跳到正文
研踪PaperTrail

版本更新

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。

部分采集异常

全站更新概况

+1085新增论文
+884其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 06:59各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 09:56 — 2026-11-19 09:56(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-19 06:59最近发现新增版本:2026-11-19 06:59库内论文最新更新时间:2026-11-18 08:00

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

26,871 已收录论文22,375 AI 相关8,156 有修订112 HF 社区发现

论文修订列表

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 →

找到 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v2arXiv:2609.31016

Robust Successor Features

Erik Nikulski, Yamen Habib, Vicenç Gomez, Anders Jonsson, Rubén Moreno-Bote, Javier Segovia-Aguas

原文摘要

Generalization in Reinforcement Learning (RL) refers to the ability to execute close-to-optimal policies in unseen tasks after the agent has been trained on a different set of tasks. Building on the seminal work of the successor representation and further adaptations with function approximation, Transfer in RL has traditionally focused on generalizing to tasks that only differ in the reward function. A decade after the introduction of the successor representation, Robust RL emerged simultaneously from several articles in the field of operations research. In Robust RL, the transition kernel is unknown, and the goal is to maximize the expected reward under this uncertainty. Our work unifies these two paradigms through robust successor features, which generalize across both the reward function and the transition kernel, under the assumption that tasks are linear Markov Decision Processes. We derive a bound on Generalized Policy Improvement (GPI) that explicitly quantifies how performance degrades with the mismatch between transition kernels, recovering existing successor-feature guarantees when dynamics are shared. Finally, the generalization capabilities of robust successor features are validated on several grid-based benchmarks and compared to previous alternatives that focus solely on either the reward or the transition kernel.

cs.LG

版本更新 · v2arXiv:2610.21809

From Adults to Children: Benchmarking Foundation Models for Chest X-Ray Classification under Domain Shift

Sara Inácio, Hugo Proença, João C. Neves

原文摘要

Foundation models have shown significant potential across diverse fields and have been applied to medical imaging, but their robustness across patient populations remains unclear. In this work, we investigate foundation models' ability to generalize from adult to pediatric chest X-ray classification. To the best of our knowledge, this is the first benchmark to compare multiple foundation models under a common adult-to-pediatric evaluation setting while also analyzing the effect of adaptation depth. We harmonize VinDr-CXR and PediCXR into a five-label classification task and evaluate six foundation models and two CNN baselines. All models are adapted using adult data only and tested in both the in-domain and pediatric domains using linear probing, partial fine-tuning, and full fine-tuning. The benchmark reveals a clear and consistent trend: all models suffer a substantial performance degradation when transferred from adult to pediatric data, with drops exceeding 10 percentage points. While Macro-AUROC values reach approximately 92% on the adult test set, performance decreases to around 78% on the pediatric domain. Another important finding is that increasing the depth of adaptation improves pediatric performance on average, although the effect varies across models. Moreover, strong in-domain performance does not necessarily indicate greater robustness to domain shift.

cs.CV

版本更新 · v4arXiv:2607.07779

From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier

Eric Jiang, Xiao Liang, Junyi Zhang, Justin Baker, Zhi Zhang, Yingjia Wan, Yubei Li, Jinxi Yu 等 41 位作者

原文摘要

Large language models have made rapid progress in generating machine-checked proofs for well-defined mathematical problems. Extending this progress to research mathematics requires more than solving isolated theorems. Research involves choosing questions, developing definitions and conjectures, connecting results, and combining formal proofs with expert judgment. This survey examines how LLM-driven systems can support these broader activities. We review formal-mathematics tasks, datasets, and autoformalization, and organize proof-generation methods into three overlapping areas: training strategies, inference-time search and adaptation, and agentic workflows. We then examine benchmark results, selected research projects, and platforms for collaborative mathematical work. A central distinction runs throughout the survey: checking a formal proof does not by itself establish that it captures the intended problem or makes a new mathematical contribution. We therefore distinguish theorem benchmarks, repository tasks, formalization projects, and research claims, and discuss the evidence needed to assess each. Finally, we identify five priorities for progress: better data and evaluation, representations of mathematical relationships, conjecture and concept generation, reliable tool integration, and human--AI collaboration. Together, these perspectives connect advances in proof generation to the practical demands of mathematical research.

cs.CL · cs.AI

版本更新 · v3arXiv:2604.24033

Event-based SLAM Benchmark for High-Speed Maneuvers

Sheng Zhong, Junkai Niu, Guillermo Gallego, Kaizhen Sun, Yang Yi, Zhiqiang Miao, Dewen Hu, Yaonan Wang 等 10 位作者

原文摘要

Event-based cameras are bio-inspired sensors with pixels that independently and asynchronously respond to brightness changes at microsecond resolution, offering the potential to handle visual tasks in high-speed maneuvering scenarios. Existing event-based approaches, although successful in mitigating motion blur caused by high-speed maneuvers, suffer from many limitations. Some of them highlight a success of pose tracking for a fronto-parallel fast shaking camera closed to the structure, while others assume pure (optionally aggressive) three-degree-of-freedom rotations. The former requires persistent local map visibility within the field of view (FOV), whereas the latter fails to generalize to six-degree-of-freedom (6-DoF) motions where both linear and angular velocities may be large. Consequently, current successes do not fully demonstrate that event-based state estimation under arbitrary aggressive maneuvers is a fully solved problem. To quantitatively assess the extent to which the potential of event cameras has been unlocked, we conduct a thorough analysis of state-of-the-art (SOTA) event-based visual odometry (VO)/visual-inertial odometry (VIO) methods and report shortcomings in current public datasets. Furthermore, we introduce a benchmarking framework for event-based state estimation, called EvSLAM, characterized by sufficient variation in data collection platforms, diverse extreme lighting scenarios, and a wide scope of challenging motion patterns under a clear and rigorous definition of high-speed maneuvers for mobile robots, along with a novel evaluation metric designed to fairly assess the operational limits of event-based solutions. This framework benchmarks state-of-the-art methods, yielding insights into optimal architectures and persistent challenges.

cs.RO

版本更新 · v2arXiv:2006.16930

A new Hodge operator in Discrete Exterior Calculus. Application to fluid mechanics

Rama Ayoub, Aziz Hamdouni, Dina Razafindralandy

原文摘要

This article introduces a new and general construction of discrete Hodge operator in the context of Discrete Exterior Calculus (DEC). This discrete Hodge operator enables to circumvent the well-centeredness limitation on the mesh with the popular diagonal Hodge. It allows a dual mesh based on any interior point, such as the incenter or the barycenter. It opens the way towards mesh-optimized discrete Hodge operators. In the particular case of a well-centered triangulation, it reduces to the diagonal Hodge if the dual mesh is circumcentric. Based on an analytical development, this discrete Hodge does not make use of Whitney forms, and is exact on piecewise constant forms, whichever interior point is chosen for the construction of the dual mesh. Numerical tests oriented to the resolution of fluid mechanics problems and thermal transfer are carried out. Convergence on various types of mesh is investigated.

cs.CE

版本更新 · v2arXiv:2605.07865

KL for a KL: On-Policy Distillation with Control Variate Baseline

Minjae Oh, Sangjun Song, Gyubin Choi, Yunho Choi, Yohan Jo

原文摘要

On-Policy Distillation (OPD) has emerged as a dominant post-training paradigm for Large Language Models, especially in reasoning domains. However, OPD remains unstable in practice due to the high gradient variance of its single-sample Monte Carlo estimator, and recipes for stable training are still immature. We propose vOPD (On-Policy Distillation with a control variate baseline), which casts OPD as policy-gradient RL and stabilizes it by introducing a control variate baseline---canonically a value function---from the RL literature. We show that the OPD value function admits a closed form: the per-token negative reverse KL divergence between student and teacher, available directly from the existing forward pass with no additional critic or inference. Existing stabilization methods either compute the full token-level reverse KL over the entire vocabulary, adding significant overhead, or restrict it to a top-k support, biasing the objective. vOPD instead preserves the lightweight single-sample estimator and subtracts the value function as a detached baseline to keep the gradient unbiased while reducing variance. Moreover, we show that a top-k approximation of the baseline further lowers cost without compromising performance. Across mathematics, science, and instruction-following benchmarks, vOPD consistently outperforms base OPD and matches the most expensive full-vocabulary method, offering an efficient stabilization of OPD through principled RL variance reduction.

cs.LG · cs.AI · cs.CL

版本更新 · v3arXiv:2602.02313

From Outcome to Representation: Tracing Reasoning Mechanisms through Integrated Policy Gradient

Changming Li, Kaixing Zhang, Haoyun Xu, Yingdong Shi, Zheng Zhang, Kaitao Song, Kan Ren

原文摘要

Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, yet the internal mechanisms driving these multi-step processes remain opaque. Existing mechanistic interpretability approaches often rely on superficial text-pattern co-occurrences or capture only short-term effects, struggling to trace the long-horizon, outcome-driven influence of internal components such as neurons or sparse features in multi-step reasoning.In this paper, we introduce Integrated Policy Gradient (IPG), a novel, training-free framework that brings policy-based attribution into mechanistic interpretability for LLM reasoning. Grounded in \textit{outcome-oriented} and \textit{sequential-influence-aware} principles, it backpropagates outcome-level, non-differentiable behavioral signals (e.g., reasoning outcome correctness) through entire inference trajectories, utilizing path integration to isolate outcome-relevant mediators at component level for reliable attribution. This provides a linear approximation of Causal Mediation Analysis (CMA) in reasoning. Empirical evaluations demonstrate that \method achieves precise localization and reveals mechanistic insights by identifying sparse, concentrated subsets of internal components associated with specific reasoning behaviors. Our method also enables modulation of reasoning capabilities, offering a powerful and reliable framework for understanding LLM reasoning. The project page is at https://foundation-model-research.github.io/IPG .

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2609.24894

SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models

Ali Kerem Bozkurt, Baris Cem Bakay, Ibrahim Kulac, Cigdem Gunduz-Demir, Erkut Erdem, Aykut Erdem

原文摘要

Whole-slide pathology images (WSIs) contain gigapixel-scale visual content, creating a major scalability challenge for slide-level multimodal large language models (MLLMs). Existing approaches process thousands of patch tokens and typically apply compression only after slide encoding, leaving multimodal attention computationally expensive. We introduce SLICEChat, a slide-level MLLM that integrates progressive token pruning within a hybrid Mamba--Transformer slide encoder. Mamba layers enable efficient long-range propagation, while Transformer layers preserve global interactions as the sequence is progressively shortened. Between stages, language-supervised, region-aware pruning removes spatially coherent low-utility regions under a controlled keep-rate schedule, producing compact slide representations before multimodal fusion. On SlideBench VQA, SLICEChat achieves 79.84% accuracy on TCGA and 59.09% on BCNB cohorts, outperforming prior slide-level pathology MLLMs, and achieves the highest overall WSI-Bench metrics. It also provides competitive memory usage and the inference latency among the evaluated models. These results demonstrate accurate and computationally efficient multimodal reasoning over gigapixel WSIs.

cs.CV · cs.CL

版本更新 · v4arXiv:2607.22140

No Edges, No Verdict: A Large-Scale Empirical Study of Declared Dependency Graphs in 78K SBOMs in the Wild

Artur Zięba-Kozarzewski

原文摘要

Software Bills of Materials (SBOMs) are read not only as inventories but as dependency graphs: vulnerability triage, reachability filtering and impact analysis traverse the edges an SBOM declares. We present the first population-scale study of the declared graph, over 78,612 SBOMs committed to public code (77,092 parseable). Of these, 52.9% omit the dependency-relationship field, although the NTIA minimum elements require it (42.3% once the 46.5% of files carrying the tool entry of a single generation harness are set aside), and a further 8.8% declare a graph in which most components are orphans, so for 61.7% a missing path says nothing about reachability. Scans of 11 large container images are all degenerate (91.4-98.0% orphans), through file entries. The format does not predict which documents these are; the producing tool does (eta^2 = 0.41-0.65), jointly with the ecosystem where a document describes one. CycloneDX completeness declarations appear in 0.10% of CycloneDX documents, and a widely used quality score separates the regimes only weakly. Reading such graphs closed-world, so that no declared path means unreachable, discards almost the whole inventory: under a production detector the median degenerate document would lose 96.4% of its components, which carry 29 version-confirmed known-exploited CVEs across 1,901 documents. Where graphs are informative, the veto touches 14 such CVEs across 164 documents, which measures its reach, not its correctness. On an 18-SBOM testbed scored with the KEV flag removed (EPSS retained), the veto suppressed 5 of 14 version-confirmed known-exploited instances, Log4Shell among them; reading silence as unknown restores them in this illustration. We release the scanner and the dataset.

cs.SE · cs.CR

版本更新 · v2arXiv:2611.04253

UMLoad: Fast On-Demand Model Loading on Unified Memory Architecture

Zimeng Wang, Jinrong Yang, Rong Chen

原文摘要

On-demand model loading dominates response latency for interactive on-device AI, yet unified memory architectures (UMAs), now common on edge devices, should make it cheap by placing weights in memory the GPU already sees. However, frameworks still use the loading flow built for discrete GPUs, leaving significant inefficiencies. This paper presents UMLoad, a system-level model-loading accelerator that decouples a framework's logical allocations from their physical page backing. UMLoad uses on-demand reconstruction to eliminate the weight copy while preserving copy independence, and GPU-assisted page zeroing to accelerate runtime allocation while preserving its security guarantee. Implemented on Intel, AMD, and NVIDIA UMA platforms and evaluated with llama$.$cpp, PyTorch, and vLLM across six models, UMLoad reduces average loading time by 36.6%-71.9% over vanilla and 19.9%-62.7% over pipelined loaders, and cuts mean LLM-routing time to first token (TTFT) by 51.3%-59.3% and model-backed tool completion latency by 10.2%-31.6%.

cs.OS · cs.AR

版本更新 · v2arXiv:2606.26757

Batch-Invariant Spectral Intelligence for Robust and Explainable Insect Authentication

Majharulislam Babor, Giacomo Rossi, Annalisa Altavilla, Oliver Schlüter, Marina M. -C. Höhne

原文摘要

Edible insects offer an efficient source of alternative protein, requiring less land and water and emitting less greenhouse gas than conventional livestock. However, their successful integration into the food supply chain demands reliable species authentication to control allergen exposure, prevent adulteration, and meet regulatory standards. Near-infrared spectroscopy provides a rapid analytical tool, but its performance drops when applied to production batches unseen during training due to batch-to-batch variation in spectral measurements. We introduce the Batch-Invariant Spectral Network (BISN), an end-to-end framework that combines a learnable preprocessing module, initialised with Savitzky-Golay filtering, with an unsupervised, entropy-regularised auxiliary branch connected through a gradient reversal layer. The branch uses no batch labels and supplies opposing entropy gradients to the auxiliary head and preprocessing module. Using 2,700 spectra from three species (Acheta domesticus, Hermetia illucens, and Tenebrio molitor) collected across three independent production batches, BISN achieves a mean leave-one-batch-out accuracy of 0.93 (standard deviation 0.04), outperforming the strongest baseline by four percentage points (p=0.002). Further insights gained by using explainable AI confirm that model decisions consistently rely on the lipid and protein absorption regions across all folds, connecting predictive performance to known insect biochemistry. BISN addresses both cross-batch robustness and biochemical interpretability for automated insect species authentication in a controlled benchtop setting. The source code and dataset are publicly available at https://github.com/majharB/bisn.

cs.LG

版本更新 · v2arXiv:2611.04527

Future Representation Distillation for Imagination-free World Action Models

Jaehyeong Jo, Sangwon Jang, Sihyun Yu, Seonghyeon Ye, Yekyung Nah, Hojung Jung, Kimin Lee, Sung Ju Hwang

原文摘要

World Action Models (WAMs) use the predictive knowledge of pretrained video diffusion models for robot control through future video prediction. However, iterative video denoising is costly, and inaccurate visual predictions can compromise action prediction. Our key idea is to make this predictive knowledge available through visual representations computed from the current observation, enabling action prediction without generating future videos. We introduce DreamFree, a WAM that repurposes a pretrained video diffusion model as a predictive visual encoder through representation distillation. The visual encoder learns to predict a frozen video diffusion model's representation using only the current observation. An action module is then trained to predict actions by extracting action-relevant information from the visual encoder. Across real-world and simulated tasks, DreamFree achieves higher success rates than state-of-the-art VLAs and WAMs, while performing real-time closed-loop control at 11Hz with a 14B video diffusion backbone. Experiments show that DreamFree can translate stronger video priors and additional video data into better robot control and enable learning new robot tasks from video demonstrations, including videos from a different embodiment, without action annotation for the new tasks.

cs.RO

版本更新 · v2arXiv:2605.16725

Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models

SeungWon Seo, DongHeun Han, SeongRae Noh, HyeongYeop Kang

原文摘要

Executable world models can be read, edited, executed, and reused for planning, but only if the program captures the environment's transition law rather than semantic shortcuts in its surface vocabulary. We study online executable world-model learning under prior misalignment, where an agent must induce state-dependent dynamics from interaction evidence alone, without rule descriptions, reward signals, or trustworthy lexical priors. We introduce Alice, a closed-loop system that treats failed candidate updates as structural signal: when a candidate explains a new transition but loses previously explained ones, the preservation conflict reveals dynamics that the current program had conflated. Alice refines these conflicts into hypothesis classes that both provide a few broken examples, one per affected class, for update and guide frontier exploration toward transitions that are novel and underrepresented with respect to the current program. We evaluate Alice on Baba in Wonderland, a prior-misaligned variant of Baba Is You that preserves simulator dynamics while replacing semantically meaningful rule-property labels with unrelated words. Experiments show that Alice substantially improves executable world-model learning under prior misalignment, and five-run ablations support overall improvement trends as class structure and exploration signals are added. Project page: https://ssw03270.github.io/BABAinWonderland_NeurIPS-26_Page/.

cs.AI

版本更新 · v6arXiv:2606.10829

Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models

Yusuf Sahin, Ahmed Rockey Saikia, Volkan Cevher, Paolo Favaro

原文摘要

Masked diffusion language models can reduce inference steps by revealing multiple tokens per denoising iteration, but this parallelism is fragile: positions that are individually confident may be unsafe to commit together when their predictions are coupled. Existing training-free samplers such as Top-$k$, Fast-dLLM, and EB-Sampler mainly control how many tokens to reveal, while often ranking candidates by token-wise scores that ignore interactions within the selected set. We propose ADAS, a training-free reranking rule that leaves the base sampler's stopping rule unchanged and greedily discounts each token-wise confidence score according to its attention to already selected positions, weighted by their prediction uncertainty. Across LLaDA-8B-Base and Dream-7B-Base on the reasoning benchmarks GSM8K and MATH500 and the code benchmarks HumanEval and MBPP, plugging ADAS into all three samplers improves low-NFE performance at matched denoiser evaluations by $9.11$ and $10.46$ percentage points on average, respectively, with $3.1\%$ per-forward runtime overhead. Code is available at https://github.com/yusufsahin99/ADAS.

cs.CL · cs.AI

版本更新 · v2arXiv:2604.02285

The Computational Complexity of Avoiding Strict Saddle Points in Constrained Optimization

Andreas Kontogiannis, Ioannis Panageas, Vasilis Pollatos

原文摘要

The complexity of finding second-order stationary points (SOSPs) in constrained settings has remained unclear and has been highlighted as an open question by the works of Hollender and Zampetakis [2023] and Kontogiannis et al. [2024]. In particular, under one established definition (SOSP1) where nonnegative curvature is required only along the null space of the active constraints [Bertsekas, 1997], the problem lies in TFNP, and algorithms with $O(poly(1/ε))$ running times have been proposed. Under another established notion of stationarity (SOSP2) checking is coNP-hard in high dimensions. We investigate the computational landscape of finding SOSPs under polytope constraints. We prove that, even if promised that all KKT points lie a constant distance away from the domain's boundary--where SOSP1 and SOSP2 reduce to the standard unconstrained conditions--finding an approximate SOSP under either definition is PLS-hard, and the hardness continues to hold even in $[0,1]^2$. As a direct consequence, our result establishes a fundamental barrier on the continuity of SOSP-computing algorithms: unless PLS=CLS, no deterministic, iterative algorithm with a computationally efficient, continuous update rule can guarantee that every $ε$-approximate fixed point is an $(ε,\sqrtε)$-SOSP, even under the above interior promise. We establish PLS-completeness by proving that the problem of finding approximate SOSP1 belongs to PLS in high dimensions. In addition, we prove that, for every fixed $d\ge 2$, finding an approximate SOSP2 is also PLS-complete, escaping the coNP-hardness which appears in high dimensions. We also establish PLS-hardness and a polynomial-time search reduction to LOCALOPT for finding $(r^{2+γ},r)$-local pure Nash equilibria, for every fixed rational $γ\in(0,1]$, in two-player nonconvex common-interest games with actions in $[0,1]$.

cs.CC · cs.DS

版本更新 · v2arXiv:2611.04108

Separating Common and Unique Directions for Model Merging

Shiting Wang, Yingjie Zou, Ke Li

原文摘要

Model merging combines multiple fine-tuned models without additional training, and arithmetic methods have emerged as a simple yet effective way to merge models without data. However, existing arithmetic methods treat task vectors in parameter space and apply a single element-wise rule to directions that can differ in mergeability. In a shared directional basis, we find a consistent two-regime structure: a low-dispersion common bulk shared across tasks and a high-dispersion task-dominated tail that carries disproportionate energy. These findings motivate Common--Unique Subspace Decomposition (CUSD), a data-free pre-merging method that separates task vectors into common and unique directional components, merges the common components with a downstream arithmetic operator, and retains unique residuals separately. Experiments across $11$ base models, four model families, and four arithmetic-based merging operators show that CUSD improves 42 of 44 model--operator combinations and achieves up to 22.5% improvement over the corresponding baselines. Our code is publicly available at https://github.com/stwang666/CUSD

cs.LG · cs.AI

版本更新 · v3arXiv:2610.33004

Entity-Aware Evaluation of OCR Systems for Historical Document Transcription

Camilo Mariño, Diego Belzarena, Marina Gardella, Ignacio Ramírez, Gregory Randall, Jean-Michel Morel

原文摘要

Optical Character Recognition (OCR) is essential for digitizing historical archives, yet standard evaluation metrics such as Character Error Rate (CER) do not necessarily reflect whether meaningful information, such as names, dates, and identifiers, is preserved. In this work, we investigate entitylevel analysis of OCR errors as a complementary perspective for evaluating OCR quality in historical documents. Using a publicly available benchmark of 175 documents from the Berrutti Archive, augmented with 5,209 manually annotated entity mentions that will be released upon acceptance, we compare sequence-recognition OCR systems, OCR-specialized vision-language models, and general-purpose vision-language models. Beyond global transcription accuracy, we analyze entity preservation and recoverability under varying character-level edit tolerances. Our experiments show that OCR rankings depend on the evaluation criterion: while Qwen 3.6 achieves the highest entity coverage across all tested tolerances, several systems with lower exact-match coverage recover substantially when small errors are tolerated, suggesting that many of their errors correspond to localized character-level deviations rather than fundamentally incorrect entity transcriptions. Conversely, some systems remain unable to recover many entities even under relaxed matching. These findings show that OCR quality cannot be fully characterized by aggregate transcription metrics alone and highlight the importance of evaluating how OCR errors affect the preservation and recoverability of meaningful information.

cs.CL · cs.AI · cs.CV · cs.LG · eess.IV

版本更新 · v7arXiv:2310.19385

Gradient-free online learning of subgrid-scale dynamics with neural emulators

Hugo Frezat, Ronan Fablet, Guillaume Balarac, Julien Le Sommer

原文摘要

In this paper, we propose a generic algorithm to train machine learning-based subgrid parametrizations online, i.e., with $\textit{a posteriori}$ loss functions, but for non-differentiable numerical solvers. The proposed approach leverages a neural emulator to approximate the reduced state-space solver, which is then used to allow gradient propagation through temporal integration steps. We apply this methodology on a chaotic two-timescales Lorenz-96 system and a single layer quasi-geostrophic system with zonal dynamics, known to be highly unstable with offline strategies. Using our algorithm, we are able to train a parametrization that recovers most of the benefits of online strategies without having to compute the gradient of the original solver. We found that training the neural emulator and parametrization components separately with different loss quantities is necessary in order to minimize the propagation of approximation biases. Experiments on emulator architectures with different complexities also indicates that emulator performance is key in order to learn an accurate parametrization. This work is a step towards learning parametrization with online strategies for climate models.

physics.comp-ph · cs.LG · physics.flu-dyn

版本更新 · v2arXiv:2607.22149

Unbiased Open World Regularization for Fair Self-Supervised Learning

Léo Nicollier, Marc Pic, Pablo Musé, Enric Meinhardt-Llopis, Gabriele Facciolo

原文摘要

Despite recent advances, self-supervised learning (SSL) models and Joint-Embedding Predictive Architectures (JEPAs) remain susceptible to spurious correlations. Many anti-collapse regularizers constrain the global representation distribution to match a prescribed target, such as a multivariate Gaussian or the uniform distribution on the sphere. However, global matching does not prevent groups defined by a bias attribute from occupying distinct regions of the representation space. We show that existing encoder-only debiasing regularizers, including EnD and FSCL, can be interpreted as restricted forms of conditional distribution matching. Building on this interpretation, we introduce Unbiased Open World (UOW), which matches the representation distribution within each observed bias group to a common target distribution. At the population optimum, using a discriminative conditional discrepancy guarantees independence between the representation and the targeted attribute. We instantiate UOW in Gaussian and spherical spaces and evaluate it across controlled synthetic settings and real-world fairness benchmarks. Across Synthetic Engraving, Colored MNIST, CelebA, and Waterbirds, conditional matching substantially reduces bias compared with global regularization while preserving useful downstream representations. Jointly conditioning on multiple bias attributes further reduces intersectional disparities missed by separate marginal constraints. Finally, experiments on CelebA show that models can be trained from random initialization using UOW as a pretraining objective, provided checkpoints are selected according to fairness-aware validation criteria.

cs.LG

版本更新 · v2arXiv:2611.04074

The Complexity of ReLU Network Synthesis from a Parameter Multiset

Dimitrios Myrisiotis

原文摘要

We ask how hard it is to build a ReLU network when its parameter values are given in advance. An instance supplies an appropriate encoding of a target behavior, a multiset of rational numbers, and a bound on the number of neurons (output included). The question is whether one can choose the graph of a ReLU network within the bound, and place the numbers on its edges and biases so that it meets the target. This separates the numbers from the architecture. Matching two labeled examples exactly is already $\mathsf{NP}$-complete, so we ask what changes when the target must hold on every input or on average. Agreeing with a Boolean circuit on every Boolean input is $Σ_2^{\mathsf P}$-complete, already for four neurons. Agreeing with a given ReLU network on every real input lies in $\mathsf{DP}$ for every fixed neuron bound and is $\mathsf{DP}$-complete for three neurons. Approximating a ReLU network on the unit cube within absolute error one everywhere is $Σ_2^{\mathsf P}$-complete, even with no hidden neurons and all numbers equal and positive. Deciding whether some network has expected squared loss at most a threshold is $\mathsf{NP}^{\mathsf{PP}}$-complete for uniform Boolean inputs. For uniform inputs on the unit cube and for standard Gaussian inputs with a positive threshold, the same holds for two neurons when a positive risk gap, given in binary and possibly exponentially small, separates yes from no instances. Without a gap, the cube version is complete for guessing a polynomial-length string, then comparing a sum of exponentially many rationals with a threshold, all computable in polynomial time from the input and the guess.

cs.CC · cs.LG

版本更新 · v2arXiv:2609.33387

From Grey-Box to Green-Box: When can Physics-Informed Machine Learning Reduce Carbon Footprints in Structural Health Monitoring?

Daisy R. Bradley, Nathan A. Hinchliffe, Daniel J. Pitchforth, Matthew R. Jones, Elizabeth J. Cross

原文摘要

Machine learning plays an increasingly vital role in engineering, but the corresponding increase in compute time is not without environmental cost. Physics-informed machine learning or "grey-box" models have been developed to overcome some of the limitations of traditional black-box learners, utilising the physical insight that an engineer would have about the structure they are modelling and have shown promising results in the structural engineering field among many others. This work explores whether an additional advantage could be a reduced environmental impact, considering the relationship between training data quantity and training time, linking this duration to carbon emissions from computing. In a structural health monitoring context, four physics-informed machine learning approaches - spanning Gaussian processes and neural networks - are evaluated: residual modelling, input augmentation, hybrid modelling, and constrained learning. The emissions for training each of the models to reach a given error threshold is compared, and in most examples, shown to be lower for the physics-informed models (with input augmented models being an exception). This reduction in training emissions further compounds the environmental savings achieved by collecting and storing less data. Although promising results, we cannot expect a silver bullet and the case studies demonstrate that a trade-off is needed between the increased complexity that comes from introducing physics into a machine learner, against the gain from reduced training data requirements.

cs.LG

版本更新 · v3arXiv:2606.17441

Patients With Personality: Realistic Patient Simulation through Controlled Diversity and Selective Disclosure

Moritz Schlager, Friederike Jungmann, Samuel Schmidgall, Philipp Raffler, Franziska Hartl, Eva Wende, Paula Roßm"uller, Conrad Ketzer 等 18 位作者

原文摘要

Realistic patient simulation is a key requirement for developing and testing clinical LLMs at scale without costly user studies. Existing simulators lack realism and controllability: they overshare information and miss the variability of real patient behavior. Here, we introduce PatientsWithPersonality (PWP), a patient simulation framework that generates realistic yet diverse patient responses through explicit personality parametrization over a latent patient state. Grounded in the six-dimensional HEXACO personality model, it gives fine-grained control over conversational style, cooperativeness, and information disclosure. We evaluate PWP in the first direct comparison of different patient simulators under a shared protocol, anchored in transcripts of real physician-patient encounters. Clinicians judge PWP conversations as realistic at least as often as the recorded encounters themselves and far more often than prior simulators, and almost never flag them as "too informative". Our simulator also reproduces the disclosure pacing of real patients, and its HEXACO-conditioned personality traits can be recovered by clinicians and an autorater. PWP further shows a substantially wider behavioral range than the closest baseline. In a downstream benchmark, LLMs interviewing patients simulated by PWP perform closest to how they perform on the real encounters, whereas prior simulators make the task easier. PWP thus provides a realistic, steerable, and diverse patient population for improving and benchmarking clinical LLMs.

cs.HC · cs.AI · cs.CY

版本更新 · v6arXiv:2307.16694

Investigating and Improving Latent Density Segmentation Models for Aleatoric Uncertainty Quantification in Medical Imaging

M. M. Amaan Valiuddin, Christiaan G. A. Viviers, Ruud J. G. van Sloun, Peter H. N. de With, Fons van der Sommen

原文摘要

Data uncertainties, such as sensor noise, occlusions or limitations in the acquisition method can introduce irreducible ambiguities in images, which result in varying, yet plausible, semantic hypotheses. In Machine Learning, this ambiguity is commonly referred to as aleatoric uncertainty. In image segmentation, latent density models can be utilized to address this problem. The most popular approach is the Probabilistic U-Net (PU-Net), which uses latent Normal densities to optimize the conditional data log-likelihood Evidence Lower Bound. In this work, we demonstrate that the PU-Net latent space is severely sparse and heavily under-utilized. To address this, we modify the training objective to introduce the entropy-regularized Sinkhorn Divergence in the latent space, which promotes homogeneity across all latent dimensions, effectively improving gradient-descent updates and latent space informativeness. Applied to public datasets of various clinical segmentation problems, our proposed methodology achieves the best Empirical Wasserstein Distance on every dataset compared against preceding latent variable models for probabilistic segmentation. The results indicate that encouraging a homogeneous latent space significantly improves latent density modeling for medical image segmentation.

cs.CV

版本更新 · v2arXiv:2607.27002

IMFuse: Instance-Aware Multi-Layer Fusion for LLM-Enhanced Sequential Recommendation

Yuheng Zheng, Yu Cui, Bin Wu, Jian Zhang, Ye Feng, Can Wang, Jiawei Chen

原文摘要

Leveraging large language models (LLMs) to enrich item embeddings with textual semantics has become a prevailing paradigm for enhancing sequential recommendation (SR). However, existing methods typically rely solely on the final-layer LLM embeddings, leaving the semantics encoded in other layers largely unexploited. Through an empirical analysis, we uncover three key findings: 1) item embeddings from deeper LLM layers suffer from increasingly severe spectral collapse, which reduces their information richness and hinders the optimization; 2) intermediate LLM layers encode complementary item semantics beyond the final layer; 3) different items exhibit heterogeneous layer-wise semantic patterns. These findings suggest that the final layer alone is insufficient and that multi-layer LLM semantics should be exploited adaptively for each item. To this end, we propose IMFuse, a novel Instance-Aware MultiLayer Fusion strategy for LLM-enhanced SR. IMFuse adaptively aggregates embeddings from all LLM layers with learnable layerwise fusion weights, and further customizes the fusion for each item via an instance-aware Mixture-of-Experts (MoE) module. As a plugand-play strategy, IMFuse can be seamlessly integrated into various SR backbones and LLM-based enhancement methods. Extensive experiments on four real-world datasets demonstrate that IMFuse consistently improves state-of-the-art methods, achieving an average relative improvement of 6.72% with limited computational overhead.

cs.IR

版本更新 · v3arXiv:2511.14581

Online learning of subgrid-scale models for quasi-geostrophic turbulence in planetary interiors

Hugo Frezat, Thomas Gastine, Alexandre Fournier

原文摘要

Machine learning approaches to subgrid-scale (SGS) modeling are now well established in atmospheric and oceanic applications. Among these, online end-to-end learning, where the differentiable solver participates in the training, has shown particular promise. Yet existing studies are largely restricted to idealised periodic domains, with no mechanical boundaries, precluding them from addressing the dynamics of bounded rotating flows relevant to planetary interiors. Here we consider two-dimensional quasi-geostrophic turbulence in a rapidly rotating annular bounded domain. We examine three configurations varying the geometry of the container and the rotation rate. The system exhibits key features such as zonal jets, Rossby waves, and, in the spherical shell geometry, a slow quasi-periodic inward drift of the jets. The spectral properties of the zonal and non-zonal flow can be understood in the framework of zonostrophic turbulence theory. We develop a differentiable solver for this system, which allows us to train SGS models online, over a time span of one turnover time, using coarse-grained data from direct numerical simulations. In all cases, a SGS model trained on a single turnover time accurately reproduces global integrated diagnostics, energy spectra as well as long-term dynamical behaviours, such as jet migration, occurring on timescales which exceed the training window by one order of magnitude. The online-trained model further outperforms classical hyperdiffusivity and Leith closure schemes, for which reducing the radial resolution is impractical. The resulting speed-up paves the way to further investigations of long-term geophysical fluid processes beyond the reach of direct numerical simulations.

physics.flu-dyn · astro-ph.EP · cs.LG

版本更新 · v2arXiv:2611.00815

VCoT-SQL: Enhancing Text-to-SQL Generation through Dual Chain-of-Thought Validation Training

Rui Zhang, Yujia Su, Ruixuan Li, Yuhua Li, Yixin Su

原文摘要

Open-source LLMs provide a flexible alternative to closed-source models for Text-to-SQL but still struggle with complex queries. Finetuning with chain-of-thought (CoT) data improves reasoning, yet standard datasets lack CoT annotations, requiring synthetic generation. Existing synthesis methods only verify the final answer, allowing flawed reasoning steps to corrupt the training data. We propose VCoT-SQL, a framework that improves Text-to-SQL generation through intermediate-step validated CoT supervision and a dedicated SQL validator, which enables small open-source models to outperform frontier closed-source models. VCoT-SQL trains two complementary models on curated reasoning traces: an SQL generator using clause-level CoT templates where reasoning steps are verified via execution and schema alignment checks, and an SQL validator using diagnostic CoT templates to detect syntactic, semantic, and type level errors. We further design a hierarchical schema filtering pipeline that integrates and refines complementary retrieval strategies to distill relevant database elements. VCoT-SQL achieves 66.82% execution accuracy on challenging dataset BIRD dev and 86.8% on Spider test, improving the base 7B model by 7% on BIRD. Notably, our CoT synthesis relies on 7B models yet outperforms methods that use 72B-scale or even proprietary closed source teachers for data generation, demonstrating that rigorous step-level validation can be more effective than scaling up teacher model size. Our dataset and code are available at https://github.com/INTREBID/VCoT-SQL.

cs.AI

版本更新 · v2arXiv:2610.26684

MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control

Lynn Yi, Zihan Xiong, Junjie Cao, Xiaolong Weng, Yingzhe Ma, Gus Xia, Jinliang Liu, Yuxin Xie 等 20 位作者

原文摘要

A cover song re-renders an existing piece, most commonly by preserving its tonal content -- melody and chord progression -- while reshaping other musical attributes. This suggests a natural formulation for generative cover synthesis with pretrained music language models: explicitly control tonal content, while specifying lyrics and style through text. Existing approaches condition on frame-level features, tightly coupling generation to the reference's timing and structure, and limiting flexibility such as tempo variation, structural rearrangement, or partial conditioning. To this end, we present MuLaCover, a cover generation model that conditions a pretrained text-to-song foundation model on an editable symbolic lead sheet. Our design enables alignment-free control: generated outputs preserve the tonal signature of the source without frame-level alignment, allowing flexible timing, structure, and segment-level generation. We further introduce a training curriculum with partially mismatched audio-symbolic pairs, improving diversity and robustness. We evaluate MuLaCover with objective metrics, standard subjective ratings, and in-depth expert interviews that provide fine-grained diagnostic insights. Experiments show that MuLaCover achieves state-of-the-art performance among open-source systems and is competitive with leading commercial models such as Suno-v5.5. Audio samples and code are available at our project page: https://mulalabs.ai/mulacover/

cs.SD · eess.AS

版本更新 · v3arXiv:2604.27810

Hyper-Dimensional Fingerprints as Molecular Representations

Jonas Teufel, Luca Torresi, André Eberhard, Pascal Friederich

原文摘要

Numerical molecular representations underpin virtual screening, property prediction, and materials discovery. Conventional fingerprints are efficient and deterministic but lose structural information through hash-based compression at low dimensionalities, whereas graph neural networks recover expressiveness through compute-intensive, task-specific training. Here, we introduce hyperdimensional fingerprints (HDF), which compose the chemical attributes of atoms and their multi-hop environments through algebraic operations on high-dimensional vectors, producing deterministic representations without any training. Across diverse property-prediction benchmarks, HDF ranks consistently among the best representations across datasets and models. Crucially, HDF encodes structure more efficiently: at low dimensionalities, its distances correlate with graph edit distance more strongly than Morgan fingerprints', yielding effective similarity metrics and competitive nearest-neighbor regression at just 64 components. In Bayesian optimization, HDF-based surrogates are more sample-efficient than Morgan fingerprints with a Tanimoto kernel for most of the tested objectives. These results establish HDF as compact, training-free representations for property prediction, similarity search, and sample-efficient optimization.

cs.LG

版本更新 · v2arXiv:2610.25256

PanoDent-KD: From Generalist Knowledge Distillation to Cross-Dataset Specialist Detection and Embedded Deployment in Panoramic Radiographs

Muhammad Waqas Ashraf, Imad Ali Shah, Ali Hassan

原文摘要

Reliable panoramic-radiograph detection requires consistency across datasets with different class definitions and deployment software. We present PanoDent-KD, an auditable 1280-pixel YOLO26m pipeline linking a 12-class source generalist, feature-level knowledge distillation (KD), exact classifier-row transfer, teacher-free five-class specialization, and embedded deployment. A common training and evaluation pipeline compares three source-training arms across three seeds: a supervised baseline (B1), single-teacher KD (STKD), and multi-teacher KD (MTKD). Five shared classifier rows initialize nine OralXrays-9 specialists, while the backbone, FPN-PAN neck, and dual-detection-head topology are retained unchanged. On the 2,686-image test subset, all three arms achieve macro box F1 near 0.82. B1 achieves the highest three-seed arm-level mean macro box F1 (0.8239$\pm$0.0027) and $mAP_{50:95}$ (0.6130$\pm$0.0067). STKD seed 1, selected after development but before final testing, was used for deployment. Its Jetson Orin Nano Super FP16 TensorRT engine achieves 77.03-ms median and 80.86-ms P95 prediction-call latency, throughput of 12.90 images/s, and gross total-module energy of 1.39 J/image, with high numerical agreement between within-device PyTorch and TensorRT FP16 inference. These findings demonstrate the feasibility of an auditable, device-specific deployment workflow, but do not establish clinical validity or improved target-domain accuracy from KD.

cs.CV · cs.PF

版本更新 · v3arXiv:2607.08407

Who Needs DRAM? We Have Fiber

Hannah Atmer, Yuan Yao, Thiemo Voigt, Stefanos Kaxiras

原文摘要

The rising pressure on DRAM availability and contract pricing reflects generative AI's massive high-performance memory requirements. This pressure is heavily compounded by hyperscale data center expansion, which now consumes a significant portion of global DRAM output. In this work, we propose a new architecture, Fiber Memory, which reimagines the role of optical fiber in a hyperscale data center, deploying it as an active, recirculating delay-line memory for immutable data, such as large language model weights. We present a hybrid data- and pipeline-parallel optical broadcast delay-line memory architecture that accounts for fiber's physical realities. By incorporating space-division multiplexed multi-core fibers, passive optical tap-and-amplify interfaces, co-packaged optics, and centralized in-ring 3R (re-amplify, reshape, retime) regeneration, our case study evaluation suggests that Fiber Memory can eliminate redundant weight storage across tens of thousands of AI accelerators and reduce weight-delivery power by over 75% compared to traditional HBM3e configurations.

cs.AR · cs.DC · cs.ET · cs.NI