查看已发布论文的最新修订，在详情页对照实际观测到的版本。
时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →
Tejas Kotwal, Govind Menon
We introduce a matrix generalization of the cone of Harvey and Lawson and prove that it is an exact special Lagrangian manifold. We further show that it belongs to a family of exact special Lagrangian manifolds that foliate the balanced manifold arising in deep learning.
math.DG · cs.LG · math.SG
Yifan Zhu, Guanting Chen, Bing Wei, Haoran Luo
Large Language Models face a multi-objective optimization problem in constrained long-text generation, balancing global structure, local coherence, and constraint satisfaction. We propose LoopWeaver, a hierarchical workflow with two sequential offline preference-optimization stages. Constraint-aware planning produces structured plans, feasibility filtering removes invalid plans, and a shared deterministic reward constructs preference pairs for plan-level and generation-level DPO. At inference time, LoopWeaver remains feed-forward: it generates and revises a complete plan, filters the revised plan, and then generates segments conditioned on the current sub-plan and running narrative. We evaluate the method on four LongGenBench-style structured scenarios across multiple backbones. Results show improvements in both constraint accuracy and text quality across all four open-source backbones. Our software and data are publicly available at https://github.com/cgtaa-cmyk/LoopWeaver.
cs.CL
Mabon Ninan, Nhat Nguyen, Soumyajyoti Dutta, Sidharth Anil, Marcus Botacin
Millions of malware variants threaten users daily, such that clustering these samples is key for fast incident response. AutoYara is the current state-of-the-art for automatic YARA rule generation, but the task remains challenging on realistic datasets, where intra-family diversity and noisy clustering can degrade rule quality. We present AutoPYara, a solution armored with: (1) precise cluster centroid selection based on similarity hashing, and (2) an improved heuristic for estimating subclusters within a malware family using historical VirusTotal data. We implement AutoPYara as an open-source Python package (pip install autopyara) to support reproducibility and practical use. We show that AutoPYara, (1) increases rule coverage by 14 percentage points; (2) reduces variance by 7.1 percentage points, comparing the average variance AutoPYara exhibits to that of AutoYara; and (3) improves threat-hunting accuracy by 10%. AutoPYara produces robust and effective YARA rules than prior automatic approaches in practical settings.
cs.CR · cs.LG
Sushmita Gupta, Sanjay Seetharaman
The maximin share (MMS) guarantee has become one of the central fairness benchmarks for allocating indivisible items. Since Kurokawa, Procaccia, and Wang [EC'14, JACM'18] showed that exact MMS allocations need not exist, a substantial literature has developed around the existence and computation of approximate MMS allocations, including the recent work of Heidari, Kaviani, Seddighin, and Shahrezaei [SODA'26]. In contrast, a fundamental complexity question posed more than a decade ago by Bouveret and Lemaître [JAAMAS'16] has remained unresolved: how hard is it to decide whether an exact MMS allocation exists? For additive valuations, Lonc and Truszczynski [JAIR'20] established membership in the complexity class $Δ_2^P$ (also known as $P^{NP}$), but no hardness result was known. For the more general class of 2-additive valuations, Bouveret and Lemaître established NP-hardness, leaving a substantial gap to the $Δ_2^P$ upper bound. Moreover, the complexity of MMS existence for additive and $k$-additive valuations was posed as open questions. We resolve this longstanding question by proving that deciding the existence of an MMS allocation for additive goods is $Δ_2^P$-complete, even for five agents. Additionally, we prove weak coNP-hardness for three agents, thereby establishing a precise dichotomy with the known existence guarantee for two agents, and strong coNP-hardness when the number of agents is unrestricted. Furthermore, our strong hardness construction yields an inverse-polynomial gap in the optimal MMS approximation ratio, ruling out an FPTAS for approximating this ratio unless P=NP. Finally, we show that all these results for goods extend to the chores setting through a polynomial-time transformation that preserves MMS existence.
cs.GT · cs.DS
Qi Wang
Corporate annual reports describe hedging through transactional, policy, accounting, and explicit non-use language. This study presents AWARE-FX, the foreign-exchange application of the Auditable Weak-supervision and Aggregation framework, for constructing traceable firm-year disclosure measures. Professional-source retrieval, evidence-state rules, channel classifiers, and top-three aggregation link each score to supporting passages. The application covers 24,909 Hong Kong firm-years from 2008-2025 and 543,527 candidate snippets. Evaluation combines weak-label held-out tests, three-seed encoder comparisons, a 2023-2025 temporal test, calibration diagnostics, selective prediction, and a stratified 300-snippet audit coded by one researcher. The paired temporal tests do not detect statistically significant differences between FinBERT and ModernBERT. The negation-aware lexicon has higher broad-task audit F1 than strict-gate FinBERT and Qwen3-8B, demonstrating that learned models do not uniformly improve on domain rules. At 80% temporal coverage, retained-sample F1 increases by 0.050-0.077, although the study does not measure human review time or deployment impact. Reproducible Qwen3-8B results show substantial variation across evidence channels. Linked exposure associations provide exploratory external validation, with sensitivity to the multiple-testing family. The scores measure detected hedging disclosure rather than hedge notional or causal effectiveness. The contribution is an evaluated measurement workflow with inspectable evidence and explicit validation limits. Independent duplicate annotation and retrieval-recall assessment remain necessary for stronger reliability claims.
cs.CL · q-fin.RM
Fabio Carrara, Fabrizio Falchi, Maria Girardi, Nicola Messina, Cristina Padovani, Daniele Pellegrini
Thanks to recent advancements in numerical methods, computer power, and monitoring technology, seismic ambient noise provides precious information about the structural behavior of old buildings. The measurement of the vibrations produced by anthropic and environmental sources and their use for dynamic identification and structural health monitoring of buildings initiated an emerging, cross-disciplinary field engaging seismologists, engineers, mathematicians, and computer scientists. In this work, we employ recent deep learning techniques for time-series forecasting to inspect and detect anomalies in the large dataset recorded during a long-term monitoring campaign conducted on the San Frediano bell tower in Lucca. We frame the problem as an unsupervised anomaly detection task and train a Temporal Fusion Transformer to learn the normal dynamics of the structure. We then detect the anomalies by looking at the differences between the predicted and observed frequencies.
eess.SP · cs.LG
Yuchen Cong, Zerui Tao, Chao Li, Zhe Sun, Qibin Zhao
Score-based variational inference (SBVI) provides an alternative to classical Kullback--Leibler (KL)-based variational inference by learning a distribution using only score queries of the target. EigenVI~\cite{cai2024eigenvi} formulates SBVI as an eigenvalue problem, but faces two limitations: the number of variational parameters grows exponentially with the data dimension, and the single-eigenvector formulation cannot represent the full minimum-eigenvalue eigenspace. We propose QuanVI, a quantum-inspired SBVI algorithm that addresses both limitations. Rather than selecting a single eigenvector, QuanVI captures a learned subspace through a density-operator formulation. To enable scalable computation, \model{} employs a matrix-product-operator (MPO) structure parameterized by a quantum tensor network (QTN) with unitary-constrained local tensors and auxiliary ancilla wires. Numerical experiments demonstrate the scalability of QuanVI beyond EigenVI and competitive performance on synthetic distributions and Bayesian posterior-approximation benchmarks, including challenging non-Gaussian targets. The code is available at https://github.com/ChaoLiAtRIKEN/quanvi.
cs.LG
Thang Do, Arnulf Jentzen, Benno Kuckuck
We prove that for every open $U \subseteq \mathbb{R}^n$ the spherical projection of every gradient trajectory $θ(t)$, $t \geq 0$, of a definable $C^1$-potential $F \colon U \to \mathbb{R}$ has finite length and, in particular, converges (directional convergence). In other words, every gradient trajectory of a definable $C^1$-potential has finite total angular motion. Here, definable means definable in an arbitrary o-minimal structure expanding the real field. Notably, the gradient trajectory in this result is an arbitrary solution of the gradient flow differential equation (whose solutions may not be unique) with no further assumptions: The gradient trajectory may be unbounded and diverge to infinity or it may be convergent. The established theorem therefore provides affirmative answers to both the gradient conjecture at infinity for definable potentials and the definable Thom gradient conjecture. We extend our conclusions from the Euclidean metric to a general class of ambient metrics including Riemannian metrics and we establish uniform local upper bounds for the lengths of the spherical projections of gradient flow trajectories. We finally apply our findings to the training of deep neural networks (DNNs) to conclude that, in the case of definable and continuously differentiable activation and loss functions, the spherical projection of the DNN training flow must always converge (directional convergence).
math.DS · cs.LG · math.AG · math.CA · math.LO
Han Tong, Haolin Zou, Shubhangi Ghosh, Arian Maleki
Data attribution, which traces a model's prediction back to specific training data, is an important tool for interpreting sophisticated AI models. The widely used TRAK algorithm addresses this challenge by first approximating the underlying model with a kernel machine and then leveraging techniques developed for approximating the leave-one-out (ALO) risk. Despite its strong empirical performance, the theoretical conditions under which TRAK approximations are accurate, as well as the regimes in which they break down, remain largely unexplored. In this paper, we provide a theoretical analysis of the TRAK algorithm, characterizing its performance and quantifying the errors introduced by the approximations on which the method relies. We show that although the approximations can incur significant errors, TRAK preserves the separation between highly influential and weakly influential data points. We corroborate our theoretical results through extensive simulations and empirical studies.
cs.LG
Saurav Bellam
Code-graph and embedding tools are routinely added to LLM coding agents on the premise that they supply repository structure the model lacks. We report a pre-registered study of how much such tools help off-the-shelf agents localize the code an issue requires changing and how the benefit varies with model size. Nine open-weight models (Qwen3 0.6B to 32B, Gemma 4 E2B to 12B) run one fixed localization harness on 500 held-out SWE-bench tasks under four tool sets (grep only; plus embedding search; plus code-graph tools; both) and a placebo arm whose structural tools return random entities, with five sampled seeds per condition: 170,500 episodes under hypotheses, tests and claim criteria frozen before the runs. The tools raise canonical function Acc@10 by +0.06 to +0.10 for the Qwen3 models up to 14B and the two small Gemma 4 models, by +0.03 at 32B (a near miss after correction), and not at all for Gemma 4 12B, which rarely submits; the gain is larger for small models than for the largest model in both families. The placebo shows that the gain is caused by what the tools return rather than by having them, and that random tool output harms two small models. The pre-registered claim that a 4B model with tools matches a 32B model without them fails. Secondary analyses show that the embedding index, not the code graph, carries the gain; that the gain replicates on tasks created after every model's release and survives a shell harness, thinking mode, FP8 serving and a file-level metric that output formatting cannot inflate; and that it is mostly exposure: the tools show the gold code more often. Injecting the gold code directly explains the size trend. A 32B model already finds the code without the tools, so they add little exposure, while small models act on a shown answer less often (conversion 0.09, 0.24 and 0.40 at 1.7B, 4B and 32B). We release registration, code, episodes and analyses.
cs.SE · cs.CL · cs.LG
Pranava Seth, Mamta Gulati
The rapid increase in the deployment of Low Earth Orbit (LEO) satellites, catering to diverse applications such as communication, Earth observation, environmental monitoring, and scientific research, has significantly amplified the complexity of trajectory management. The current work focuses on calculating and analyzing perturbation effects on a satellite's anticipated trajectory in LEO, considering Solar Radiation Pressure (SRP) as the main perturbing force. The acceleration due to SRP and it's effects on the satellite was calculated using a custom-built Python module mainly based on the hypothesis of the cannonball model. The study demonstrates the effectiveness of the proposed model through comprehensive simulations and comparisons with existing analytical and numerical methods. Here, the primary Keplerian orbital characteristics were employed to analyze a simulated low-earth orbit LEO satellite, initially visualizing the satellite's trajectory and ground tracks at a designated altitude. The study also focuses on a comparative analysis of ground stations, primarily considering the main regions of the subcontinent, with revisit time as the key parameter for comparison. In the end, we combine analytical techniques with Machine Learning (ML) algorithms to predict changes in the position vectors of the satellite. Using ML techniques, the model can adaptively learn and refine predictions based on historical data and real-time input, thus improving accuracy over time. In addition, the incorporation of analytical methods allows for a deeper understanding of the underlying physics governing satellite motion, enabling more precise adjustments and corrections.
cs.CE
Alessio Spagnoletti, Tim Y. J. Wang, Marcelo Pereyra, O. Deniz Akyildiz
Vision-Language Latent Diffusion Models (LDMs) (Rombach et al., 2022) provide powerful generative priors for inverse problems. However, existing LDM-based inverse solvers typically require a large number of neural function evaluations (NFEs) and backpropagation through large pretrained components, leading to substantial computational costs and, in some cases, degraded reconstruction quality. We propose a unified Euclidean-Wasserstein-2 gradient-flow framework that jointly performs posterior sampling and prompt optimization in the latent space through a single flow that aligns the prior and posterior with the observed data. Combined with few-step latent text-to-image models, this formulation enables low-NFE inference without backpropagation through autoencoders. Experiments across several canonical imaging inverse problems show that our method achieves state-of-the-art performance with significantly reduced computational cost.
stat.ML · cs.CV · cs.LG
Pranava Seth, Deepak Mishra, Veena Iyer
This article describes the development of a novel U-Net-enhanced Wavelet Neural Operator (U-WNO),which combines wavelet decomposition, operator learning, and an encoder-decoder mechanism. This approach harnesses the superiority of the wavelets in time frequency localization of the functions, and the combine down-sampling and up-sampling operations to generate the segmentation map to enable accurate tracking of patterns in spatial domain and effective learning of the functional mappings to perform regional segmentation. By bridging the gap between theoretical advancements and practical applications, the U-WNO holds potential for significant impact in multiple science and industrial fields, facilitating more accurate decision-making and improved operational efficiencies. The operator is demonstrated for different pregnancy trimesters, utilizing two-dimensional ultrasound images.
eess.IV · cs.CV
Ben Griffin, Aaron Ontoyin Yin, Diego Vidaurre, Ugur Koyluoglu, Joseph Ternasky, Fuat Alican, Yigit Ihlamur
Many high-stakes screening decisions in finance amount to predicting a rare outcome from unstructured text, such as whether a founder will successfully build a large company, or which crowdfunded loan will fail to attract funding. When positives are this rare, simple models may be preferable to more complex ones. For example, a model that learns a weight for each feature may have too little signal to estimate those weights reliably, and also inspecting the model means reading a list of fitted coefficients rather than a simple rule that can be checked by eye. We introduce Rule Forest, which uses a large language model to generate simple YES/NO questions, rather than using it to directly predict outcomes, and combines the strongest questions into an equal-weight "green-flags" scorecard. This scorecard is as accurate as an equivalent model that learns a weight per question, within noise, and its advantage appears largest when positives are rarest. The result is an interpretable list of rules that a domain expert can edit and extend. When predicting founder success, the fraction of shortlisted founders who succeed increases from about 1 in 50 to 1 in 10, and to about 1 in 6 with a handful of expert-written questions. A second dataset which focuses on identifying failed loans, Kiva microloans, shows the same qualitative pattern. Across both tasks, the lesson is the same: a language model is most useful not as the predictor but as a generator of features a person can read, edit, and improve, and when positives are scarce that interpretability costs no measurable accuracy.
cs.AI · cs.LG
Taolin Han, Yuchen Zhang, Jinghang Wang, Yun Wu, Wai Yuet Chiu, Zhaohai Li, Yifei Zhang, Jinxin Wang 等 25 位作者
Large language models (LLMs) are increasingly involved in scientific discovery, yet it remains unclear whether they can support complex real laboratory science. Here we introduce Science Edge Evaluation (SEE), a multimodal benchmark of expert-curated questions grounded in peer-reviewed literature and experimental practice in chemistry, biology, and materials science. Evaluation of 28 multimodal large language models (MLLMs) shows that even the best-performing model reaches only 54.9% accuracy. Moreover, general-purpose models outperform science-specialized models on average. In the visual-agent evaluation, the use of tools increases the best accuracy to 56.1%. Tool use can expand the information available to models, but more information does not necessarily lead to reliable scientific reasoning. The key challenge is whether models can manage tool-derived information within the boundaries of the original experimental evidence. Together, these findings reveal that current MLLMs still cannot reliably make justified and evidence-bounded inferences from experimental results, which is an essential capability in real scientific discovery. Bridging this gap requires MLLMs to transition from explaining established scientific concepts to deriving novel and evidence-based insights from experimental data.
cs.AI
Federico Bruzzone, Walter Cazzola, Luca Favalli
The development of programming languages involves complex theoretical and practical challenges, particularly when addressing modularity and reusability through language extensions. While language workbenches aim to enable modular development under the constraints of the language extension problem, one critical constraint--separate compilation--is often relaxed due to its complexity. However, this relaxation undermines artifact reusability and integration with common dependency systems. A key difficulty under separate compilation arises from managing attribute grammars, as extensions may introduce new attributes that invalidate previously generated abstract syntax tree structures. Existing approaches, such as the use of dynamic maps in the Neverlang workbench, favor flexibility at the cost of compile-time correctness, leading to potential runtime errors due to undefined attributes. This work addresses this issue by introducing nlgcheck, a theoretically sound static analysis tool based on data-flow analysis for the Neverlang language workbench, which detects potential runtime errors--such as undefined attribute accesses--when separately compiled language components are composed, before the resulting language is ever run, thus preserving separate compilation while maintaining strong static correctness guarantees. Experimental evaluation using mutation testing on Neverlang-based projects demonstrates that nlgcheck effectively enhances robustness without sacrificing modularity or flexibility and with a level of performance that does not impede its adoption in daily development activities.
cs.PL · cs.SE
Chuansen Peng, Xiaojing Shen
Inferring time-varying graphs from high-dimensional nodal observations is challenging when windows contain fewer samples than nodes, observations are heavy-tailed, and the dependence drifts multiplicatively over time. We propose the dynamic elliptical graph factor model (\textsc{Degfm}), combining: an elliptical likelihood that down-weights outliers; a low-rank-plus-diagonal (LRaD) parameterization of each precision matrix, shown to be the posterior precision of a field conditioned on a few aggregate linear measurements; and a temporal regularizer given by the squared affine-invariant distance between consecutive precision matrices, capturing multiplicative evolution and invariant to node rescaling and to the choice between precision and covariance. Estimation on a product of quotient manifolds is solved by a safeguarded Riemannian conjugate-gradient method with closed-form temporal gradients via generalized eigendecompositions. We prove that (i) LRaD is locally identifiable modulo orthogonal transformations under a tangent-space transversality (coherence) condition; (ii) with rank-preserving Armijo backtracking, the solver is well defined and converges to critical points with $\min_{k<K}\|\grad F(θ^{(k)})\|^2=\mathcal{O}(1/K)$; (iii) a localized estimator obeys a finite-sample oracle inequality whose error scales with the intrinsic dimension $pr+p-r(r-1)/2$ times an effective temporal dimension decreasing from $1$ to $1/T$ as coupling strengthens, quantifying the variance reduction and bias of temporal coupling, and extending to misspecified non-LRaD models; (iv) for Student-$t$ observations, the local restricted strong convexity is proved rather than assumed, with curvature of order $ν/(p+ν)$ shown unimprovable; and (v) partial-correlation graphs are recovered exactly by thresholding. Experiments on synthetic data, S\&P~500 returns, and HCP fMRI data validate the approach.
cs.LG · cs.GR
Haiming Tang, Xianjie Dai, Gujie Shao, Zuyi Guo, Jingguang Li, Kailang Ma, Yihong Tang, Heye Huang
Memory lets an embodied agent reuse past experience, yet retaining useful information does not ensure that the agent can apply it when conditions change. We present MemTransfer, a benchmark comparing six memory representations, a working-memory baseline and five representations of past experience, under a shared frozen vision-language-model policy. It comprises 100 navigation cases across ten task types in a simulated warehouse, with expert demonstrations supplying the history. Three comparisons vary the starting pose, route availability, and amount and task relevance of history. With one demonstration per task, Full-context and Episodic memory reach 95.3% and 100.0% success at the original demonstration start, but lose 48-49 percentage points at a new test start. Summary changes little between these two test starts, yet with four demonstrations per task it retains a smaller fraction of its unchanged-route success after blocking (39.3%) than Working memory (44.8%) or the two trajectory memories (56-58%). At the new test start, increasing from one to four relevant demonstrations raises Episodic success by 14.3 percentage points, while the other evaluated representations gain no more than 1.3 percentage points. Replacing half of the relevant histories with other-task experience lowers success for both trajectory memories. These results show that robustness to one kind of mismatch does not imply robustness to another, motivating evaluation of both stored information and its use at decision time.
cs.RO
Gengsheng Li, Mao Zheng, Mingyang Song, Ruiqi Liu, Tianyu Yang, Jie Sun, Qiyong Zhong, Haiyun Guo 等 11 位作者
Multi-turn agents that plan, invoke tools, and interact with environments offer a promising paradigm for solving complex tasks, yet their capabilities typically rely on very large models whose inference cost is prohibitive in practice. On-Policy Distillation (OPD) is a natural recipe for transferring such capabilities to smaller students, but we find that it suffers a characteristic failure mode in this setting: small student errors compound across turns and push the trajectory out of the teacher's familiar state distribution, so the teacher's supervision becomes least reliable precisely where the student needs it most. We propose Guided On-Policy Distillation (Guided-OPD), a simple yet effective algorithm that mixes teacher- and student-generated turns within each rollout and schedules the teacher's intervention probability along a curriculum that decays to zero. Strong guidance keeps early trajectories close to the teacher distribution and is then gradually withdrawn to recover the purely on-policy regime used at inference. On ALFWorld, ScienceWorld, and WebShop, distilling Qwen3 students from a Qwen3-30B-A3B teacher, Guided-OPD yields average relative gains of 21.1\% in Score and 25.5\% in Success Rate over vanilla OPD, with larger gains on smaller students.
cs.LG · cs.AI
Luxi Lin, Zhihang Lin, Zhanpeng Zeng, Rongrong Ji
Multimodal Large Language Models (MLLMs) deliver strong performance across vision-language tasks but suffer from high autoregressive decoding latency. Although speculative decoding can accelerate Large Language Models (LLMs) without changing their output distribution, directly applying existing approaches to MLLMs yields limited speedups because text and visual tokens exhibit distinct characteristics. We present Multimodal Speculative Decoding (MSD), a framework specifically designed for efficient MLLM inference. MSD is motivated by two key observations: text and visual tokens should be handled separately during drafting, and an effective draft model requires both strong language modeling and visual perception capabilities. Accordingly, MSD decouples text and visual token processing in the draft model and applies token-specific strategies to improve drafting efficiency. We further introduce a two-stage training strategy. The draft model is first trained on text-only instruction-tuning data to strengthen its language modeling ability and is then progressively exposed to multimodal data to develop visual perception while preserving its language competence. Extensive experiments across multimodal benchmarks demonstrate that MSD achieves up to $2.29\times$ inference speedup for LLaVA-1.5-7B and $2.46\times$ for LLaVA-1.5-13B without sacrificing generation quality. These results establish MSD as an effective and general approach for accelerating multimodal autoregressive generation. Our code is available at https://github.com/Lyn-Lucy/MSD
cs.CV · cs.AI
Proshanto Chanda, Munib Mesinovic, Tingting Zhu, Abhirup Banerjee
Multi-label retinal screening requires capturing co-occurring pathologies and clinical context, yet standard multimodal fusion remains opaque. We propose a dual-hub heterogeneous graph neural network (GNN) that couples spatial fundus features and structured clinical covariates through cross-modal message passing while providing inherent interpretability. Rather than relying on post-hoc saliency approximations, our architecture exposes multi-level decision pathways during forward aggregation: spatially biased self-attention captures lesion-level patch interactions, while modality-specific graph attention coefficients explicitly quantify the contribution of visual regions and clinical risk factors to each disease node. Evaluated on the BRSET dataset (16,266 photographs from 8,524 patients), the proposed model achieves 76.1% Macro-AUPRC across seven conditions, matching or exceeding image-only (75.9%) and ResNet-50+MLP fusion (75.9%) baselines, with largest contextual gains in macular edema (+3.5 percentage points, pp) and diabetic retinopathy (+2.1 pp). Codebase is available at: https://github.com/proshanto-c/ca-mlc-refactor.
cs.CV · cs.LG
Heyue Li, Shaolin Xiang, Tian Tian, Qichun Liu, Tiefu Li, Zhihua Wang, Yanshu Guo, Hanjun Jiang
As quantum processors scale, online calibration, quantum error correction (QEC), and measurement-driven feedback require continuous classical processing and parameter updates. Sharing on-chip resources reduces hardware cost, but computation completion, the last parameter read, and result consumption occur at different times. Their dependencies must be managed separately while preserving quantum operations' real-time requirements. We present QCORE, a quantum-computing-oriented, resource-efficient runtime architecture that coordinates these lifecycles for safe resource reuse and parameter consistency. QCORE models resource occupancy, parameter protection, and consumer dependencies as independent lifecycles and provides three mechanisms: pre-use checks and parameter binding to verify timing, identity, and dependencies; access-aware protection through value snapshots, version references, or active-configuration windows; and joint admission of resource reservations and parameter installation. After request submission, hardware autonomously handles admission, protection, installation, and reclamation, reducing fine-grained Host coordination and providing a foundation for one Host to manage multiple controllers. We implement synthesizable RTL and validate FPGA timing at 100 MHz. Independent release reduces whole-program execution time by 16.83% in Ramsey calibration and QEC replay. Joint admission increases on-time completions from 5/15 to 15/15 under contention across five arrival phases. Under identical external deadlines, a shared NN backend reduces LUT usage by 12.28%-13.81% and DSP usage by 39.39% compared with two statically assigned backends. These results show that lifecycle coordination exploits inter-task timing slack for on-chip sharing, increasing service capacity under limited resources.
quant-ph · cs.AR
Fabian Bongratz, Tom Nuno Wolf, Jaume Gual Ramon, Christian Wachinger
Interpretable models are crucial for supporting clinical decision-making, driving advances in their development and application for medical images. However, the nature of 3D volumetric data makes it inherently challenging to visualize and interpret intricate and complex structures like the cerebral cortex. Cortical surface renderings, on the other hand, provide a more accessible and understandable 3D representation of brain anatomy, facilitating visualization and interactive exploration. Motivated by this advantage and the widespread use of surface data for studying neurological disorders, we present the eXplainable Surface Vision Transformer (X-SiT). This is the first inherently interpretable neural network that offers human-understandable predictions based on interpretable cortical features. As part of X-SiT, we introduce a prototypical surface patch decoder for classifying surface patch embeddings, incorporating case-based reasoning with spatially corresponding cortical prototypes. The results demonstrate state-of-the-art performance in detecting Alzheimer's disease and frontotemporal dementia while additionally providing informative prototypes that align with known disease patterns and reveal classification errors.
cs.GR · cs.CV · cs.LG
Dier Tang, Jing Yee Tan, Guangyue Han
Spectral contrastive learning keeps the $k$ directions along which two views of the data depend most strongly, while downstream tasks may need other directions. Existing guarantees for spectral features assume that the distribution of tasks has no preferred direction. We show that this isotropy condition is the wrong criterion. With linear probing, the task distribution affects the average probing gain only through the matrix $BΛB^\top$, where $B$ records the dependence between views and $Λ$ is the task covariance: optimal features span its top-$k$ eigenspace, whereas spectral features span that of $BB^\top$. Transfer therefore depends on alignment, and strongly uneven task preferences cost nothing when they favour the spectral directions. Otherwise the regret of spectral features is at most linear in the anisotropy of $Λ$. No representation chosen without task information improves this rate when the leading spectrum is flat, and a spectral gap makes it quadratic. With labelled tasks, the same matrix gives a correction: Fisher discriminant directions for a frozen encoder, or a one-term change to the spectral contrastive loss. We bound the regret of the correction by the error in estimating $BΛB^\top$, and compare this error with the misalignment of spectral features to decide when to correct. The analysis extends to finite samples, continuous variables and noisy views. Correction reduces synthetic held-out regret from $0.858$ to $0.003$ with $2000$ labelled tasks, and the decision rule gives the lowest regret among the tested rules at every bank size. On CIFAR-100, spectral features of frozen encoders keep most of the task signal on unseen classes, and where a bank of other classes would lower accuracy, the rule keeps them in every case.
cs.LG · cs.IT · stat.ML
Elouan Gardès, Seung Eun Yi, Kartik Ahuja, Théo Moutakanni, Huy V. Vo, Piotr Bojanowski, Wolfgang M. Pernice, Loïc Landrieu 等 9 位作者
We propose a label-free approach to adapt powerful but generic vision foundation models to specialized scientific domains. Standard supervised fine-tuning is often ill-suited to these settings: labels are scarce, and task-specific training can reduce the generality needed to cope with complex domain shifts. We instead leverage metadata to adapt representations to new domains in a weakly-supervised manner. Our method, FINO, combines a standard self-supervised objective with flexible metadata guidance that handles both highly granular discrete metadata and continuous metadata. It encourages the representation to preserve informative factors while suppressing spurious ones. Across subcellular fluorescence microscopy, Earth observation, wildlife monitoring, and medical imaging, FINO outperforms matched self-supervised and fully supervised adaptation baselines. Complete-adaptation repeats confirm consistent performance across domains. Without task labels for backbone adaptation, FINO also obtains higher reported scores than selected specialised systems on three domains and matches the fourth under differing cross-paper protocols. Code is available at github.com/facebookresearch/dinov3/tree/FINO.
cs.CV · cs.AI
Andrin Rehmann, Heiko Zimmermann, Dion Häfner
Differentiable partial differential equation (PDE) solvers underpin solver-in-the-loop MLtraining, gradient-based optimal control, and inverse problems, yet the practical cost of obtaining correct, usable gradients from a given solver on a given problem is largely undocumented. Integration effort, computational cost, memory, gradient accuracy, and numerical stability vary widely across solvers and are discoverable only by trial and error. We introduce Mosaic, an extensible benchmarking framework for differentiable PDE solvers that standardizes access to solver gradients. Each solver is packaged as a containerized component (Tesseract) exposing a uniform gradient API regardless of language or automatic differentiation (AD) strategy, enabling researchers to evaluate, compare, and build on non-trivial physical solvers. Our evaluation of 14 solvers across fluid dynamics, structural mechanics, and heat transfer demonstrates that the benchmark surfaces practically relevant differences: order-of-magnitude variation in computational cost and memory, alongside setup incompatibilities and instabilities that rule out solvers for specific tasks. Despite this variation, all solvers that produce gradients converge to similar optima on our tasks, indicating that the practical barriers are memory limits, numerical stability, and setup compatibility rather than gradient accuracy alone. Mosaic is open-source and available at github.com/pasteurlabs/mosaic.
physics.comp-ph · cs.LG
Chun Kang, Yunbo Zhang, Fanhu Zeng, Jian Liu, Siwei Deng, Lei Sha
Accurate prediction of enzyme kinetic parameters can support enzyme engineering and metabolic modeling by complementing experimental characterization. Existing prediction methods often pool residue-level protein features before combining them with substrate features. Such substrate-independent pooling cannot adapt residue weighting to the substrate during aggregation, potentially diluting information relevant to a specific enzyme-substrate pair. Since the contributions of individual residues to catalysis can depend on the substrate, substrate-conditioned aggregation offers a way to emphasize residue features relevant to the prediction. We introduce KineCouple, which uses substrate queries and residue-level keys and values in cross-attention, allowing the substrate to guide residue selection before aggregation. The model preserves the global protein representation and adds a gated correction defined as the difference between the conditioned readout and a uniform readout. ProtT5 and MolT5 remain frozen, and separate models predict kcat and Km on a logarithmic scale. In pooled out-of-fold predictions on the CataPro benchmarks, KineCouple reduces kcat RMSE from 1.333 to 1.330 and increases PCC from 0.492 to 0.496 relative to reproduced CataPro. For Km, RMSE decreases from 0.998 to 0.997 and PCC increases from 0.633 to 0.634. Spearman correlation also improves for both tasks.
cs.AI · q-bio.QM
Yu Cai, Canxi Huang, Zike Li, Jing Gong, Xiaoyu He
Federated learning heavily relies on distributed gradient descent techniques. In the situation where gradient information is not available, the gradients need to be estimated from zeroth-order information, which typically involves computing finite-differences along isotropic random directions. This method suffers from high estimation errors, as the geometric features of the objective landscape may be overlooked during the isotropic sampling. In this work, we propose a non-isotropic sampling method to improve zeroth-order gradient estimation. The method uses historical solution trajectories to identify a promising subspace and constructs a non-isotropic Gaussian smoothing that balances exploitation in this subspace with global exploration. We implement this method in zeroth-order federated settings, and show that the convergence rate aligns with existing ones while introducing no significant overheads in communication or local computation. The effectiveness of our proposal is verified on several numerical experiments in comparison to several commonly-used zeroth-order federated optimization algorithms. The experiments cover both independent and identically distributed data and heterogeneous client data distributions.
cs.LG · cs.AI
Sebastian Meyer, Florian Starke
We introduce $n$-almost symmetric Datalog and study $n$-almost symmetric linear arc monadic Datalog. We characterize the finite relational structures whose constraint satisfaction problem is solved by this Datalog fragment as those that can be primitive positively constructed from the transitive tournament on $n+2$ vertices. We also give characterizations in terms of a certain homomorphism duality (which we call $n$-fixed unfolded caterpillar duality) and in universal-algebraic terms (the existence of $k$-absorptive operations and of operations forming an elevator chain of length $n+1$). This article generalizes the results from Bodirsky and Starke about symmetric linear arc monadic Datalog.
cs.LO · math.RA
Rodrigo Almeida, Noelia Otero, Jost Arndt, Simon Baur, Wojciech Samek, Jackie Ma
End-to-end weather forecasting systems produce skillful global gridded and station forecasts directly from raw Earth observations, replacing the numerical weather prediction pipeline, including data assimilation, at a fraction of its cost. These systems are deterministic and issue no uncertainty. Here we render the Aardvark Weather model probabilistic by attaching one stochastic mechanism to each component: learned, input-dependent noise at the observation encoder, aimed at the uncertainty inherited from the observing system, and Monte Carlo dropout in the processor, aimed at the uncertainty of the learned dynamics. The resulting nested ensemble attributes forecast spread to the two sources through a law-of-total-variance decomposition, cross-checked by withholding observation streams. Probabilistic finetuning significantly improves the mean forecast, by 11% on average across variables and lead times. The ensemble is close to calibrated against ERA5 through the medium range, is at least as accurate as the deterministic model at weather stations while beating it in relative economic value at every lead time, and remains considerably behind the operational ECMWF IFS ensemble. The encoder branch behaves as observation-driven uncertainty. Component-attributed uncertainty makes end-to-end forecasts more transparent, a step toward observation-driven digital twins of the atmosphere.
physics.ao-ph · cs.LG