Papers

Kolmogorov-Arnold Networks (KANs) with spline activations have recently shown promise for interpretable function approximation. Distance-Aware Error for Kolmogorov Networks (DAREK) introduces a computationally efficient bottom-up approach to uncertainty quantification by equipping KANs with distance-aware error bounds; yet, in high-dimensional settings, the theoretical guarantees can be weakened by the emergence of fictitious knots. Inspired by the Kolmogorov-Arnold representation theorem, DAREK adopts a componentwise formulation in which each input dimension is treated separately; as a result, induced knot locations may appear in the combined input space without corresponding to actual training data. These fictitious knots mislead the DAREK uncertainty estimator into reporting low uncertainty far from any real observation, violating the distance-awareness guarantee. We identify this failure mode precisely, characterize its geometric structure, and propose a drainage uncertainty mechanism that restores distance-awareness by constructing a monotonically decreasing uncertainty path from any fictitious knot region toward the nearest real knot. The proposed drainage method provides a practical heuristic correction that mitigates the fictitious-knot failure mode while restoring theoretical distance-awareness in high-dimensional settings. Experiments on a 2D synthetic benchmark and a 100-dimensional face dataset show that drainage raises sampled distance-awareness (SDA) from 85% to 98-99%, matching Gaussian processes at lower computational cost.

We revisit Valiant's algorithm (Commun. ACM'84) for learning $n$-variable CNF formulas with clause size $k$ and variable degree $d$ from i.i.d. uniform random solutions in the local lemma regime. For fixed $t\geq1$, under $k\gtrsim(1+1/t)\log d$, Valiant's algorithm achieves total variation error $\varepsilon$ with $\widetilde{O}(n^{\lceil t \rceil}/\varepsilon)$ sample complexity. For $t>1$, we prove a matching lower bound for Valiant's algorithm. At $t=1$ (covering $0<t<1$), we show Valiant's algorithm has optimal sample complexity up to logarithmic factors by an information-theoretic lower bound $\widetilde\Omega(n/\varepsilon)$.

Trajectory curvature constraints are inherent in practical multi-robot systems due to the limited turning capabilities of the robots. Without properly accounting for these constraints, robots may fail to accomplish assigned tasks, and their trajectories may diverge from the intended paths. This paper proposes a distributed safe cooperative vector field approach for multi-robot systems subject to trajectory curvature constraints. The proposed approach is composed of a cooperative vector field and a safety-oriented collision avoidance vector field, aiming to address the problems of cooperative motion and safe collision avoidance in multi-robot path-following tasks. A safety-oriented collision avoidance vector field with adaptively adjustable reactive boundary is developed to accommodate the kinematic curvature constraints of robots, thereby ensuring the physical feasibility of collision avoidance maneuvers. The proposed vector field requires only a single virtual variable from each neighboring robot to achieve cooperative motion and ensure both obstacle avoidance and inter-robot collision avoidance. The effectiveness of the proposed approach is validated through both simulations and real-world experiments on an actual multi-robot platform.

We analyze a stochastic algorithm with Halpern-type anchoring for constrained convex-concave problems and monotone variational inequalities. This single-loop and single-call algorithm uses one unbiased sample of the gradient operator at every iteration, to be applicable to monotone games with noisy feedback. With $t$ denoting the iteration counter, we prove an anytime last-iterate convergence rate of $O(t^{-1/4})$ for both the gradient-mapping norm and restricted gap, bypassing the $O(t^{-1/5})$ constrained-anytime bottleneck in the literature. Specializing then to multi-point oracles, we use variance reduction to achieve the $O(t^{-1/2})$ rate with an anytime single-loop algorithm using $2$ samples per iteration. Our results allow constrained problems with a potentially unbounded feasible set; as well as a structured class of stochastic oracles whose variance need not be uniformly bounded.

Advanced artificial intelligence models think in tokens; contemporary communication systems carry bits. The direct way to bridge this gap is to transmit tokens, but that makes a model-specific representation part of the air interface, coupling the endpoints through a shared tokenizer, codebook, and often a neural transceiver. We take a different route: keep bits in the payload and let tokens control how those bits are generated and protected. The resulting token-bit interface transition aligns task-side tokens with source- and channel-coding units, translates token relevance into codec controls, and preserves the induced priority order across the coding chain. We instantiate it for image classification, where a vision transformer scores the task relevance of each image region from its attention maps: those scores steer block-wise JPEG rate allocation, then group the compressed bits for protection at different polar-code rates. The payload remains an explicit, reconstructable bitstream recovered by a correspondingly configured decoder. Over-the-air experiments on a software-defined radio testbed show improved accuracy–latency tradeoffs over separate source-channel coding, performance competitive with far more memory-intensive neural joint source-channel coding, and graceful degradation under channel mismatch. Token communication, then, need not transmit tokens explicitly; what it needs is an interface through which tokens determine how bits are communicated.

Ecological monitoring increasingly relies on machine learning models, whose performance depends on the quality and quantity of labelled data. However, obtaining these labels is costly, particularly in passive acoustic monitoring, where vast amounts of data are collected but only a small proportion can feasibly be annotated. Active learning addresses this bottleneck by prioritizing which samples should be labelled. However, progress is difficult to measure, because published methods are evaluated under different models, budgets, evaluation metrics and datasets. To address this challenge, we present the 2026 Active Learning for Bioacoustics BioDCASE challenge: a systematic evaluation of sampling methods designed to identify effective AL strategies. Participant methods were evaluated across four subsets composed of terrestrial and marine data. Across ten proposed sampling methods from seven teams, the top-ranked method achieved an area under the learning curve 26.4 % higher than random sampling at the same annotation budget, averaged over four data subsets. Significant variation in performance was observed across subsets, with the top-performing submission achieving a 67.1 % gain for the HSN subset over random sampling and a gain of 8 % for the ATBFL subset. Top-ranking submissions combined multiple acquisition signals, and diversity-based selection outperformed pure uncertainty sampling. Furthermore, there is evidence that transitioning from diversity-based to uncertainty-based selection and explicitly reducing redundancy within acquisition batches improve model training. There is also initial evidence that larger acquisition batch sizes may be increasingly beneficial later in the labelling process.

Conformal counterfactual prediction constructs prediction sets with finite-sample coverage guarantees for counterfactual outcomes and individual treatment effects under the no-interference assumption. In this work, we relax this assumption by allowing each unit's potential outcomes to depend on other units' treatments and covariates. In this setting, propensity-score reweighting does not restore weighted exchangeability, and existing methods may fail to achieve valid coverage. To address this issue, we develop interference-adjusted weighted conformal prediction that accounts for interference by constructing an observable upper bound on the ideal and unobserved conformal $p$-value under the target intervention. The resulting prediction sets provide finite-sample marginal coverage guarantees for counterfactual outcomes and individual treatment effects in both transductive and inductive settings. We also derive a sharper construction when intervention-induced changes in nonconformity scores are bounded. Numerical experiments show that our methods preserve nominal coverage, whereas existing methods may not.

Technical systems are increasingly monitored using sensor and operational data to detect degradation and performance deterioration at an early stage. However, observed trends in measurement data do not necessarily correspond to physical aging, since noise, outliers, unstable initial regions, or changing operating conditions may produce similar patterns. This paper proposes Trend-based Reference Evaluation for Degradation Detection (TREDD), an interpretable method for detecting degradation as a persistent, trend-based deviation from an early reference state. TREDD combines rolling-window smoothing, baseline estimation, a direction-dependent degradation index, long-term trend extraction, and persistent drift detection. In addition, the method separates computational drift detection from the interpretation of drift as plausible physical aging by incorporating data-quality assessment, context checking, and robust auxiliary analysis. The approach is evaluated on the NASA Lithium-Ion Battery Aging Dataset using discharge-cycle capacity as the degradation-relevant condition variable. The representative case study illustrates that TREDD can identify clear degradation trajectories while assigning reduced confidence to weak, gradual, or atypical trends. The method therefore supports transparent and confidence-based degradation interpretation rather than purely predictive battery health estimation.

In bandits with probing, a learner selects at most $k$ of $n$ arms per round, earns the largest of their rewards, and competes with the best fixed single arm. For independent arms with i.i.d. rewards in $[0,1]$ and $2\le k<n$, the minimax regret is $\Theta\bigl(\frac{n-k}{n}\min\{T,n/k\}\bigr)$, the cost of locating an unknown good arm, and observing only the maximum suffices to attain it. In particular, two probes give $\Theta(\min\{T,n\})$ regret, which resolves two open questions of Bhaskara et al. (2023) with weaker feedback. Our policy turns the probing surplus, the excess of the maximum over each probed arm, into exploration capital, and a permanent random core yields the sharp dependence on $k$. On arbitrary fixed reward arrays, same-round contrasts between blocks of arms attain the same rate, because the surplus pays for the stability of mirror descent. Winner feedback, the maximum together with its winning label, instead incurs an additional learning cost under joint i.i.d. rewards and on fixed arrays. We characterize this cost even when values are revealed only intermittently, using policies that know neither the horizon nor the revelation rate. For three independent arms and two probes, exact maxima, Bernoulli-rounded maxima with winning labels, and winning labels alone have minimax regret $\Theta(1)$, $\Theta(\sqrt T)$, and $\Theta(T)$: rounding preserves conditional means but not the rate.

The single-source shortest paths (SSSP) problem in graphs with non-negative edge weights is one of the most classic problems in algorithms. For decades, the best known running time in the comparison-addition model was the $O(m+n\log n)$ bound of Dijkstra's algorithm with Fibonacci heaps. Recently, Duan, Mao, Shu, and Yin (FOCS'23) gave a randomized $O(m\log^{1/2} n \log\log^{1/2} n)$-time algorithm for SSSP in weighted undirected graphs. For weighted directed graphs, Duan, Mao, Mao, Shu, and Yin (STOC'25) gave an $O(m\log^{2/3} n)$-time algorithm for SSSP. Very recently, Duan, Mao, Shu, and Yin (ICALP'26) obtained an algorithm for directed graphs whose running time matches the $O(m\log^{1/2} n \log\log^{1/2} n)$ time of the undirected case. In this paper, we present a faster algorithm for SSSP in weighted undirected graphs, giving the first improvement in running time since the FOCS'23 breakthrough of Duan, Mao, Shu, and Yin. Our algorithm runs in $O(m\log^{1/2} n \log\log^{1/4} n \log\log\log^{1/4} n)$ time, improving the previous running time by a factor of $(\frac{\log\log n}{\log\log\log n})^{1/4}$. Our main contribution is a simple and efficient tool that computes, for every vertex, its distance to the nearest vertex in a random sample; this tool may be of independent interest.

Thickness is a critical geometric attribute in Design for Manufacturability (DFM), yet its computational analysis in CAD environments remains largely process-agnostic. Existing approaches rely either on inscribed-sphere or ray-casting methods, each carrying limitations that make them poorly suited as universal solutions across manufacturing processes. This paper presents a process-aware thickness analysis system for parts intended for molding and milling, where the geometric method is selected and its outputs interpreted according to the DFM rules meaningful to each process. For molding, the sphere-based method detects maximum thickness violations and wall non-uniformity, and segments parts into distinct thickness zones. For milling, ray-casting identifies regions of insufficient thickness and detects thin features prone to deflection or failure. Validation on representative parts demonstrates that this hybrid approach surfaces process-specific manufacturability issues, offering designers actionable geometric feedback early in the design cycle.

We propose a dissipative, irreversible damage model for anisotropic media in large deformations to address the damage process of the myocardium following a cardiac infarction. We model damage to the collagen in the cleavage planes resulting from an increased load to the passive tissue. Starting from variational principles, we derive a quasi-static differential model governing the irreversible evolution of the damage. We apply our model to two test cases. First, a rectangular passive slab geometry to which an indenter-like load is applied. Then, we couple our model with a model for the numerical simulation of left ventricular electromechanics. Our results show that a redistribution of the load within a left ventricle occurring following a cardiac infarction can produce the damage to the collagen scaffold in the infarcted area consistent with experimental results. This is indicative of the fact that passive load-dependent dissipative phenomena are implicated in post-infarction remodelling.

Environmental, Social, and Governance (ESG) reporting is critical for corporate accountability, with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) offering strong potential to automate KPI extraction. However, open-source LLM performance in domain-specific ESG tasks remains insufficiently understood. This paper evaluates open-source LLMs in ESG contexts using a structured framework and evaluation resource based on 498 real-world ESG reports from EU-listed companies (2010-2024). We evaluate seven open-source models (2B to 30B parameters) – glm-4.7-flash, nemotron-3-nano:4b, qwen3:4b-instruct, gemma3:4b, gemma4:e4b, gemma4:e2b, and ministral-3:8b – using 100 persona-based synthetic QA pairs covering ESG information needs. System performance is assessed via RAGAS metrics, including contextual recall, precision, relevance, faithfulness, answer relevancy, and factual correctness. Results show notable performance variations across architectures. Retrieval performance is strong across models (context recall around 0.58-0.61, context precision around 0.78-0.81, context relevance 0.965-0.985). Generation diverges most on faithfulness (0.607-0.822) and least on answer relevancy (0.760-0.881): glm-4.7-flash leads in faithfulness (0.822), qwen3 in factual correctness (0.449), and ministral-3 in answer relevancy (0.881). Low overall factual correctness (0.387-0.449) highlights the need for domain-specific fine-tuning. This work provides data-driven guidance for deploying open-source models in ESG reporting.

Dynamic-vision-sensor (DVS) cameras generate events on a per-pixel basis with a $\mu$s-level temporal resolution, calling for new algorithm-hardware co-design approaches compared to standard frame-based vision. While event-driven graph neural networks (EV-GNNs) emerge as a promising algorithmic solution, they raise new HW challenges by mixing dense-regular compute operations and sparse-irregular memory accesses. We present ETHEREAL, the first EV-GNN accelerator that scales to 640$\times$480 resolutions, thanks to a neighbor-parallel spline convolution engine and a 2D/3D-split memory hierarchy with a novel region-of-interest spatiotemporal caching mechanism. Measurement results demonstrate end-to-end inference with 25.6$\mu$s latency and 1.7$\mu$J energy per event on state-of-the-art workloads

What did an ancestral bird species sound like? Existing ancestral state reconstruction methods can infer low-dimensional traits such as morphological characters at internal nodes of a phylogenetic tree, but no one has tried to produce rich perceptual signals such as audio. Some of the challenges include inferred representations that are either too low-dimensional to decode or lie in non-generative feature spaces, so no method to date can produce ancestral audio. We introduce the first framework that generates plausible ancestral vocalizations. Our pipeline encodes bird recordings into a VAE latent space, learns a low-dimensional trait projection aligned with phylogenetic distances, performs ancestral inference in this trait space, and recovers decodable latents through an anchored inverse lift before emitting novel waveforms for each ancestral node. Because the entire pipeline stays within a decodable latent space, every internal node receives a genuinely new audio output representing plausible intermediate ancestral sounds unavailable to retrieval-based alternatives. Experiments on two phylogenetically distant bird clades, 21-species Tyrannidae and 19-species Paridae, show that our method is the only approach that simultaneously achieves genuine generation, phylogenetic consistency, and naturalistic audio quality across both datasets.

Discrete diffusion models are a prominent family for graph generation, but standard class-conditional mechanisms embed the class signal in the denoiser during training, tying the conditioning mechanism to the trained model. Classifier guidance avoids this coupling in continuous domains by steering a frozen model with a classifier's gradient, but discrete graph diffusion samples discrete edge states, so gradients cannot propagate through the sampled graph. We introduce ProtoGuide, a post-hoc, backbone-agnostic framework that recovers an analogous mechanism. At each reverse step the denoiser's per-edge output is relaxed into a differentiable soft adjacency, embedded by a frozen Siamese graph neural network, and scored against a target-class prototype and its nearest competitor; the resulting per-edge gradient, damped by a cosine schedule, is injected back into the denoiser output. All components stay frozen, so guidance is retargeted by supplying a different prototype. On five classes of real-world networks and two architecturally different backbones, EDGE and DiGress, ProtoGuide raises macro classification accuracy from 50.7% to 73.5% and from 73.6% to 83.8%, and outperforms DiGress's built-in conditional training under our configuration. Gains are largest where the unguided models are weakest, and are not uniform across classes. Per-graph coverage remains high in most settings, while distributional effects are class-dependent. A Best-of-N selection baseline matches this accuracy given enough oversampling, but at a substantial cost in graph diversity. An independently initialized classifier, a directionality test, and a few-shot analysis support target-directed steering and robustness to very small support sets.

Protein-protein interaction databases record evidence without weighing it. In BioGRID, an interaction asserted once by a single high-throughput screen and one confirmed by twenty laboratories across a dozen assays are the same kind of row in the same file. Tools built on such databases inherit that flattening: they draw every reported interaction as an edge, and the resulting picture states that two proteins interact without stating how much anyone should believe it. We present ProLiVis 2.0, a rewrite of the literature-centric visualization system of arXiv:2111.12794. It contributes three things. First, a citation-trust model that scores each interaction from seven terms, including a term for the number of independent laboratories behind the supporting publications, obtained by clustering those publications over shared institutional affiliations; a plain count of publications cannot distinguish five confirmations from one group publishing five times. Second, a deterministic reformulation of the center layout, closed-form and $O(n \log n)$, which replaces the force-directed placement of the original and makes published figures regenerable from a session manifest. Third, an implementation that runs entirely in a web browser, with an embedded analytical database, requiring no installation and uploading no data. On BioGRID release 5.0.260 restricted to SARS-CoV-2, 24,344 of 34,540 reported interactions (70%) rest on a single publication, and raising the trust threshold to 0.2 leaves 11,320 of them. That the large majority of a curated interaction network is unreplicated is a fact no existing view of the database makes visible.

Recently, Large Language Models (LLMs) have gained significant attention due to their strong language understanding and generation capabilities, demonstrating impressive reasoning abilities as well as effective utilization of external knowledge. Many studies have proposed methods that specialize in improving performance for individual tasks. However, ironically, only a limited number of attempts have explored general-purpose, task-agnostic methods. In this work, we present a unified framework integrating reasoning and Retrieval-Augmented Generation (RAG) tasks. We further propose Controllable White-Box Meta-Prompting (CWM), a low-cost white-box method for adaptive RAG tasks previously dominated by black-box approaches, without requiring external decision modules or multi-sampling. CWM achieves state-of-the-art performance on three adaptive RAG benchmarks across recent LLMs, including GPT-oss-20b, Qwen3-14b, and Llama3.1-8b, while also demonstrating strong generality by extending to reasoning tasks. In addition, CWM provides controllability by enabling retrieval decisions to be regulated through the manipulation of internal model signals. Our code is available at https://github.com/JeongEunhye00/CWM.

The introduction of human-robot collaboration (HRC) in industrial assembly operations is revolutionizing the manufacturing landscape. In this evolving environment, operators are required to seamlessly coordinate their manual tasks with real-time task information and robotic behaviors. These demands fluctuate during operation, yet conventional workload assessments depend on body-worn physiological sensors that complicate practical deployment. Here, we present a vision-based attention–action framework for continuous and interpretable workload-related assessment in HRC assembly. The framework combines RGB-D observations with robot states and calibrated task-related areas to construct a temporally confirmed representation of operator behavior. This representation identifies where task demand is concentrated and explains how it develops when attention and action diverge, the task context changes, or the operator hesitates. We evaluated the framework in a three-level collaborative gearbox assembly experiment with ten participants, using subjective ratings and synchronized physiological signals as independent references. Raw NASA-TLX ratings confirmed increasing perceived workload across conditions, with significant effects on overall workload and its mental and temporal dimensions. The vision-derived HRC-CWL output was significantly associated with ECG-derived features in seven of nine participants with complete correlation data. Synchronized interaction episodes further showed temporal correspondence between detected hesitation and physiological activity. Real-time deployment demonstrated that the framework can operate without requiring operators to wear additional sensors. These findings support HRC-CWL as an interpretable behavioral proxy for cognitive ergonomics analysis and adaptive robot assistance, rather than a direct psychophysiological measure of workload.

Large language model (LLM) inference in AI datacenters creates a coupled control problem between GPU serving and facility cooling. Raising ambient temperature setpoints can reduce cooling energy and carbon, but also shrinks thermal headroom, induces GPU throttling, and leads to Service-Level-Objective (SLO) violations. In this paper, we study joint cooling–computing control for LLM inference: minimizing per-job GPU-plus-cooling energy while satisfying thermal safety and latency SLO constraints. We present ETCInfer, an energy-efficient, thermal-aware scheduler that selects a pre-job Computer Room Air Conditioner (CRAC) setpoint and adapts per-GPU frequency and micro-batch size during execution. ETCInfer builds compact physics-informed control models by calibrating GPU heat generation, chassis heat dissipation, CRAC power, and prefill/decode latency relations from telemetry. These models estimate hidden thermal states and time-to-throttle, enabling the scheduler to evaluate energy, temperature, and latency before applying an action. We formulate this joint setpoint–frequency–micro-batch control problem as a partially observable Markov decision process and design ETCAdapter, a learning-based controller that minimizes per-job energy under thermal safety and SLO constraints. We implement ETCInfer as a coordination layer over typical inference and cluster management stacks. Evaluation across real-trace simulation and validation experiments shows that ETCInfer reduces total job energy by up to 33.1%, thermal throttle exposure by up to 92.9%, and keeps SLO violation rates below 0.7% even at ambient temperatures up to $48^{\circ}\mathrm{C}$.

We propose a pre-fine-tuning probing method for Parameter-Efficient Fine-Tuning (PEFT) layer selection, aiming to obtain more stable and higher gains with fewer trainable parameters when adapting large vision–language models (VLMs). Unlike the common practice of applying LoRA and other adapters to all layers at once—where layer selection often relies on heuristic rules—we focus on the vision encoder and directly evaluate the "adaptability” of each Transformer layer. Specifically, we characterize each layer from two perspectives: (i) the statistical properties of its Q/K/V projection weights (e.g., norms and condition numbers); (ii) robustness under controlled parameter perturbations. We then systematically compare these indicators with the downstream performance gains brought by applying PEFT to a single layer. Across experiments covering seven benchmarks and five PEFT variants, we observe a consistent correlation: layers (or matrices) with larger weight norms and higher condition numbers are usually more robust to perturbations and are more likely to yield larger fine-tuning gains. These results show that distribution-statistics analysis and perturbation tests before fine-tuning can provide practical signals for adaptation-layer selection, thereby maintaining or improving performance while reducing trainable parameters.

Unsupervised registration of large-scale LiDAR point clouds remains challenging due to the geometric ambiguity inherent in outdoor scenes, which degrades pseudo-label quality and leads to suboptimal convergence, particularly for sparse, low-resolution scans such as those from nuScenes. We reveal that registration models intrinsically encode semantic awareness that strongly correlates with registration accuracy, albeit without explicit semantic supervision. However, this native awareness is fragile: noisy supervision arising from geometric ambiguity in unsupervised settings rapidly erodes the learned semantic structure, causing performance collapse. To this end, we propose CAESAR, a teacher-student framework guided by an off-the-shelf 3D segmentation model exclusively during training. We observe that potential inlier matches are often buried just beneath a few spurious neighbors in the noisy feature space, motivating Dual-Cue Guided Re-Matching to recover them through reselection rather than simply rejecting. Building on this, a train-only Semantic-Geometric Label Mining performs lightweight, batch-specific teacher refinement and mines reliable pseudo-labels under semantic guidance. We further introduce Semantic Predictive Distillation to consolidate the student's semantic awareness in the feature space. Extensive experiments on KITTI and nuScenes demonstrate state-of-the-art performance, with pronounced gains on the challenging nuScenes benchmark. Crucially, CAESAR incurs zero inference overhead and requires no semantic annotations on the registration data. Code will be released.

While homographies are fundamental to many computer vision tasks, the majority of conventional estimation techniques provide only point estimates without directly quantifying uncertainty introduced by noisy observations. Uncertainty, though, propagates to subsequent processing steps such as camera calibration and 3D reconstruction and is particularly relevant in safety-critical and socially relevant fields including medical imaging, autonomous driving, and defense. We present a fast Bayesian formulation for homography estimation from point correspondences that explicitly incorporates measurement uncertainty and prior knowledge while providing a posterior distribution over the homography parameters. A closed-form solution of the posterior mean of the homography is derived in homogeneous coordinates and supplemented by an iterative Bayesian approach to handle non-linearities. Synthetic experiments demonstrate the applicability to projective transformations and show improved estimation accuracy over DLT under varying noise conditions. Image stitching experiments further demonstrate applicability to real image correspondences while additionally providing uncertainty information.

Objective: To develop an intelligent framework, termed CUA-Net, for the automated classification of congenital uterine anomalies (CUA) without requiring coronal plane reconstruction, and to evaluate its clinical applicability. Methods: CUA-Net was built on 3D ResNet-18, equipped with a dynamic data resampling strategy to mitigate the data imbalance issue and a hard sample mining technique to fully learn from the difficult cases by loss adjustment. We further proposed the self-supervised reconstruction to comprehensively explore the volumes and the online data augmentation to refine the wrong predictions and enhance the model's generalization. We compared the CUA-Net with different deep-learning methods and junior/senior sonographers in the testing set. The evaluation metrics included accuracy, precision, recall, F1-score, micro-AUC, and macro-AUC. Results: The proposed CUA-Net exhibited satisfactory performance in both internal and external test sets. In the internal cohort, the model achieved accuracy of 93.88%, precision of 87.01%, recall of 95.92%, F1-score of 88.09%, and micro-AUC of 0.9982 and macro-AUC of 0.9997. In the external set, it maintained good performance with accuracy of 91.52%, precision of 83.27%, recall of 88.63%, F1-score of 81.49%, micro-AUC of 0.9945 and macro-AUC of 0.9990. Our CUA-Net outperformed the junior sonographers across all performance indicators and achieved performance comparable to that of the senior sonographers across most metrics. Conclusion: The CUA-Net demonstrates favorable accuracy and generalizability in classifying common CUA categories, while showing preliminary potential for recognizing less prevalent anomalies. These capabilities may help optimize clinical workflows and support more standardized diagnosis.

We present LOVER, a \underline{L}ong to sh\underline{O}rt \underline{V}ideo \underline{E}vidence \underline{R}einforced model for grounded question answering (GQA). LOVER highlights three innovations over existing reinforcement-learning (RL) based video reasoning models: (1) Long-to-short Video Evidence Curriculum Learning, which organizes RL training according to evidence duration and progressively adapts the model from long-range grounding to short-term reasoning; (2) GQA Rewards, which underscore the benefit of IoP reward over IoU for evidence spotting rather than strict temporal span overlap; (3) Adaptive Timestamp Rendering, which adaptively renders timestamps onto video frames using background-aware position and color selection to enhance temporal observability. The three designs are model-agnostic and reciprocal. They effectively improve QA, grounding, and grounded QA performance over different backbones. Notably, LOVER built on Time-R1 achieves new state-of-the-art (SOTA) results among open-source models on popular GQA benchmarks: NExT-GQA and ReXTime. Comprehensive ablation studies further validate the effectiveness of our three innovative components.

In this paper we propose augmented Lagrangian finite element methods for cavitation in the Reynolds and Stokes models of lubrication, for which the discrete complementarity conditions hold exactly and the augmentation parameter drops out of the method. For the Reynolds equation this follows from nodal quadrature in a mixed piecewise linear method, for which we prove the classical first-order error estimate. We also determine the computable stability threshold of a multiplier-free stabilised alternative. For Stokes flow we show that the constrained scalar is the mechanical pressure when the deviatoric stress, with zero bulk viscosity, is used, but not with the customary incompressible stress. We discretise with a jump-stabilised Crouzeix-Raviart element and piecewise constant pressure, and prove well-posedness, stability in two and three dimensions, and a first-order error estimate. We present numerical examples which verify these properties and show that close pressure profiles in the two models do not imply close cavity predictions, the latter also being sensitive to the end conditions of the computational domain.

Passive acoustic monitoring can measure biodiversity at larger scales, but time–frequency annotation of animal vocalizations is expensive, site-specific, and difficult to sustain at scale. We present a label-efficient sound detection framework that combines masked audio pretraining with a lightweight detector on mel spectrograms, then further improves robustness through iterative self-training on unlabeled audio. We first pretrain a ViT-based encoder on unlabeled recordings via masked reconstruction and transfer the encoder to a detection backbone. To better separate animal sounds from confounding background, we add a box-level contrastive loss that pulls matched event regions together while pushing noisy negatives apart. We then apply a two-stage pseudo-labeling curriculum to exploit large unlabeled pools without additional annotation. We evaluate the performance on two ecologically distinct domains: tropical rainforest soundscapes (Indonesia) and bird vocalizations in Mediterranean habitats (Spain). On both domains, masked audio pretraining and contrastive learning consistently improve time–frequency detection under temporal and cross-site distribution shift, and self-training yields further gains in out-of-distribution performance. On the rainforest domain, MAST with self-training achieves +0.22 mAP and +0.24 F1 over the strongest baseline under cross-site shift. On the bird domain, self-training achieves +0.12 mAP and +0.10 F1 over the strongest baseline under cross-site shift. Overall, our results show that MAST can effectively extend self-supervised audio representations from clip-level tasks to robust box-level localization across diverse bioacoustic settings, providing a practical path for biodiversity monitoring with limited labels.

We study the weighted feedback vertex set problem in tournaments. For every fixed integer $k\geq 2$, we give a deterministic $(2+1/k)$-approximation algorithm with running time $n^{2^{O(k)}}$, apart from polynomial dependence on the encoding length of the weights. Consequently, for every fixed $\varepsilon>0$, weighted feedback vertex set in tournaments has a deterministic $(2+\varepsilon)$-approximation running in time $n^{2^{O(1/\varepsilon)}}$. The algorithm combines two ingredients. When the triangle graph of the tournament has bounded clique number, a chain decomposition of its transitive complement yields an exact dynamic program for a maximum-weight transitive subtournament. When the clique number is large, a structural theorem for triangle graphs supplies a constant-size strongly good cost vector. A local-ratio reduction with this cost vector gives the claimed guarantee. As a by-product, the dynamic program solves weighted feedback vertex set exactly in $\mathcal B_7$-free tournaments in time $O(n^7)$, where $\mathcal B_7$ is the family of seven-vertex tournaments with feedback vertex set number at least three.

Founders face two linked decisions: whether to pursue an idea before founding, and which operating actions and capital partners fit afterward. We present a public-data decision-support toolchain combining time-bounded proposal profiling, market and moat checks, and deterministic aggregation with auditable investor-company event chains for retrospective analysis. Pre-founding: (a) After threshold selection on 198 development companies, the frozen pipeline achieves F0.5=0.5357 [0.412, 0.655] on an independent, row-disjoint 198-company validation sample. On the combined 396 rows, the Full Pipeline scores 0.6301 versus 0.2734 for a paired Raw LLM baseline. Post-stratification of 1,027 completed cases in a separate scale cohort yields 0.6506 [0.598, 0.707]; the run remains incomplete. A 377-row composition-matched check yields 0.6573. (b) The AI-inference study identifies distribution-layer businesses as a replicable path to independent profitability with a limited revenue ceiling, and frontier-model ownership as a path to capital-market upside at exceptional capital cost. Post-founding: (a) Public sources support auditable event-chain analysis. (b) In the chip-company study, sustained product, customer, and supply-chain progress is associated with better observed outcomes; financing alone does not establish operating progress. (c) Financing comprises 79% of confirmed visible post-investment actions. Evidence tentatively favors acquisition-experienced strategic corporate investors for acquisition-oriented founders and financing-led institutional VCs with fewer observed control events for independence-oriented founders. Findings are developmental and observational, not causal guarantees or investment advice. We release shared ontology, provenance-bearing EventChain data, schemas, benchmarks, and executable skills for audit, reuse, and extension.

Many applications require solving large numbers of independent linear systems on GPUs. While this need is well addressed for small to large systems, tiny ones, understood here as systems of dimension below 32, remain challenging. This is especially relevant in constitutive law evaluation, where millions of integration points are handled independently, and where each constitutive update generally relies on a Newton iterative method. Each iteration then requires the double-precision solution of a tiny general square linear system using LU factorization with partial pivoting (LUpp). The present study was conducted within a closed-source prototype, which serves as a demonstrator for porting to NVIDIA GPUs constitutive law evaluations currently provided on CPUs by TFEL/MFront, an open-source code generation tool for material knowledge. We compare several double-precision LUpp solvers, including implementations from GPU linear algebra libraries as well as custom-designed CUDA kernels. The comparison is performed first on large batches of standalone linear systems, and then within the full constitutive-law evaluation workflow, where each integration point requires a sequence of distinct linear systems, one per iteration of its own Newton loop. The study shows that the best LUpp solving strategy strongly depends on several factors including system size and application context. We discuss several key aspects, including register pressure, occupancy, the ability to invoke the LUpp solver directly from device code, and whether assigning several threads to each system is the most efficient strategy. Experiments on an NVIDIA H100 GPU show that the specialized LUpp solvers proposed in this work can outperform existing state-of-the-art approaches for this class of workloads, with speedups of up to 6.5x over cuSolverDx, and up to 17.7x over MAGMA.