualized on the Bloch sphere. This framework provides insight into low-energy nonlinear dynamics exhibiting homogeneous or inhomogeneous broadening depending on the scattering mechanism, enabling the interpretation of nonlinear signals in both the perturbative regime, described by a susceptibility expansion, and the non-perturbative regime. Building on this foundation, we comprehensively survey THz-2DCS investigations of nonlinear plasmon, phonon, magnon, and polariton. Finally, we outline future opportunities, including integration with optical-pump THz-probe platforms for nonequilibrium quantum control.
Read the full abstract
Statistics Theory
Characterizing Heterogeneous Rates in Finite Mixture Estimation via Partial Optimal Transport
Parameter estimation in finite mixture models can exhibit highly heterogeneous convergence behavior: locally isolated components may be estimated substantially faster than groups of competing components. Existing analyses based on Wasserstein distances typically characterize only the worst-case rate and therefore do not fully capture this local heterogeneity. In this paper, we introduce a Voronoi-based partial optimal transport (VPOT) framework for obtaining refined local and global convergence guarantees for the maximum likelihood estimator of the mixing measure. The key geometric idea is to localize the comparison of two mixing measures to extended Voronoi neighborhoods and use partial optimal transport to accommodate the unequal masses of their local restrictions. Within each neighborhood, the first-order POT discrepancy is raised to a power determined by the number of locally competing atoms, allowing the resulting loss to adapt to the local degree of singularity. Under suitable regularity and strong identifiability conditions, we establish uniform local and global upper bounds for a maximum likelihood estimator under the VPOT loss. These bounds reveal a configuration-dependent form of parameter estimation: less singular local configurations admit faster convergence, whereas the most singular configuration recovers the classical worst-case behavior characterized by Wasserstein-based analyses. We further establish a minimax lower bound showing that the convergence rate for estimating the mixing measure under the VPOT loss is optimal. Our results hold in arbitrary fixed dimension without requiring mixing proportions to be uniformly bounded away from zero or prior knowledge of the true number of mixture components. Overall, VPOT provides a configuration-adaptive framework for capturing heterogeneous parameter-estimation behavior in finite mixture models.
Read the full abstract
Machine Learning
Stable by Construction: Variational Latent Markov Operators for Long-Horizon PDE Prediction
Neural PDE solvers provide efficient surrogates for time-dependent physical systems, but autoregressive prediction over long horizons remains challenging because local errors can induce distribution shift and accumulate under recursive deployment. We develop a variational approach to this problem by introducing latent Markov dynamics in which physical states are represented by latent distributions and evolved through probabilistic transitions. The framework is formulated directly on function spaces and specialized to functional Gaussian models, where structured latent perturbations induce a spectral geometry and variational transition alignment regularizes the learned dynamics. We further analyze how these mechanisms affect autoregressive error propagation, providing a theoretical connection between variational training and long-horizon prediction. We instantiate the framework as the Variational Autoencoding Markov Operator (VAMO), which combines spatially resolved latent fields, structured Gaussian perturbations, and a neural-operator transition. Empirically, we demonstrate the effectiveness of VAMO on several fluid-dynamics benchmarks with prediction horizons extending substantially beyond those represented during training, where it consistently reduces error accumulation and improves rollout stability over several deterministic and noise-injection baselines. Overall, these results highlight variational modeling as a complementary approach to robust long-horizon neural PDE dynamics.
Read the full abstract
Materials Science
Application of Regional Chemical Potential Analysis to Si Adsorption on the Diamond (001) Surface
Adsorption of carbon dimers and Si atoms on the reconstructed diamond (001) surface is inves- tigated using density functional theory and regional chemical potential (RCP) analysis. We first demonstrate that the RCP distribution provides a real-space description of the bonding rearrange- ments responsible for the site-selective growth of experimentally observed carbon-dimer ribbons. We then examine the adsorption of single and multiple Si atoms. The calculated adsorption ener- gies show that a single Si atom preferentially bridges a surface carbon dimer and that subsequently adsorbed Si atoms favor neighboring dimer sites through Si-Si bond formation. The RCP analysis identifies electron-donating regions at the ends of finite Si chains, providing an intuitive explanation for their preferential one-dimensional growth and a physically motivated strategy for selecting candi- date adsorption structures. At higher Si coverages, geometry optimizations yield Si stripe and planar square-lattice structures on the diamond surface. Surface phase analysis indicates that an increase in the effective Si chemical potential favors structures with progressively higher Si coverages, from the Si stripe phase to the Si square-lattice phase. The calculated band structures reveal a progressive reduction of the surface band gap with increasing Si coverage. In the Si square-lattice structure, several bands cross the Fermi level, and the conducting states along the two in-plane directions have distinct Si and C character because the underlying diamond (001) substrate lacks fourfold rotational symmetry. These results establish RCP analysis as a useful approach for interpreting surface covalent bonding and guiding the exploration of adsorption-driven surface structures.
Read the full abstract
Signal Processing
DiSR-ECG: Residual Shifting Conditional Diffusion for Robust ECG Super-Resolution
Electrocardiogram (ECG) signals are essential for arrhythmia diagnosis. With the growing adoption of long-term monitoring via wearable and portable devices, energy-efficient acquisition has become critical, motivating the development of ECG super-resolution (SR) techniques to reconstruct high-resolution signals from low-sampling-rate inputs. While recent SR methods based on discriminative neural networks have shown strong performance, their robustness under distribution shift remains uncertain, which poses a key challenge for real-world deployment. In this study, we propose DiSR-ECG, a residual shifting conditional diffusion framework for robust ECG SR. The model integrates residual shifting with Mamba-based temporal modeling and conditional guidance to enable accurate multi-lead reconstruction. Experiments on two large-scale ECG databases, PTB-XL for in-domain evaluation and Chapman Shaoxing for cross-dataset evaluation, demonstrate that DiSR ECG achieves state-of-the-art performance in both settings, with particularly strong generalization under distribution shift. These results highlight the potential of DiSR-ECG to provide reliable and clinically applicable ECG reconstruction for real-world monitoring.
Read the full abstract
Statistical Methodology
A Multiverse of Good and Bad Controls: Candidate Causal Graphs for Interpreting Model Robustness Analysis
Model robustness analysis estimates an effect across a multiverse of specifications that pools control sets identifying the declared estimand with sets that condition on mediators or colliders. We propose stating rival assumptions about contested controls as a small set of candidate causal graphs, enumerating the adjustment sets each graph licenses, and reporting robustness metrics conditional on each graph. A finite-mixture identity splits the licensed multiverse's dispersion into within-graph and between-graph components; the between-graph share is a conditional descriptive summary whose reading depends on the candidate set, the weights, and a common estimand. Simulations examine misleading pooled robustness assessments and the limits of the decomposition. Applications to hurricane fatalities, job training, and union wages show fragility that survives every graph, instability produced by unlicensed specifications, and a fragility verdict concealing a significant premium in each adjustment-identified candidate world. An R package implements the workflow.
Read the full abstract
Machine Learning
Divergence Timing and Cumulative Disagreement under KV-Cache Eviction
KV-cache eviction perturbs the conditional token distributions governing autoregressive generation. We investigate how first-divergence timing and subsequent token mismatch determine cumulative disagreement. We derive an exact decomposition under a specified stepwise maximal coupling: the expected mismatch fraction equals a first-mismatch contribution plus post-divergence exposure multiplied by its mismatch rate. An explicit construction over unrestricted autoregressive kernel pairs realizes the sharp interval of risks compatible with a finite divergence-aligned observation window. Residual-branch conditional Monte Carlo provides unbiased joint estimates of occurrence, occupation, and window/tail contributions, with per-replicate variance dominance for total token loss. Complete trajectories from Meta-Llama-3.1-8B-Instruct and Qwen2.5-7B-Instruct show that SnapKV at 50% retention enters divergence later and less often than SnapKV-512 or recent-token retention with the same 50% prompt-cache budget, while post-divergence total variation (TV) remains high. In an exploratory analysis of 288 documents, post-divergence exposure accounts for 85-90% of four aggregate mismatch gaps. On 288 independent documents at 90% retention, prespecified comparisons show higher branch-aligned TV in the late than in the early window in both models.
Read the full abstract
Optics
Integrated Photonic Devices in Thin-Film Barium Titanate: Opportunities and Challenges
Thin-film barium titanate (BaTiO3, or BTO) has emerged as a promising electro-optic (EO) material for integrated photonics due to its exceptionally large Pockels coefficients, low optical loss, and compatibility with heterogeneous integration. Recent advances in epitaxial thin-film growth, crystal orientation control, ferroelectric domain engineering, and scalable integration have enabled EO performance in thin-film BTO approaching bulk-like properties on photonic platforms. This review provides a comprehensive overview of integrated photonic devices based on thin-film BTO, including fundamental material properties, thin-film growth and integration strategies, passive waveguide configurations, EO response at both the film and device levels, and relevant optical applications. We review the role of film orientation, domain structure, and device geometry in determining accessible EO coefficients and modulation mechanisms, as well as the distinctions between intrinsic and effective EO responses demonstrated at the film and device levels. Representative studies are compared in terms of film-quality-related metrics and device performance figures of merit, alongside emerging applications realized in BTO-based platforms. Finally, we discuss the remaining challenges and outline future development directions toward high-performance BTO-based integrated photonic systems.
Read the full abstract
Nuclear Theory
Revisiting nuclear chirality in $^{128}$Cs with relativistic configuration-interaction density functional theory
Nuclear chirality in $^{128}$Cs is revisited within the microscopic relativistic configuration-interaction density functional (ReCD) theory. The positive-parity doublet bands are investigated by simultaneously examining their energy spectra, electromagnetic transition probabilities, $g$ factors, spectroscopic quadrupole moments, and underlying angular-momentum geometry. Without introducing additional parameters adjusted to the spectroscopic data, the ReCD calculations provide an overall satisfactory description of the available experimental observables. In particular, a comprehensive analysis of the available experimental data and the calculated spectroscopic observables indicates qualitative resemblances between the partner bands around $I = 17\hbar$. A microscopic analysis of the angular-momentum geometry through azimuthal plots reveals a distinct evolution of the rotational mode with increasing spin: chiral vibration at $I < 17\hbar$, static chirality at $I = 17\hbar$, and a transition toward planar rotation at higher spins. These results suggest that static chiral geometry in $^{128}$Cs is confined to a narrow spin region around $I = 17\hbar$ within the present ReCD calculations.
Read the full abstract
Computation and Language
RoleBreak: Benchmarking Long-Horizon Role-Playing Robustness in Spoken Dialogue
Speech-to-speech dialogue models increasingly support persona control, yet existing spoken role-playing benchmarks remain largely character-centric and short-horizon. This leaves open whether spoken dialogue models can sustain diverse roles over extended interactions, especially beyond predefined fictional characters. We introduce RoleBreak, an open benchmark for long-horizon role-playing robustness in spoken dialogue. RoleBreak contains 310 character-based and user-centered roles, 6,688 human-verified dialogue turns, and 11,743 fine-grained evaluation criteria, with 1,856 turns carrying expressive emotion targets for evaluating vocal emotion. Its scenarios are designed to stress role consistency, interaction quality, safety, and affect over extended conversations. We evaluate nine configurations spanning full-duplex, omni-modal, and cascaded ASR–LLM–TTS paradigms. We find four key patterns. First, current systems are substantially stronger at semantic role adherence than at vocal emotion. Second, semantic robustness remains brittle over long interactions: even the strongest evaluated system encounters its first persona and safety failures after only 10.4 and 11.6 turns on average. Third, scaling the LLM substantially improves semantic robustness and delays failure, but yields little improvement in vocal emotion. Finally, user vocal emotion affects role-playing behavior even when linguistic content is fixed. These findings highlight persistent gaps in both long-horizon robustness and vocal expressiveness in spoken role-playing systems.
Read the full abstract
Analysis of PDEs
On the internal modes of the ground state for 3D cubic–quintic equations
Motivated by the problem of asymptotic stability for ground states of the Klein–Gordon and Schrödinger equations in three spatial dimensions in the presence of internal modes, we study the corresponding models with cubic–quintic nonlinearities. These equations arise in several physical contexts; in particular, the cubic–quintic Klein–Gordon equation appears naturally in the study of spin-$0$ particles in quantum field theory. More precisely, let $Q_\omega$ be the positive radial ground state of the three-dimensional cubic–quintic elliptic equation \[ -\Delta Q_\omega+\omega Q_\omega-Q_\omega^3+Q_\omega^5=0. \] We study two related, but logically distinct, spectral problems as $\omega$ approaches the endpoint $3/16$ of the ground-state branch. First, we determine the complete discrete spectrum of the scalar Hessian \[ L_+=-\Delta+\omega-3Q_\omega^2+5Q_\omega^4. \] This operator is also the exact linearized spatial operator around the static state $Q_\omega$ for the real scalar cubic–quintic Klein–Gordon equation with mass parameter $\omega$. We prove that the number of its discrete angular-momentum sectors tends to infinity, and obtain sharp asymptotics for their locations and multiplicities. Second, for the cubic–quintic nonlinear Schrödinger equation, we analyze the full Hamiltonian matrix linearization and prove the existence of internal modes in precisely an interval of angular-momentum sectors of length comparable to $(3/16-\omega)^{-1}$. %The rotating complex Klein–Gordon problem leads %to a different gyroscopically coupled pencil; since that pencil is not %analyzed here, no identification of its internal spectrum is asserted. These results provide a rigorous linear foundation for future nonlinear stability and radiation-damping analysis in three-dimensional cubic–quintic models.
Read the full abstract
Sound
Structure Across Voices: Comparing acoustic-event type accumulation and sequence dependence across four vocal corpora using frozen audio encoders
Comparing acoustic structure across very different vocal corpora is difficult because the recordings use different native event units, contain different amounts of sequence, and were collected under different conditions. We develop a matched procedure for comparing such corpora without forcing them into the same event definition. Frozen audio encoders provide a common acoustic representation for recorded events, while matched sampling gives each corpus the same amount of evidence for acoustic and sequence analysis. We apply this procedure to sperm-whale codas, human speech phones, Bengalese-finch syllables, and common-marmoset calls. The comparison reveals different patterns across the four corpora. Sperm-whale recordings stand out broadly: new acoustic forms continue to appear, while their sequences also show strong organization and repetition. Finch recordings show the strongest organization of sounds over time, especially in how neighboring sounds and repeated patterns are arranged. Direct temporal and spectral measurements show that these differences are also present in the recorded sounds themselves. The comparison provides a practical way to measure acoustic diversity and temporal organization across very different vocal corpora by combining a common acoustic representation with matched observation opportunity, without treating their native sounds as equivalent.
Read the full abstract
Signal Processing
Reassessing 3GPP NR CSI Codebook Structures in Near-Field Channels: Finite-Feedback Multilayer Precoding and Design Insights
3GPP TR 38.901 Rel-19 introduces antenna-element-level spherical-wave modeling, while NR Type-I and enhanced Type-II (eType-II) CSI codebooks continue to use plane-wave DFT beams. Whether this mismatch materially degrades finite-feedback multilayer precoding in standardized multipath channels remains unclear. To isolate its impact, we evaluate both codebooks over strictly paired far-field (FF) and near-field (NF) 3GPP channels that share user locations, multipath parameters, polarization, and link budgets and differ only in their wavefront models. Simulations cover Rank 1-4 transmission in 7-GHz UMi and 24-GHz InH-linear scenarios. We find no systematic FF/NF shift in singular-mode gains or equal-power SVD (SVD-EP) rates. Instead, spherical-wave phases reorder multipath projections onto plane-wave candidates and thereby alter codeword selection. For Rank-4 InH-linear users at 0.1 normalized Rayleigh distance, given FF-selected Type-I and eType-II codewords incur median direct mismatch losses of 2.28% and 5.34% on the NF channel, respectively; codebook reselection identifies better-matched codewords and reduces these losses to 0.770% and 3.28%. Nested candidate-set comparisons further show that relaxing Type-I interlayer constraints improves the SVD-EP-normalized rate by 20.7 percentage points, whereas finite-range sampling adds only 0.579 points. These results support prioritizing multilayer multibeam representation in large-aperture NR CSI codebooks, with range states providing complementary refinement.
Read the full abstract
Computer Vision
EgoPathBench: Evaluating Zero-Shot Egocentric Waypoint Decision-Making in Vision-Language Models
Zero-shot waypoint navigation requires vision-language models to select, from the current first-person observation, a sequence of spatial actions that is feasible for the agent and reaches the goal, placing joint demands on the integrated spatial intelligence of today's foundation VLMs. Existing spatial-intelligence benchmarks primarily evaluate isolated judgments of relations, directions, or targets and therefore do not directly measure the integrated navigation ability required to combine target recognition, action-consequence assessment, distance estimation, and path planning. To fill this evaluation gap, we introduce EgoPathBench, a dataset and five-task benchmark for first-person waypoint decision-making. Each question presents an egocentric RGB image, a natural-language goal, and numbered visible waypoints; a model returns traversable candidates or an ordered route. Predictions are evaluated for candidate feasibility, adjacent-edge legality, and goal arrival under point-agent or embodied geometry. EgoPathBench contains 31,852 training, 1,345 validation, and 1,111 benchmark questions and retains at least one geometrically verified reference route for every route question. Across nine VLMs, the highest EgoPath Score is only 28.3. The top-ranked model reaches 35.9% success on Point Path, but only 2.9% and 4.0% on Embodied Path and Intent Path, respectively, showing that current models remain limited in forming complete, goal-consistent routes under embodiment constraints. Beyond the evaluation data, we release the corresponding training resource. Fine-tuning Qwen 3.5 4B on the released training split raises its EgoPath Score from 3.9 to 38.9 and improves all four reported evaluations across three external spatial benchmarks, with gains of 1.4–9.6 points.
Read the full abstract
Quantum Physics
Floquet Dressing and Bath Spectral Effects on the Geometric Phase of a Driven Dissipative Qubit
The geometric phase (GP) of a periodically driven symmetricspin-boson model (SBM) is investigated using the process-tensor time-evolving matrix product operator (PT-TEMPO) method. A longitudinal monochromatic field drives the qubit along the same coordinate that couples to an Ohmic bosonic environment. The gauge-invariant kinematic GP is evaluated from the reduced-statetrajectory, and a circular non-additivity measure quantifies the combined effects of driving and dissipation relative to driven-unitary and undriven-dissipative references. Amplitude, frequency, coupling-strength, and bath-cutoff sweeps reveal regimes in which periodic driving reduces or enhances environmental phase deformation relative to the unitary counterpart. The one-cycle GP exhibits pronounced nonmonotonic drive frequency dependence, while its bath-induced shift depends sensitively on both coupling strength and cutoff. These trends are interpreted qualitatively in terms of Floquet dressing and bath spectral structure. A two-cycle echo provides a complementary reversibility diagnostic, whose persistence signal does not generally measure the Tong GP. The results characterize the non-additive influence of driving and dissipation on geometric-phase dynamics and identify parameter regimes of reduced bath-induced deformation.
Read the full abstract
Quantum Physics
Strong converse for the quantum capacity of the pure-loss bosonic channel
This paper reports the proof of a strong converse for the unconstrained quantum capacity of the pure-loss bosonic channel. At every fixed rate above capacity, the entanglement-generation fidelity of every code is bounded by a constant times the reciprocal of the number of channel uses. The bound holds without an energy constraint and for arbitrary encoded states, including states correlated across all input modes, and arbitrary joint decoders. The proof combines quantum Chebyshev and hockey-stick testing inequalities with a uniform relative-entropy-variance bound for the balanced pure-loss channel, corresponding to transmissivity $\eta=1/2$. The variance bound follows by expressing the balanced beam splitter in bright and dark modes: the dark modes are exactly in vacuum, and any state orthogonal to that vacuum contains at least one dark photon. For general transmissivity, dilating the degrading attenuator reduces the problem to this balanced-channel setting and bounds the decoder test by precisely the factor that produces the known quantum-capacity threshold. The resulting argument establishes the strong converse at the unconstrained quantum capacity for every pure-loss bosonic channel.
Read the full abstract
Information Retrieval
Measuring Decision-Scale Use in Tool-Augmented LLMs: A Contrastive Urban Benchmark
Urban decision-support often asks whether activity is unusually high or low for a specific place, not which place has the larger raw count. Twenty pickups in a quiet neighborhood can be more abnormal than 180 at an airport. We introduce URBANCONTRASTIVEQA, a benchmark that asks whether tool-augmented language models can make this baseline-relative comparison. Each item pairs two urban situations from public mobility data in NYC, Chicago, and Seattle, labeled by how far current activity deviates from that place's historical baseline. We evaluate six instruction-tuned models under five tool-output formats. With only raw counts, models often pick the larger number even when it is less abnormal for its zone. Server-computed baseline scores and ordinal labels raise accuracy, but gains vary by model. For heterogeneous urban feeds, tool interfaces need to expose local baselines, not just activity volumes. We release the pair bank, labels, scoring scripts, and data card.
Read the full abstract
Machine Learning
A Weighted Kernel Method for Approximation that Adapts to Learned Multivariable Structure
Approximating the input-output behavior of a multivariable black-box function from limited data is challenging when blind to the importance of its inputs and their interactions. We introduce total sensitivity kernels (TSKs), a method based on families of weighted ANOVA kernels that learn and adapt to this multivariable structure. TSKs parameterize the weights on each multivariable component of the target function by factors for each input. We propose learning these factors directly from function evaluations by selecting the reproducing kernel Hilbert space (RKHS) in which the target function has minimum norm. Under suitable conditions, we show that this norm-minimization problem admits a unique solution, and we establish consistency of a finite-data formulation based on minimum-norm interpolation. The learned TSK factors characterize the participation of individual inputs across interactions and main effects, providing a kernel-dependent notion of input sensitivity related to total Sobol indices. Numerical experiments demonstrate that adapting the kernel to learned multivariable structure can substantially improve approximation accuracy over a standard product kernel.
Read the full abstract
Software Engineering
An Exploratory Study of Dependabot Cooldown Adoption in Open-Source GitHub Projects
Automated dependency updates can rapidly propagate malicious package releases before maintainers and the broader community have enough time to detect them. In July 2025, GitHub made Dependabot cooldown generally available as a defense against software supply chain attacks. However, the effects of its early adoption remain unknown. In this exploratory study, we empirically examine how popular open-source GitHub repositories adopt and configure the feature and investigate their motivations. We find that security concerns motivated 83 of 92 adoption events with known motivations. Security linter warnings triggered 43 of 75 security-only adoptions. Among 251 ecosystems within repositories that retained cooldown, 97.2% set a general delay. Of these, 64.3% used seven days, while use of each update type setting was below 10%. Early adopters therefore favor simple default delays over fine-grained controls. These findings suggest that tools could provide robust defaults reflecting ecosystem support and reserve fine-grained controls for dependencies with clear update priorities.
Read the full abstract
Software Engineering
ExecuCritic: Calibrated Critic Shaping for Code Generation with Verifiable Rewards
Execution feedback is a useful supervision signal for code models because unit tests are objective and directly measure program correctness. Its weakness is that an entire program is often reduced to one pass or fail bit, leaving RLVR to solve a difficult credit assignment problem. At the same time, coding systems often include separate reviewer or tester roles, but these critics are usually prompted rather than trained and are not calibrated against execution. We propose ExecuCritic, a joint training framework in which a coder and a critic are updated on the same execution rollouts. The critic predicts pass or fail outcomes and gives short diagnostic feedback; the coder uses this signal only when the critic agrees with the executor on the current rollout group. Across eight code benchmarks and two recent open backbones, ExecuCritic improves over GRPO without a critic, prompted reviewer systems and scalar reward model baselines, while requiring fewer policy gradient steps and fewer sandbox executions. Ablations and reliability analyses suggest that the gains come from better credit assignment rather than larger sampling budgets.
Read the full abstract
Computer Vision
G3AR: Graph-Guided Neural Visual Geometry for Scalable Multi-Sequence Aerial Registration
Full-context neural visual geometry is impractical for thousands of images, while sequence-based chunking poorly captures irregular non-local overlap in multi-sequence aerial collections. We present Graph-Guided Neural Visual Geometry for Aerial Registration (G3AR), a graph-guided framework for scalable dense neural geometry. Before local inference, G3AR builds a geometrically verified image-proximity graph that guides bounded overlapping chunks and induces a chunk graph whose maximum spanning tree defines alignment topology. Compatible backbones process chunks independently; shared-image predictions then estimate three-dimensional similarity (Sim(3)) transforms that register local cameras and geometry in a common frame. Across four real aerial scenes, G3AR improves pose error and runtime in matched VGGT- and Pi3-backed comparisons, while its DA3 variant achieves the lowest pose error among evaluated neural-geometry methods.
Read the full abstract
Algebraic Geometry
Punctured log Gromov-Witten theory of log modifications and double ramification cycles with target log variety
We expand upon a previous study conducted by the author on the behavior of punctured log Gromov-Witten theory under log étale modifications $\widetilde{X} \rightarrow X$, giving expressions for log Gromov-Witten classes on $\widetilde{X}$ in terms of log Gromov-Witten classes on $X$, facilitating a complete reduction of the punctured log Gromov-Witten theory of any modification $\widetilde{X}$ of an snc log scheme $X$ to the punctured log Gromov-Witten theory of $X$. We apply this result in two settings. First, we prove a log-orbifold correspondence equating the logarithmic invariants of the canonical wall structure of Gross and Siebert with a class of orbifold invariants considered in the relative quantum cohomology ring of Tseng and You, and more generally construct a family of algebra homomorphisms from the intrinsic mirror algebra $R_{(X,D)}$ of Gross and Siebert to appropriate power series rings. Second, we show the punctured log Gromov-Witten classes of split toric bundles are effectively reconstructed in terms of the punctured log Gromov-Witten classes of the base. Additional input for the second application is the introduction and study of double ramification cycles with target log variety, generalizing the double ramification cycles with target variety investigated by Janda-Pandharipande-Pixton-Zvonkine.
Read the full abstract
Computer Vision
SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation
Multimodal large language models (MLLMs) have made strong progress on visual question answering and image captioning, yet they still produce fluent claims about objects, attributes, or relations that are not grounded in the image. Many remedies either modify decoding at test time, which adds latency, or fine tune with preferences such as DPO variants, which teach which answer is preferred but not when the model's own answer is unreliable. We argue that calibrated self assessment is the missing signal. We introduce Savor, a training framework that (i) augments the output schema with token and answer confidence, (ii) optimises the policy with a Group Relative Policy Optimisation (GRPO) objective that penalises calibration error and poor abstention decisions, and (iii) uses the learned confidence at inference time to revisit visual evidence only when the model is uncertain. Experiments on POPE, HallusionBench, AMBER and MMHal-Bench across two recent backbones (InternVL3-8B and Qwen3-VL-8B) show that Savor reduces hallucination while preserving general capability on MME and MMBench, with lower Expected Calibration Error than DPO and decoding baselines.
Read the full abstract
Hardware Architecture
A 420 GOPS/W CGRA with a Configurable MAC and Dynamic Truncation
Edge devices demand for highly efficient yet flexible processing capability to handle dynamic real-time workloads. Coarse grain reconfigurable architecture (CGRA) emerges as a suitable accelerator candidate in edge devices, because they are as flexible as general purpose processors and offer high efficiency close to that of domain specific accelerators. However, a typical CGRA requires two cycles for a multiply-and-accumulate (MAC) operation, and workloads such as neural network inference and signal processing involve many MAC operations, resulting in long CGRA processing time. This work proposes a CGRA that has configurable MAC units in the processing elements (PEs) that can perform an addition (ADD) or multiplication (MUL) or a MAC by using the same multiplier and adder, in a single cycle. The readout precision of MAC result can be adjusted by a truncation block. The proposed CGRA is implemented with 40nm CMOS technology. It attains an energy efficiency of 420.6GOPS/W operating at supply of 0.6V and frequency of 21MHz, which is 1.4 times higher than the state-of-the-art.
Read the full abstract
Systems and Control
Large Language Models in the Loop: A Stability- and Network-Aware Survey in Networked Control, Cyber-Physical, and Multi-Agent Systems
Modern networked control systems (NCSs), cyber-physical systems (CPSs), and complex multi-agent network systems (CNSs) increasingly rely on large language models (LLMs) for high-level decision-making. However, the slow, stochastic nature of LLMs directly conflicts with the strict stability and safety guarantees required by these physical systems. This survey presents a unified analysis of how LLMs can be admitted into the control loop of NCS, CPS, and CNS without compromising closed-loop guarantees. We organize this around a core principle: the LLM operates as a slow supervisor adjusting high-level goals and constraints, while a fast, certified inner loop maintains physical stability. Under this framework, LLM integration maps directly to classical networked control challenges, where inference latency acts as delay, API failures as packet dropouts, tokenization as quantization, and hallucinations as bounded disturbances. We assess current developments across all these three domains, highlighting that rising model capabilities are frequently accompanied by a drop in formal safety assurances. Finally, we propose concrete future research directions, identifying the widespread lack of formal stability proofs as the field's central open problem.
Read the full abstract
Human-Computer Interaction
CATVis: A Collaborative Multi-Agent Workflow for Turbomachinery Simulation Data Visualization
Recent advances in AI for Science have enabled natural language (NL) interfaces for scientific data analysis. In turbomachinery CFD post-processing, translating ambiguous high-level analytical goals (e.g., vortex identification) into precise visualization procedures supporting complex domain-specific analysis is challenging. We present CATVis, a Collaborative multi-agent workflow system that bridges this gap by transforming NL intents into structured middle representation for visualization. Our approach reformulates domain-specific visualization procedures as composable workflow representations, and use multi agent to generate workflow representations via intent planning, template generation, and error-aware refinement, where each stage incrementally updates a shared structured representation. We evaluate the impact of external knowledge and workflow structuring on generation accuracy, demonstrating that the proposed approach significantly improves complex workflow generation correctness while reducing prompt complexity.
Read the full abstract
Computer Vision
A Vision-Language Foundation Model for Precise and Comprehensive Brain Tumor Diagnosis from Preoperative Multimodal Data
We developed BrainVLM to classify all 12 World Health Organization (WHO) 2021 brain tumor types. BrainVLM integrates an uncertainty quantification strategy to indicate prediction reliability and a module for generating radiology reports to elucidate the clinical rationale. BrainVLM was trained on multi-modal data (MRI scans, demographics, and radiology reports) from 40,043 individuals. It was validated on 5,211 patients with pathologically confirmed brain tumors, including 3,877 held-out patients from the primary hospital and 1,334 patients from 11 independent hospitals. We further conducted two proof-of-concept studies to validate its clinical utility in AI-clinician workflows: 1) a blinded multireader study where 12 neuroradiologists across varying experience levels interpreted 248 retrospective cases with or without AI assistance, and 2) a real-world prospective study in which 1,009 patients were independently and blindly assessed by BrainVLM and radiologists before surgery. Additionally, we demonstrated BrainVLM's utility in preoperative molecular subgroup prediction for adult-type diffuse gliomas, using a multi-center cohort of 632 patients. In primary evaluation, BrainVLM achieved an area under the curve (macro-AUC) of 0.85 (95% CI: 0.84-0.86), and an F1 score of 0.82 (95% CI: 0.81-0.83), surpassing neuroradiologists (F1 = 0.80 (95% CI: 0.79-0.81)). In external validation across 11 centers, BrainVLM achieved an AUC = 0.80 (95% CI: 0.79-0.82) and F1 = 0.75 (95% CI: 0.73-0.78), compared with F1 = 0.71 (95% CI: 0.69-0.73) for neuroradiologists. In prospective real-world evaluation, BrainVLM maintained performance comparable to neuroradiologists. The BrainVLM project page is available at https://hku-healthai.github.io/brainvlm_project.github.io/.
Read the full abstract
Combinatorics
On the number of palindromic factors of low complexity words
Factor complexity counts the distinct factors of each length in an infinite word, while palindromic complexity counts those invariant under reversal. For recurrent aperiodic words with reversal-closed language, the total number of palindromic factors in two consecutive lengths is at most the one-step growth of factor complexity plus two. We prove that equality is forced whenever the factor complexity at a given length does not exceed three halves of that length plus one. We construct examples showing that the bound is optimal. We also obtain an adaptive local criterion and consequences for reversal-closed quasi-Sturmian words and palindromic defect.