跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 10:17 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 11:11 — 2026-11-08 11:11（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：2026-11-08 10:17最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

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。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 10:15（北京时间）
新论文 · v1arXiv:2611.03617

Tracing the Scientific Discovery Capacity of LLMs to Their Training Data

Arda Uzunoglu, Mahler Revsine, Michael Schatz, Benjamin Van Durme, Mehrdad Farajtabar, Daniel Khashabi, Eric Nalisnick

原文摘要

Large language models (LLMs) show growing promise for scientific discovery, yet basic questions remain about what enables reliable discovery. How can we trace the scientific discovery capacity of LLMs to their training data? We study this question as one of missing probability mass and develop a theoretical account in which monofacts-the facts observed once during training-set the discovery capacity. In materials science and regulatory genomics, we directly manipulate monofact rates in training sets and find that more monofacts consistently yield more discoveries across two open-weight model families, sampling strategies, and reasoning budgets. Further experiments show the relationship cannot be explained by training-set diversity alone and can transfer across scientific domains when paired with in-domain data. Together, our results identify monofact rate in training data as a key factor governing discoveries in language models.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03615

A Circuit Complexity Trichotomy For Regular Languages

Stefan Göller, Amaldev Manuel

原文摘要

We establish a trichotomy for the non-uniform, unbounded-fan-in circuit complexity of regular languages: the complexity of every regular language lies in exactly one of $O(1)$, $Ω(\log n)\cap O(\log n\log\log n)$, or $Ω(n)\cap O(n)$. Our main technical contribution is a characterization of the sublinear class in terms of algebra, word congruences, regular expressions, and logic. This class consists precisely of the regular languages computable by constant-depth circuits of size $O(\log^2 n)$, or, equivalently, by circuits of size $O(\log n\log\log n)$ and depth $O((\log\log n)^2)$. Consequently, every regular language of sublinear circuit complexity is definable in $\mathrm{FO}^2[Σ,<,\mathrm{mod}]$, which is contained in wire-linear $\mathbf{AC}^0$. For each of the three classes, deciding membership is $\mathbf{PSPACE}$-complete when the language is specified by a nondeterministic finite automaton. We also obtain a corresponding classification for regular languages with a neutral letter.

cs.CC · cs.FL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03614

Benchmark Prediction with Sparse and Unpaired Cached Responses

Hayden Helm, Avijit Ghosh, Ben Johnson, Carey Priebe

原文摘要

Evaluating a generative model on all queries from all available benchmark tasks is prohibitively expensive. As such, models are often evaluated on different subsets of tasks and/or different subsets of queries from a given task. The resulting collection of responses and the corresponding (model, task) score matrix are sparse and unpaired. In this paper, we introduce the Product Kernel Perspective Space (PKPS), a collection of low-dimensional representations of models based on their embedded responses. PKPS generalizes existing methods for representing black-box generative models by comparing responses to similar -- rather than just identical -- queries and is therefore able to utilize sparse and unpaired information. Theoretically, we show that benchmark prediction using PKPS is query-efficient relative to methods that only use information from dense and paired portions of the evaluation data. Empirically, we show that PKPS-based methods outperform baselines on benchmark prediction across two large benchmark suites.

cs.LG · stat.ME · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03612

Efficient Closure Learning in Dynamical Systems: A Comparison of Data-Assimilated and Embedded Approaches

Rileigh Bandy, Teresa Portone, Mohammad Khalil, Eric Crislip, Kyle Neal

原文摘要

Increased computing power has transformed computational science and improved predictive capabilities for complex systems, but many phenomena still exceed current simulation capabilities or require rapid evaluations for fast design iterations. Closure models address this challenge by approximating unresolved effects in reduced or incomplete dynamical systems. Data-driven closures offer a flexible mechanism for improving model accuracy and applicability, but approaches that embed the closure within a computational model for construction and training phases can be computationally expensive and cause numerical instabilities in the computational model during training. To avoid the challenges posed by embedded approaches, staged approaches to closure-model learning have been developed. The first stage uses data assimilation to infer state and closure trajectories from observations. The second stage trains a machine learning closure model offline using the assimilated data, thereby avoiding repeated simulator calls during training. In this work, we investigate the cost and accuracy tradeoffs between embedded and staged data-driven closure modeling approaches for a synthetic epidemiological SIQR model with a nonlinear state-dependent quarantine closure. The results illustrate a practical accuracy-efficiency trade-off: for this exemplar, embedded training provides the strongest average accuracy, while the staged approach yields comparable qualitative behavior with a moderate increase in error, substantially fewer model evaluations, and improved optimization robustness.

cs.LG · math.DS · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03610

A GPU Engine for Sparse Matrix-Vector Products on $k^2$-Tree-Compressed Graphs

Francesco Tosoni, Gabriele Mencagli

原文摘要

The $k^2$-tree is a compact representation of Boolean matrices: it stores the recursive hierarchy of their non-empty submatrices, with neither values nor coordinates, and serves rows and columns alike. Its traversal, however, locates the children of each node by rank queries, a chain of dependent irregular loads that leaves a GPU waiting on memory. We implement sparse matrix-vector multiplication (SpMV) on $k^2$-trees for the GPU. Since the traversal does not depend on the vector, the positions of the children are static: we descend the tree one level at a time and obtain them from a parallel prefix sum or from a sampled directory of about 0.1 bits per node. Descending in tiles bounds the temporary memory by the depth of the tree, so the device memory of a product is known before it runs. The same traversal computes right and left products, for one vector or a batch, over the plus-times, Boolean and tropical semirings. We evaluate the engine on an NVIDIA GB10 and an H100 with fourteen Wikidata, Software Heritage, web and social graphs of up to 1.2 billion edges, against cuSPARSE, a grammar-compressed GPU engine and a Boolean CSR. Our results show that the tree is 2.3-27x smaller than the CSR of cuSPARSE and that, with its last internal level cached, a product takes 0.7-2.4x the time of cuSPARSE on the right and 0.27-2.6x on the left. On a 1.2-billion-edge graph, a product needs 1.1 GB on the device, 9x less than cuSPARSE. The engine is memory bounded: the $k^2$-tree is the format of choice when device memory, not time, is the constraint.

cs.DS · cs.DB · cs.DC · cs.MS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03776

Proceedings of the CSCW 2026 Workshop on Women's Health as Cooperative Work: Participatory AI Across Care, Community, and Policy

Sherilyn Francis

原文摘要

This submission indexes contributions to the CSCW 2026 workshop, "Women's Health as Cooperative Work: Participatory AI Across Care, Community, and Policy," held on October 11, 2026. The workshop examines women's health as cooperative work spanning patients, caregivers, clinicians, communities, institutions, and digital technologies. Contributions explore participatory AI, coordination breakdowns, the distribution of care labor, governance, decision-making authority, and accountability across care, community, and policy contexts. The index provides paper titles, authors, affiliations, thematic areas, and unique report numbers to support discovery of the corresponding individual arXiv submissions. The workshop proposal is separately published under DOI 10.1145/3785651.3818821.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.02814

Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors

Francisco Valentini, Edgar Altszyler, Martin Fajcik

原文摘要

Neural retrievers are trained to estimate query-document relevance from annotated query-document pairs. Yet annotation protocols may not purely reflect relevance: they select only a subset of documents for labeling, and this selection can favor certain document types over others. We investigate whether supervised bi-encoder retrievers implicitly learn a document-level relevance prior: a query-independent signal encoded in their representation space as a side effect of training on annotated data. We estimate this prior by training simple classifiers on frozen document embeddings and evaluate three state-of-the-art retrievers across multiple IR benchmarks. We find that supervised neural retrievers encode relevance priors that generalize to unseen documents and are consistent across models. These priors are associated with a findability gap: documents with lower prior are systematically harder to retrieve, even when genuinely relevant. This effect appears in supervised dense retrievers but is weaker and less consistent in BM25, and it persists under controlled matched-document comparisons. Using LLM-based explanations, we find that judged-relevant documents tend to be comprehensive, self-contained summaries of mainstream topics, while niche, fragmentary, or highly technical content is often left unjudged. Retrievers appear to internalize this bias, ranking documents with these favored features higher than documents that lack them, independently of their actual relevance. Our findings expose a structural limitation of supervised retrieval: models trained on annotated data do not just learn relevance, but also the implicit document preferences in their training data.

cs.IR · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v7arXiv:2507.22832

Pulling Back the Curtain on Deep Networks

Maciej Satkiewicz, Roberto Corizzo, Marcin Pietroń

原文摘要

In linear models, visualizing a weight vector naturally reveals the model's preferred input direction, but extending this intuition to deep networks via gradients or GradientAscent often yields brittle or adversarial-looking features. We argue that deep networks are better understood as input-conditioned affine operators, whose natural adjoint action pulls a neuron's preferred direction back to input space. We further refine this representation through optional backward-only softening for hard-gated layers and propose pullbacks as an alternative backward operator for existing explanation procedures, including local attribution, smoothing, and iterative ascent. Across convolutional architectures (ResNet50, VGG) and transformer-based models (PVT), replacing gradients with pullbacks yields improvements in 46 out of 60 comparisons across five faithfulness, stability, and localisation metrics. In particular, PullbackAscent improves mean scores over GradientAscent across all five primary metrics on each architecture, reducing mean Infidelity by factors of 2.8 to 5.5. Strikingly, it also produces sharp, perceptually aligned and target-specific perturbations in only a few steps, without post-processing or explicit perceptual priors. More broadly, pullback-based methods achieve the best mean in 13 out of 15 architecture-metric combinations, outperforming established attribution baselines. Our results suggest that adjoint transport can serve as a reusable backward primitive, enhancing existing explanation procedures without architectural changes or elaborate attribution pipelines. We use "Semantic Pullbacks" (SP) to denote the resulting family of pullback-based explanations.

cs.LG · cs.CV · cs.NE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03605

ufakzeka-kulak: Building and Evaluating a 31.6M-Parameter Turkish Speech Recognizer from Scratch

Sait Furkan Teke

原文摘要

ufakzeka-kulak is an open Turkish speech-to-text model of 31.6M parameters, a FastConformer encoder with a token-and-duration transducer (TDT) and a CTC head, trained from scratch and released under Apache-2.0. It writes cased, punctuated Turkish with numbers as words. Its 4,977 training hours come from sources whose licences allow commercial use; 281 hours are human-transcribed, and for the other 4,696 the training text is an uploader subtitle or a machine transcript, kept only where a second, independent reading of the audio agrees with it. The recipe, checkpoint, labelling and export choices were made on development data, and the test sets were scored once, in a release gate fixed before training. With greedy TDT decoding the normalised word error rate (WER) is 0.0921 (95 percent interval 0.0792 to 0.1055) on FLEURS Turkish test and 0.0916 (0.0873 to 0.0958) on Common Voice 27.0 Turkish test, lower than Whisper base and Whisper small on both sets with paired intervals wholly below zero; Whisper large-v3 (greedy) scores 0.0604 and 0.0767. On conversational speech the WER is 0.3807. We also report punctuation and casing, degraded audio, and how closely each shipped export reproduces the trained model.

cs.CL · eess.AS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03604

Near-Optimal Space and Time Cut Sparsification in Turnstile Streams

Honghao Lin, Vahab Mirrokni, David P. Woodruff

原文摘要

A seminal result of Ahn, Guha, and McGregor (PODS'12) showed that a cut sparsifier of an unweighted graph can be computed from a near-linear number of linear measurements. Later work extended this to spectral sparsifiers (Kapralov et al., FOCS'14) and to near-linear recovery time (Kapralov et al., SODA'20). For weighted graphs, these sketches rely on grouping edges by weight, which general turnstile streams do not allow. Chen, Khanna, and Li (FOCS'22) removed this limitation, using $\tilde{O}(n/\varepsilon^3)$ bits of space. We improve the space to $\tilde{O}(n/\varepsilon^2)$ bits. Our algorithm makes one pass over a general turnstile stream of a weighted graph, processes each update in $\tilde{O}(1)$ time, and recovers, in $\tilde{O}(n/\varepsilon^2)$ time, a reweighted subgraph with $O(n\varepsilon^{-2}\log^2 n)$ edges that preserves every cut within a factor of $1\pm\varepsilon$. Its space, update time, and recovery time are all optimal up to polylogarithmic factors.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03602

Reviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning

Tengfei Liu, Yang Shi, Yuran Wang, Yuqi Tang, Yizhuo Jia, Zhuoran Zhang, Qixun Wang, Shujie Li 等 15 位作者

原文摘要

Multimodal large language models (MLLMs) can generate detailed video captions, yet they may overemphasize minor details while overlooking essential context and key events. We argue that not all visual evidence deserves equal attention, as the importance of visual information depends on the content of each video. Motivated by this observation, we propose Reviso, an agentic video captioning framework that learns what to observe and how to gather relevant visual evidence. From a low-frame-rate global preview, Reviso constructs a hierarchical Context--Focus--Points (CFP) observation plan that identifies the video context, prioritizes key aspects, and defines concrete observation targets and corresponding tools. Guided by this plan, Reviso performs goal-directed active perception by selectively revisiting temporal segments and combining tools for fine-grained inspection. It interprets the acquired evidence, updates its plan as needed, and integrates global and local information to generate the final caption. To learn this observation strategy, we develop a verification-guided pipeline that constructs high-quality training trajectories through factual verification and teacher-guided refinement. We further train Reviso using Group Relative Policy Optimization (GRPO), incorporating a key-fact reward for caption quality, a Plan Alignment Reward (PAR) for identifying important observation targets, and an Unproductive Tool-Call Penalty (UTCP) that adjusts observation-cost penalties based on caption quality. Experiments across four video captioning benchmarks show that Reviso outperforms the evaluated open-source baselines, while its generated captions better support downstream video question answering. These findings highlight the effectiveness and potential of priority-guided active observation for video captioning.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03601

DiabAgent: Toward Agentic Physiological Control

Chengxi Li, Shaoxuan Li, Deyao Hong, Qingle Liu, Yi Huang, Puheng Bian, Minzhi Xu, Lanyue Zhang 等 16 位作者

原文摘要

As pretraining scales, medical language models have advanced rapidly in clinical question answering. Their ability to achieve effective physiological control through sustained intervention still lacks systematic quantitative evaluation. Type 1 diabetes provides a concrete setting: impaired insulin secretion creates dependence on exogenous insulin, with dosing continually adjusted using information about meals, exercise, illness, and glucose measurements. We introduce DiabAgent, a research suite for agentic physiological control comprising the Agentic Physiological Control (APC) framework, the DiabetSim simulator, and the SweetBench benchmark. APC controls glucose through medical-device tools, using ongoing observations to infer individual states, accumulate personal experience, and choose treatment actions. We build DiabetSim to simulate different patients, events, and device conditions for scalable virtual testing and training. Using DiabetSim, we construct SweetBench by instantiating 32 scenario designs as 212 glucose-control tasks. With Claude Opus 5.5 and a fixed decision interval of one hour, APC achieves a COGI of 73.5, compared with 71.2 for the open-source closed-loop baseline OpenAPS. Ablations further show that individual adaptation and contextual information improve glucose control. Combining high-frequency rule-based control with lower-frequency agent decisions shows potential for balancing control performance and computational cost. Our work provides a framework, simulator, and evaluation foundation for agents to participate in human physiological control.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03600

Four Bridges: Measuring Deception Propensity in a Multi-Agent Game

Raphael Casey, Michael Simeone, Alberto Tosato, Florian Ernst, Kemal El Moujahid, James Tamplin, Tommaso Tosato

原文摘要

AI agents are increasingly deployed in settings where they interact and coordinate with other agents, yet honesty is mostly measured in single-turn, single-agent benchmarks that pressure the model to deceive. We study deception that emerges in multi-agent interaction without any instruction to deceive. We introduce Kradle, a platform for evaluating AI models, and Four Bridges, an information asymmetry game in which four agents distribute across four rooms: one is the death room, the others hold food worth more if not shared. One agent, the informed agent, knows which room is the death room and can withhold or disclose that information. We evaluate eight frontier models as the informed agent. Deceptive behavior appears in every model and in 73% of all runs (6% to 100% per model), and does not decrease with capability tier within a model family. When the informed agent does disclose, the warning is often challenged, and agents that challenge it enter the death room twice as often as those that do not. Telling all agents that one of them knows the death room collapses deception in six of eight models; telling the informed agent that the room is permanently fatal moves only one. On an open-weight model, an honesty steering vector reduces deception to 0% and adversarial honesty training to 6%. The platform and game provide a testbed for measuring deceptive behavior and comparing interventions.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03599

Should We Combine Our Data? Algorithms and Limits for Privately Assessing Data Sharing

Mahdi Haghifam, Kumar Kshitij Patel, Avrim Blum, Giulia Fanti, Juba Ziani

原文摘要

In this paper, we study when two parties should pool their data to train a machine learning model. Two agents, Alice and Bob, each hold a sensitive labeled dataset and want to train a classifier from a given hypothesis class $\mathcal{H}$. Even when each party's dataset can be perfectly classified on its own, the two parties may follow conflicting labeling standards or have selection biases that affect their features and label sets, such that no single classifier in $\mathcal{H}$ fits their combined data. Before committing to data sharing, Alice and Bob therefore want to test whether a single classifier in $\mathcal{H}$ can jointly fit both datasets---without revealing their individual data points to one another. We formalize this problem from a learning-theoretic viewpoint via $\operatorname{opt}_\mathcal{H}$, the minimum \emph{number of mistakes} made by any hypothesis in $\mathcal{H}$ on their pooled data. Through interactive communication, the agents must distinguish $\operatorname{opt}_\mathcal{H}=0$ (compatible datasets) from $\operatorname{opt}_\mathcal{H}\geq t$ (conflicting datasets) under pure $\varepsilon$-two-party differential privacy. A trusted curator could do this with $t=O(1/\varepsilon)$, and we ask how small $t$ can be without one. For thresholds on the real line over a domain of size $m$, we show that the optimal $t$ is $\tildeΘ(\log\log m/\varepsilon)$, exponentially smaller than the $Θ(\log m/\varepsilon)$ samples needed to privately learn thresholds, even with a curator. For halfspaces in $\mathbb{R}^d$, the dependence on $m$ jumps to $\log(m)$: we give a protocol with $t=\tilde{O}(d^3\log m/\varepsilon)$ and show that some domains require $t=Ω(d\log(m/d)/\varepsilon)$.

cs.LG · cs.DS · cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03598

Online Matching with Arbitrary Stochastic Rewards

Rajan Udwani

原文摘要

Online matching with stochastic rewards is a generalization of online bipartite matching in which an attempt to match an online arrival to an offline resource may fail with some probability. Each arrival allows at most one attempt and the success probabilities of its edges are revealed when it arrives. Greedy is 0.5-competitive, which is the best possible for deterministic algorithms. While better competitive ratios are known in several special cases, beating 0.5 for arbitrary probabilities has remained open. We show that, against the adaptive offline benchmark and for arbitrary probabilities, a randomized Perturbed Greedy algorithm is at least 0.591-competitive in the unweighted setting and at least 0.531-competitive with vertex weights. The perturbation functions combine Greedy with scaled versions of the classic exponential function.

cs.DS · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.18606

On the Limits of Sampling-Based Reachability: Geometry, Dynamics, and Sample Complexity

Jixian Liu, Ihab Tabbara, Hussein Sibai, Enrique Mallada

原文摘要

Reachability analysis is central to safety-critical control, robotics, and neural network verification, but classical computational methods, such as Hamilton--Jacobi reachability and set propagation, scale poorly with state dimension. Sampling-based methods have emerged as a promising alternative, often providing finite-sample guarantees that bound the probability-mass left uncovered. However, an explicit account of how the geometry of the initial set, the dynamics, and the sampling law affect the accuracy of the estimator is not fully available in the literature. We study this by casting sampling-based reachable-set recovery as geometric support estimation over a family of problems specified by an initial set, its dynamics, and a sampling law. First, we identify two regularity properties, positive reach of the initial set's complement and Lipschitz continuity of the dynamics, that together make recovery well-posed: a probability-mass coverage guarantee can be upgraded to accuracy $r$ in Hausdorff distance. Second, we bound the resulting sample complexity: recovery is achievable with $\tilde{\mathcal{O}}\big((e^{LT}/r)^n\big)$ samples, exponential in both the state dimension and the time horizon. Third, we show that neither can be removed: a minimax lower bound of $\tildeΩ\big((e^{LT}/r)^n\big)$ holds for every estimator, so the exponential dependence on dimension and the degradation over the horizon are both intrinsic, not artifacts of a particular method. Experiments on nonlinear systems confirm that adversarial sampling improves constants but not the scaling.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03597

Structured Visual Landscape: Generating Preferred Representations in Biological and Artificial Neural Networks

Yusong Zhao, Edgar Y. Walker, Hao Wang, Mi Lu

原文摘要

Understanding how neurons respond to visual stimulus is an important question in both deep learning and neuroscience. It has significant implications for enhancing the interpretability of black-box artificial neural networks and for understanding the visual representation in the human brain. We propose a structured visual representations landscape and design an activation-based prior that allows us to effectively regularize the landscape with activations from brain regions or neural network units. Our model Vis-Lens integrates a variational autoencoder and a diffusion model into an image generation framework. It enables the generation of natural, realistic preferred images by directly modifying the activation-regularized latent codes without per-image iterative optimization. We demonstrate the effectiveness of our framework on both artificial neural networks and human visual cortex using functional magnetic resonance imaging (fMRI) data. Our framework improves activation modulation and image realism compared with a recent state-of-the-art method for generating preferred visual representations of these neural targets.

cs.CV · cs.LG · cs.NE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03596

Spacetime Emergence in the Memory of a Learning Agent

Philip A. LeMaitre, T. Rick Perche

原文摘要

We show that the causal structure of spacetime can emerge within the memory of a learning agent performing a quantum information task. We train a model-based reinforcement-learning agent to maximize the quantum mutual information between localized quantum probes interacting with a quantum field in Minkowski spacetime, without directly providing it with information regarding the spacetime metric or causal structure. In learning to accomplish this task, the reinforcement-learning agent constructs an internal predictive model whose planner develops the characteristic null structure of spacetime, allowing us to reconstruct the causal structure of the Minkowski metric with high accuracy. Within this task, spacetime geometry is obtained from an agent's successful predictions and actions, providing a first step toward showing that spacetime concepts emerge from operational quantum experience.

quant-ph · cs.AI · cs.LG · gr-qc

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.17971

Beyond MACs: Deployment-Constrained Design Space Exploration for Tensorized Neural Networks

Jinsong Zhang, Minghe Li, Jiayi Tian, Jinming Lu, Zheng Zhang

原文摘要

Tensor-train (TT) compression reduces neural-network parameters, but the latency of a tensorized layer is set by its contraction order and its mapping onto hardware: a contraction path with fewer multiply-accumulate operations (MACs) is not necessarily faster on a systolic array. We present a deployment-constrained, latency-guided design space exploration (DSE) framework for fixed-rank tensorized neural networks (TNNs) under a fixed processing-element (PE) budget. Using MAC-guided path pruning, it evaluates feasible combinations of contraction paths, three PE-array partitions, and input-, output-, and weight-stationary dataflows. By minimizing the sum of inference and training latency estimates, it selects a single physical PE partition shared across layers and both modes, while allowing layer- and mode-specific paths and dataflows. On ResNet-18 and ViT-Ti/4, 25%-50% of the layers select a path other than the minimum-MAC one, the best dataflow varies across layers and models, and on a representative ViT layer the latency-selected candidate reduces simulated latency by 23.5% relative to the minimum-MAC candidate. Deployed on a Xilinx VU9P FPGA accelerator that supports both inference and training, the complete TT+INT8 system achieves 3.28x-4.00x inference and 3.42x-3.85x training speedups over dense implementations with the same PE budget.

cs.AR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03595

DynaSolver: A Neural Operator for Autoregressive 4D Flow Prediction with Dynamic Boundaries

Rui Qian, Shibo Dai, Mengjun Lin, Yuk-Kit Hou, Saining Zhang, Bohan Li, Junhao Chen, Hao Zhao 等 9 位作者

原文摘要

Neural operators provide efficient surrogates for computational fluid dynamics (CFD), but most are designed for static geometries and are not equipped to model unsteady flows induced by continuously moving boundaries. We study dynamic-boundary 4D CFD prediction for articulated moving geometries and introduce RoboCFD-4D, a temporally resolved robotic CFD benchmark spanning diverse morphologies and flow conditions. To address the computational and autoregressive challenges of this setting, we propose DynaSolver, a neural operator that explicitly conditions on boundary evolution and causal flow history. DynaSolver employs an efficient physical-token formulation that amortizes point-to-token projection across the operator stack, substantially reducing repeated point-space spatio-temporal computation while retaining accurate point-level reconstruction. We further introduce Replay-Augmented Parallel Training, which exposes the model to autoregressively generated histories while preserving parallel dense supervision, narrowing the gap between ground-truth-conditioned training and autoregressive rollout. Experiments on RoboCFD-4D show that DynaSolver achieves the best full-rollout accuracy among a broad range of learned CFD surrogates, with its advantage increasing as rollout proceeds, indicating substantially reduced autoregressive error accumulation. Project page: https://made-gpt.github.io/DynaSolver-ProjectPage.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v8arXiv:2509.22075

CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning

Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip, Ammar Ali, Stamatios Lefkimmiatis

原文摘要

Post-training LLM compression often relies on low-rank approximations, which force all columns of a projection matrix to share a single low-dimensional subspace. We propose CoSpaDi, a training-free compression framework that replaces this single-subspace assumption with a union-of-subspaces model via sparse dictionary learning. CoSpaDi factorizes each weight matrix into a dense dictionary and column-sparse coefficients, allowing different columns to select different subsets of dictionary atoms at the same storage budget. To preserve model behavior, we use calibration activations to transform functional reconstruction into a standard dictionary learning problem. Across LLaMA and Qwen models, CoSpaDi improves accuracy-compression and perplexity-compression trade-offs over SVD-based and structured pruning baselines at 20-40\% compression ratios, while naturally supporting sparse-dense computation and post-training quantization of sparse coefficients.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2603.13373

Ethical Fairness in Ubiquitous Health Sensing without Known Attributes

Shaily Roy, Harshit Sharma, Daniel A. Adler, Srijan Sen, Tanzeem Choudhury, Asif Salekin

原文摘要

Wearable and mobile sensing models infer health and well-being in everyday life, yet strong average performance can conceal failures for particular people, contexts, or devices. Existing fairness methods often require sensitive attributes during training, although such attributes may be unavailable, privacy-sensitive, or restricted. Moreover, they may reduce disparities by degrading performance for some subgroups, violating the ethical principle of non-maleficence. We present FLARE (Fisher-guided LAtent-subgroup learning with do-no-harm REgularization), to our knowledge the first attribute-free framework to operationalize beneficence, non-maleficence, and justice in ubiquitous sensing. FLARE uses Fisher information to regularize loss curvature and combines representation, loss, and curvature signals to discover latent performance strata. It then trains a separate model for each stratum using do-no-harm regularization and validation-controlled parameter sharing. We also introduce BHE (Benefit, Harm-Avoidance, Equity), a metric suite for evaluating ethical fairness beyond statistical parity. Across four physiological, behavioral, and clinical sensing datasets, FLARE achieves the highest mean subgroup F1 on every dataset. It is the only evaluated method that improves mean subgroup performance without degrading any evaluated subgroup and the only one that reduces disparity across all 15 evaluated sensitive attributes. Although some baselines achieve larger average disparity reductions, each harms at least one subgroup. Post-hoc analyses on two datasets show that the discovered strata are only weakly aligned with recorded attributes and identify a recurrent within-person state that participant-level attributes cannot capture. Label-free routing and inference take at most 8.1 ms per sample on a smartphone and 10.5 ms on a Raspberry Pi, supporting real-time on-device deployment.

cs.CY · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.26364

Having Dog Ears "for Real": Effects of Active and Passive Haptics on Embodying Non-Human Body Parts in VR

Omar A. Khan, Bao Han Trinh, Lee Lisle, Tiffany D. Do

原文摘要

Embodying non-human body parts in VR is a prevalent practice among certain subcultures and is a personally important creative outlet to many individuals. However, the discrepant morphology between real and virtual bodies can decrease Sense of Embodiment (SoE). Haptic feedback can compensate by increasing SoE felt towards non-human body parts, but there is a literature gap in comparing the effects of different haptic modalities, and their combinations, on SoE. Through an online survey sent out to social VR communities (n = 63), we determined that animal ears are a commonly embodied and ecologically valid non-human body part to study. We then ran a 2x2 within-subjects user study (n = 28) with two independent variables: active haptics, delivered through vibrotactile gloves, and passive haptics, delivered through a physical headband, for when participants reach up to touch virtual dog ears appended to their avatar in VR. Our findings show that (1) passive haptics produced the strongest overall embodiment outcomes, (2) combining modalities reduced the benefits of passive haptics, and (3) SoE towards non-human body parts positively correlates with SoE towards the entire avatar.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03594

Square-Root Pass Semi-Streaming Algorithms for Digraph Problems

Prantar Ghosh, Amirhossein Janfaza

原文摘要

We study directed graph problems in the semi-streaming model where we are restricted to $\widetilde{O}(n):=O(n\cdot \text{polylog}(n))$ space for processing the edge stream of an $n$-node graph and can make one or a few passes to solve the given problem. A longstanding open problem in multipass streaming is determining the number of semi-streaming passes needed to solve directed $s,t$-reachability: there is an exponential gap---$Ω(\log n/\log \log n)$ vs $n^{1/2+o(1)}$---between the best-known lower and upper bounds. Several related fundamental digraph problems, e.g., topological sorting, acyclicity testing, and decomposition into strongly connected components (SCCs), are known to have the same semi-streaming pass lower bound. However, no $o(n/\text{polylog}(n))$-pass upper bound was known for any of them. Our main result achieves an $n^{1/2+o(1)}$-pass semi-streaming algorithm for each of these problems. As a corollary, we get algorithms with the same pass and space usage for a broad class of DAG problems that admit a certain form of dynamic program over a topological ordering. This class includes weighted single-source shortest paths, longest paths, max-outdegree+1 coloring, and constructing a lexicographically-first DFS (depth-first search) forest. Our algorithm for the last problem can be seen as a generalization of our results on topological sorting and acyclicity testing: recall that standard textbook algorithms for these problems use DFS as a subroutine. Our algorithms are optimal up to an $n^{o(1)}$ factor in passes under the reasonable conjecture that $s,t$-reachability requires $Ω(\sqrt{n})$ semi-streaming passes. However, using the fact that our algorithms can be parameterized by the number of passes taken by topological sorting or single-source reachability algorithms, we prove stronger lower bounds for some of the problems even under weaker conjectures.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.34599

An Agentic AI Workflow for Liver Lesion Segmentation and Structured Radiology Reporting

Fatma Ahmed Mansour, Rahatara Ferdousi, Zyad Medhat Mahmoud Ashor, Manar Fathy Elshenawy, Ibrahim Shehaby, Salma Elmongi, S. Ahmed

原文摘要

Despite advances in automated liver lesion segmentation, a gap remains between image-derived predictions and clinically interpretable radiology reports. Bridging this gap requires quantitative measurements that are both reproducible and traceable. We present an evidence-grounded agentic AI framework that connects liver and lesion segmentation with deterministic quantification and structured reporting. TotalSegmentator-based nnU-Net models delineate the liver, Couinaud segments, and lesions, while computational tools extract volumes, dimensions, counts, and anatomical locations. A large language model (LLM) organizes these measurements into a predefined reporting schema, with numerical consistency checks against source measurements. On 51 LiTS cases, the segmentation stage achieved a liver Dice score of 0.947, lesion sensitivity of 75.6%, and positive predictive value of 68.9%. Exploratory screening of 25,494 MERLIN reports identified 10,208 (40.0%) with liver-related abnormalities. By connecting quantitative imaging evidence with agentic report generation, this work takes a step toward human-centered medical AI that prioritizes traceability and clinical relevance.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.15134

Training Agents to Fail Predictably: Fine-Tuning for Forecastable Tail Risk

Will Schwarzer, Scott Niekum

原文摘要

Estimating how often an ML model will fail at deployment scale is central to pre-deployment safety assessment, but a feasible evaluation set is rarely large enough to observe the failures that matter. Jones et al. (2025) address this by extrapolating from the largest k failure scores in an evaluation set to predict deployment-scale failure rates. We give a finite-k decomposition of this estimator's forecast error and show that it has a built-in bias toward over-prediction in the typical case, which is the safety-favorable direction. This bias is offset when the evaluation set misses a rare high-failure mode that the deployment set contains, leaving the forecast to under-predict at deployment scale. We propose a fine-tuning objective, the forecastability loss, that addresses this failure mode. In two proof-of-concept experiments, a language-model password game and an RL gridworld, fine-tuning substantially reduces held-out forecast error while preserving primary-task capability and achieving safety similar to that of supervised baselines.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03592

Evaluating Uncertainty Calibration in Probabilistic Time Series Foundation Models

Thomas Decker, Volker Tresp

原文摘要

Time series foundation models (TSFMs) are increasingly used for probabilistic forecasting across diverse domains, yet the reliability of their uncertainty estimates remains poorly understood. In this work, we study uncertainty calibration in probabilistic TSFMs from a broader methodological and empirical perspective. We introduce a taxonomy of how TSFMs represent predictive uncertainty and develop a fine-grained evaluation framework for calibration in multi-horizon forecasting that distinguishes pooled, horizon-wise, and stronger conditional notions of calibration. Using this framework, we conduct a comprehensive empirical evaluation of popular TSFMs across diverse datasets and show that current models exhibit distinct and systematic patterns of miscalibration that standard metrics often obscure. We further analyze common post-hoc recalibration methods and characterize which forms of calibration they can improve and which tend to persist. Our results provide practical guidance for evaluating and improving uncertainty calibration in TSFMs and highlight important limitations of current practice.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03590

A Scaling Theory of Multi-Epoch Pretraining: Late-Time Overfitting and Ensembling

Zhen Yang, Yidi Miao, Blake Bordelon

原文摘要

In the near future language model pretraining will become bound by total data rather than total compute. Such a regime requires revisiting scaling laws and scaling law theory. Motivated by prior works that have found utility in ensembling, we study how the number of training epochs and ensemble size jointly shape generalization when training data are fixed. In language-model experiments on FineWeb, logit averaging reduces late-training deterioration, delays optimal stopping, and can outperform wider or deeper single models at matched parameter-token budgets over a common training horizon. To analyze this interaction between data reuse and ensembling, we derive a dynamical mean-field theory (DMFT) for multi-epoch stochastic gradient descent in power-law random-feature ensembles, tracking error correlations across epochs and models. Ensembling reduces the prediction variance responsible for late-time growth in expected test error, changing the optimal stopping time. We use these stopping times to derive compute-allocation laws at fixed data and individual model sizes. Under this allocation, ensemble size grows with compute at least as fast as training time per member, while excess test loss above the limiting loss decreases as a power of compute.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03588

3D-BBDA: Backpropagation-Free Black-Box Domain Adaptation for Robust 3D Point Cloud Recognition

Shivangi Rai, Kunal Jangid, Vaibhav Kumar, Vinod K Kurmi

原文摘要

Robust 3D point-cloud recognition is critical for robotics, mapping, and urban sensing, yet point-cloud classifiers often suffer performance drops under domain shifts caused by sensor changes, environmental variation, and acquisition artifacts. Many existing adaptation methods are difficult to deploy in practice because they require access to source data or the internal parameters of the source model, which may be restricted by privacy, licensing, or security constraints. We present 3D-BBDA, a backpropagation-free black-box domain adaptation framework that adapts a source-trained predictor to unlabeled target data using only black-box outputs. Our method performs pseudo-label guided prototype-based alignment and employs a weighted prediction module to fuse source logits with alignment logits, reducing sensitivity to noisy pseudo-labels. To stabilize prototype memory when pseudo-label coverage is incomplete, we construct a Gaussian-perturbed prototype prior from unlabeled target predictions and use it as a fallback for missing or unreliable class prototypes during alignment. Experiments on four corrupted 3D benchmarks demonstrate consistent improvements over strong baselines. On ModelNet-40C, 3D-BBDA achieves mean errors of 32.08% (PointNet) and 29.62% (GDANet), outperforming Source-only (35.88% / 34.03%) and BFTT3D (33.78% / 32.36%). 3D-BBDA requires only a single forward pass with no gradient updates making it suitable for real-time, privacy-preserving deployment in transferable 3D recognition pipelines. Project page is available at https://visdomlab.github.io/3D_BBDA

cs.CV · cs.CE · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03774

What Malware Actually Does: An Empirical Analysis of Post-Infection Behavior Across Malware Families

Emmanuela Andam, Emanuel S. Grant, Naima Kaabouch

原文摘要

Most malware detection research focuses on identifying whether a file is malicious before it executes. Far less attention goes to what happens after infection. This paper presents an empirical analysis of post-infection malware behavior across 37 families, grounded in dynamic sandbox execution using CAPEv2. Behavioral traces are modeled as heterogeneous graphs with five node types and seven typed edge relationships, preserving relational structure that flat feature vectors discard. A voting ensemble trained on graph-derived structural features achieves 94.44% accuracy and MCC of 0.863, outperforming a flat behavioral baseline by 7.4 percentage points in MCC. A multiclass classifier distinguishes 24 malware families, and a per-family behavioral fingerprint analysis characterizes post-infection activity across registry, network, process, and API dimensions. An LLM explanation layer generates analyst-readable reports with MITRE ATT&CK mappings grounded in observed behavioral evidence. The full pipeline is deployed as HeteroScan at https://ama-andam.github.io/heteroscan.

cs.CR · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗