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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 06:41 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 08:18 — 2026-11-22 08:18(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:2026-11-22 06:41最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 8,992 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 06:39(北京时间)
版本更新 · v3arXiv:2606.23238

HOLogicBench: Evaluating Higher-Order Logical Reasoning in LLMs

Yucheng Wu, Jundong Xu, Mingzhen Ju, Yue Yu, Chenpeng Wang, Haoxuan Li, Liangming Pan

原文摘要

Existing LLM logical-reasoning benchmarks largely focus on object-level inference under fixed predicates and rules, leaving higher-order reasoning over rules and policies underexplored. We introduce HOLogicBench, a 1,379-instance benchmark that systematically evaluates five representative higher-order reasoning operations, with Isabelle/HOL formalizations and proof-verified answers. Beyond answer accuracy, HOLogicBench provides solver-verified reference reasoning paths for each instance, enabling fine-grained evaluation of model-generated reasoning against valid derivations. Across 16 model configurations, average accuracy is 53.86\%, with the best configuration reaching 65.99\%. Further analyses reveal that LLMs exhibit limited alignment with valid derivations, remain vulnerable to minimal counterfactual perturbations, and display distinct failure patterns across higher-order reasoning types.

cs.AI

版本更新 · v5arXiv:2603.21740

Prophet Inequalities with Delayed and Uncertain Acceptance

Emile Martinez, Felipe Garrido-Lucero, Umberto Grandi, Sebastian Pérez-Salazar

原文摘要

We introduce the *prophet inequality with delayed and uncertain acceptance* model, a variant of the classical prophet inequality in which a decision-maker sequentially evaluates options whose acceptance is uncertain and revealed only after a random delay. At each time step, the decision-maker observes the realized value of the arriving option and must irrevocably decide whether to select it or continue searching. Once an option is selected, the process is suspended for a delay drawn from a known distribution with expectation $d$, during which no other option can be considered. When the delay expires, the selection succeeds with a known probability. If it succeeds, the decision-maker receives the realized value and the process terminates; otherwise, the search resumes. In addition to the online decision-maker, we consider two stronger benchmarks: the value-aware decision-maker, who knows all value realizations in advance but not the acceptance outcomes, and the prophet, who knows both the values and the acceptance outcomes. We show that, in the worst case, both decision-makers achieve a $1/(d + 2)$ fraction of the prophet's value, while the decision-maker achieves half of the value-aware decision-maker's value. We then turn to the no-delay case, where we establish an equivalence between our model and the classical prophet inequality, and show that the value-aware decision-maker beats the $1/2$ barrier against the prophet whenever all acceptance probabilities are bounded away from $0$.

cs.GT

版本更新 · v5arXiv:2608.00794

Measurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation

William Caban

原文摘要

Agentic AI evaluation pipelines produce benchmark scores that justify deployment decisions, safety certifications, and regulatory compliance claims. No formal framework has characterized how validity degrades across these stages. We present a knowledge-based three-layer compounding validity model, $V_{\rm total} \leq V_1 \times V_2 \times V_3$, that captures multiplicative degradation across task generation ($V_1$), human-simulator calibration ($V_2$), and automated judgment ($V_3$). Applying it to five widely-used agentic benchmark configurations, we find $V_1$ and $V_2$ independently measurable and both degraded, but $V_3$ not currently quantifiable for any: three of the four benchmarks score with a single deterministic rule, so no second rater exists and reliability is undefined, and the fourth's partial LLM grader has no published grader-vs-human measurement. A structured survey of 55 published agentic evaluation papers finds that 26 of them report no chance-corrected inter-rater statistic of any kind, a determination four independent raters recover at Krippendorff's $α= 0.834$. On the broader judgment of whether a reported metric fits its rating design, approximately 80% of this purposive sample use structurally mismatched, incomplete, or absent inter-rater reliability (IRR) metrics (four-rater range 60.7%-84.4%). Both are consistent with systematic $V_3$ collapse. We further document $V_1$ failures (task validity flaws in 7 of 10 benchmarks) and $V_2$ miscalibration (up to 9 percentage points inter-simulator variance, with systematic demographic disparities for non-Standard American English speakers). We derive eight prescriptions grounded in psychometric science and domain-stratified reliability thresholds (intraclass correlation $\geq 0.70$; $α\geq 0.67/0.70/0.80$ by consequence level) that practitioners can apply immediately.

cs.AI

版本更新 · v3arXiv:2601.01638

Interaction Improvement

Adrienne Lancelot, Giulio Manzonetto, Guy McCusker, Gabriele Vanoni

原文摘要

The relational semantics of linear logic is a powerful framework for defining resource-aware models of the $λ$-calculus. However, its quantitative aspects are not reflected in the preorders and equational theories induced by these models. Indeed, they can be characterized in terms of (in)equalities between Böhm trees up to extensionality, which are qualitative in nature. We employ the recently introduced checkers calculus to define a quantitative contextual preorder on $λ$-terms, and demonstrate that it coincides with the preorder associated to the relational semantics.

cs.LO · cs.PL

版本更新 · v2arXiv:2601.06961

The Impact of Anisotropic Covariance Structure on the Training Dynamics and Generalization Error of Linear Networks

Taishi Watanabe, Ryo Karakida, Jun-nosuke Teramae

原文摘要

The success of deep neural networks largely depends on the statistical structure of the training data. While learning dynamics and generalization on isotropic data are well-established, the impact of pronounced anisotropy on these crucial aspects is not yet fully understood. We examine the impact of data anisotropy, represented by a spiked covariance structure, a canonical yet tractable model, on the learning dynamics and generalization error of a two-layer linear network in a linear regression setting. Our analysis reveals that the learning dynamics proceed in two distinct phases, governed initially by the input-output correlation and subsequently by other principal directions of the data structure. Furthermore, we derive an analytical expression for the generalization error, quantifying how the alignment of the spike structure of the data with the learning task improves performance. Our findings offer deep theoretical insights into how data anisotropy shapes the learning trajectory and final performance, providing a foundation for understanding complex interactions in more advanced network architectures.

stat.ML · cs.LG

版本更新 · v3arXiv:2607.22433

VIREL: Route-Local Lattice Residual Compression for Exact and Error-Bounded Floating-Point Time Series

Yue Zhang, Jiatao Lin, Haopeng Chen

原文摘要

Time-series databases store floating-point columns in independent pages that are written at ingest, rewritten at compaction, and decoded on every scan. Some columns must return the stored IEEE 754 word; others accept a pointwise bound $\varepsilon$. Codecs for both contracts turn each value into an integer on a lattice, but a real page mixes decimal resolutions. Keeping one scale per block charges every coarse step for the finest value: one scale-6 reading in a 1,024-value page cuts Falcon's compression ratio by 36%. We present VIREL, route-local lattice residual compression. A value enters a lattice only after the encoder has replayed the decoder's arithmetic on it. VIREL-Exact replays the decoder's division at each value's least decimal scale, which we prove always succeeds below $2^{51}$, gives every resolution its own lane and history, and places averages on a rational lattice; the same finer value costs it 0.6%. VIREL-EB replays a fused multiply-add on an error lattice, so every admitted value decodes within $\varepsilon$. One integer coder serves both contracts. On 14 canonical streams, VIREL-Exact emits 27.6% fewer bytes than Falcon. Fast beats ALP on ratio and both speeds at once: 7.01$\times$ against 4.19$\times$, 476 against 120 MB/s, and 5.0 against 4.5 GB/s on one core. Upper is the smallest output on all 48 larger streams. Ingest with Fast and compaction with Upper store those streams in Apache TsFile at 48.7% of ALP's bytes. VIREL-EB beats Machete on ratio and both speeds in all 90 dataset-bound cells.

cs.DB

版本更新 · v2arXiv:2606.29924

DCGrasp: Distance-aware Controllable Grasp Generation

Hiroyasu Akada, Jesús Pérez, Emre Aksan, Vasileios Choutas, Cristian Romero, Alberto Garcia-Garcia, Vladislav Golyanik, Christian Theobalt 等 9 位作者

原文摘要

Generating 3D hand-object interactions is essential for applications in robotics, AR/VR, and synthetic data generation, where flexible controllability and strong generalization to diverse object geometries are required. However, existing methods rarely satisfy these requirements, limiting their practical applicability. We present DCGrasp, a multi-modal diffusion framework for distance-aware controllable grasp generation. DCGrasp is built on a novel grasp energy term that computes Distance Profile, a signed distance from each hand vertex to the nearest object point, coupled with distance-aware weighting, effectively capturing the semantically similar hand-object interaction in near-contact regions while remaining invariant to object and hand identity. Given various controllable signals, DCGrasp first generates a Distance Profile based on a Diffusion Transformer, together with a corresponding candidate hand pose. We then refine the candidate pose through optimization, enforcing consistency between the optimized hand pose and the generated Distance Profile in near-contact regions. Our experiments show that DCGrasp produces high-quality, geometrically plausible grasps with flexible user control, generalizing to diverse object and hand shapes and scales. Our work establishes a robust and versatile pipeline for the synthesis of controllable 3D hand-object interactions. The supplementary video with dynamic visualization is available on our project page.

cs.CV

版本更新 · v3arXiv:2510.21978

Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models

Hoang Phan, Xianjun Yang, Yuanshun Yao, Jingyu Zhang, Shengjie Bi, Xiaocheng Tang, Madian Khabsa, Lijuan Liu 等 9 位作者

原文摘要

Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models. However, the RLVR recipe introduces a significant risk of capability regression, in which models forget foundational skills after prolonged training without employing regularization strategies. We empirically confirm this concern, observing that open-source reasoning models suffer performance degradation on core capabilities such as perception and faithfulness. While imposing regularization terms like KL divergence can help prevent deviation from the base model, these terms are computed on the current task and therefore do not guarantee preservation of broader knowledge. Meanwhile, commonly used experience replay across heterogeneous domains makes it nontrivial to decide how much training emphasis each objective should receive. To address this, we propose RECAP-a replay strategy with dynamic objective reweighting for general knowledge preservation. Our reweighting mechanism adapts online using short-horizon signals of convergence and instability, shifting the post-training focus away from saturated objectives and toward underperforming or volatile ones. Our method is end-to-end and readily applicable to existing RLVR pipelines without training additional models or heavy tuning. Extensive experiments on benchmarks using Qwen2.5-VL-3B and Qwen2.5-VL-7B demonstrate the effectiveness of our method, which not only preserves general capabilities but also improves reasoning by enabling more flexible trade-offs among in-task rewards.

cs.LG · cs.AI

版本更新 · v2arXiv:2509.25002

Circuit Distillation

Somin Wadhwa, Silvio Amir, Byron C. Wallace

原文摘要

Model distillation typically focuses on behavioral mimicry, where a student model is trained to replicate a teacher's output while treating its internal computations as a black box. In this work we propose an alternative approach: Distilling the underlying computational mechanisms implemented by a teacher model. Specifically, we propose circuit distillation, which introduces an objective to align internal representations between analogous circuit components in teacher and student models. We propose a method to match ``functionally correspondent'' circuit components and introduce a loss reflecting similarities between the representations that these induce. We evaluate circuit distillation on entity tracking and theory of mind (ToM) tasks using models from the Llama3 family. Our results demonstrate that circuit distillation outperforms standard distillation, successfully transferring algorithmic capabilities by adjusting only a small, targeted subset of student model parameters. This work establishes the feasibility of transferring mechanisms, which may in turn allow for efficient distillation of targeted teacher capabilities via interpretable and controllable internal student mechanisms.

cs.CL

版本更新 · v2arXiv:2412.12786

Forbidden Patterns in Mixed Linear Layouts

Deborah Haun, Laura Merker, Sergey Pupyrev

原文摘要

An ordered graph is a graph with a total order over its vertices. A linear layout of an ordered graph is a partition of the edges into sets of either non-crossing edges, called stacks, or non-nesting edges, called queues. The stack (queue) number of an ordered graph is the minimum number of required stacks (queues). Mixed linear layouts combine these layouts by allowing each set of edges to form either a stack or a queue. The minimum number of stacks plus queues is called the mixed page number. It is well known that ordered graphs with small stack number are characterized, up to a function, by the absence of large twists (that is, pairwise crossing edges). Similarly, ordered graphs with small queue number are characterized by the absence of large rainbows (that is, pairwise nesting edges). However, no such characterization via forbidden patterns is known for mixed linear layouts. We address this gap by introducing patterns similar to twists and rainbows, which we call thick patterns; such patterns allow a characterization, again up to a function, of mixed linear layouts of bounded-degree graphs. That is, we show that a family of ordered graphs with bounded maximum degree has bounded mixed page number if and only if the size of the largest thick pattern is bounded. In addition, we investigate an exact characterization of ordered graphs whose mixed page number equals a fixed integer $ k $ via a finite set of forbidden patterns. We show that for every $ k \ge 2 $, there is no such characterization, which supports the nature of our first result.

cs.DM · math.CO

版本更新 · v2arXiv:2608.06795

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes

Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo, Kaichen Yang

原文摘要

Low-rank adaptation (LoRA) enables efficient specialization and distribution of large language models through compact adapters. However, untrusted adapters introduce a supply-chain threat: a backdoored adapter can cause a model to generate harmful content, malicious code, political propaganda, or covert advertisements when an input contains a hidden trigger. Adapter-agnostic defenses merge the adapter with the base model, which dilutes backdoor signals and reduces detection performance. Existing adapter-aware methods do not address how to safely use a potentially backdoored adapter. Instead, they either train a defensive adapter to repair a backdoored base model, addressing the inverse problem rather than securing the adapter itself, or rely on a classifier that flags the entire adapter as suspicious and requires separate mitigation. These methods overlook the distinct latent-space signatures produced by trigger-bearing inputs in backdoored adapters. We introduce LoRAScan, the first adapter-aware defense that detects and rejects trigger-bearing inputs at inference time without modifying adapter parameters. Our key observation is that a small subset of LoRA insertion sites, approximately 5%, remains stable across clean inputs but exhibits highly concentrated spikes in LoRA down-projection activations when a trigger is present. LoRAScan identifies these low-variance insertion sites before model deployment and monitors them during inference. Across standard LLM backdoor benchmarks, LoRAScan rejects 98.49% of malicious inputs with a small error rate on clean inputs, outperforming existing defenses across diverse evaluation settings.

cs.CR · cs.AI · cs.CL

版本更新 · v2arXiv:2608.00283

On the Complexity of Computing Outputs of a Metric Turing Machine

Yaroslav Ivanashev

原文摘要

The classes MidP, MedP, and $\small{\overline{\text{MedP}}}$ contain functions that compute the median solution for certain types of problems. In this paper, for these classes we introduce analogous classes of functions that compute the k-th solution, where k is an order function that depends on the input. We prove that the classes MidP, MedP, and $\small{\overline{\text{MedP}}}$ are polynomial-time 1-Turing inter-reducible with the corresponding classes, where the order function is from FP or FP$^{\text{#P}}$. For MedP we also prove that it coincides with the corresponding classes, where the order function is from FP or #P. For several inclusions between function classes we give equivalent inclusions between language classes. In particular, we establish inclusion relations between MaxP and median classes MidP, MedP, and $\small{\overline{\text{MedP}}}$. We also prove that NPSV$_{\text{t}} \subseteq$ MaxP $\subseteq$ FP$^{\text{NP}}$ and both inclusions are proper if and only if NP $\neq$ coNP.

cs.CC

版本更新 · v3arXiv:2511.22693

Generative Anchored Fields: Endpoint Learning for Generative Modeling

Deressa Wodajo Deressa, Hannes Mareen, Peter Lambert, Glenn Van Wallendael

原文摘要

We present Generative Anchored Fields (GAF), a generative model that learns independent endpoint predictors, \(J\) (noise) and \(K\) (data), from any point on a linear bridge. Instead of learning the local path along a trajectory, as in diffusion or flow-based models, GAF is trained to identify the endpoint coordinates of a bridge state directly via an endpoint regression objective. Central to our approach is the decoupling of time-dependent feature learning from endpoint prediction. Unlike the transport-based models that learn a monolithic time-conditioned predictor that maps noise to data via a unified field, GAF uses a shared trunk, \(Φ\), which produces a time-conditioned feature bank and a pair of linear predictors, \(J\) and \(K\). This separation of feature learning from prediction enables \textit{Transport Algebra}: algebraic operations on multiple \(J\) and \(K\) heads for compositional sampling. Additionally, with class-specific \(K_n\) heads, where \(n\in\{1,...,N\}\) for \(N\) classes, GAF defines directed transport maps between a shared base noise distribution and multiple data domains, allowing controllable interpolation, multi-class composition, and semantic editing. This is achieved either directly on the predicted data coordinates (\(K\)) using (i) Iterative Endpoint Refinement (IER), a novel sampler that achieves high-quality generation in \(5-8\) forward steps, or (ii) on the derived velocity field \(v=K-J\). GAF achieves strong sample quality with an FID of 2.25 on ImageNet \(256\times256\) while treating compositional generation as an architectural primitive. Code available at https://github.com/IDLabMedia/GAF

cs.LG

版本更新 · v2arXiv:2605.12049

Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons

Aaron Spieler, Georg Martius, Anna Levina

原文摘要

Cortical neurons are complex, multi-timescale processors wired into recurrent circuits, shaped by long evolutionary pressure under stringent biological constraints. Mainstream machine learning, by contrast, predominantly builds models from extremely simple units, a default inherited from early neural-network theory. We treat this as a normative architectural question. How should one split a fixed parameter budget $P$ between the number of units $N$, per-unit effective complexity $k_e$, and per-unit connectivity $k_c$? What controls the optimal allocation? This calls for a model in which per-unit complexity can be tuned independently of width and connectivity. Accordingly, we introduce the ELM Network, whose recurrent layer is built from Expressive Leaky Memory (ELM) neurons, chosen to mirror functional components of cortical neurons. The architecture allows for individually adjusting $N$, $k_e$, and $k_c$ and trains stably across orders of magnitude in scale. We evaluate the model on two qualitatively different sequence benchmarks: the neuromorphic SHD-Adding task and Enwik8 character-level language modeling. Performance improves monotonically along each of the three axes individually. Under a fixed budget, a clear non-trivial optimum emerges in their tradeoff, and larger budgets favor both more numerous \emph{and} more complex neurons. A closed-form information-theoretic proxy captures these tradeoffs and attributes the diminishing returns at two ends to: per-neuron signal-to-noise saturation and across-neuron redundancy. A hyperparameter sweep spanning three orders of magnitude in trainable parameters traces a near-Pareto-frontier scaling law consistent with the proxy. This suggests that the simple-unit default in ML is not obviously optimal once this tradeoff surface is probed, and offers a normative lens on cortex's reliance on complex spatio-temporal integrators.

cs.LG · cs.AI · cs.IT · cs.NE

版本更新 · v2arXiv:2601.06640

Agentic AI Empowered Intent-Based Networking for 6G

Genze Jiang, Kezhi Wang, Xiaomin Chen, Yizhou Huang

原文摘要

The transition towards sixth-generation (6G) wireless networks necessitates autonomous orchestration mechanisms capable of translating high-level operational intents into executable network configurations. Existing approaches to Intent-Based Networking (IBN) rely upon either rule-based systems that struggle with linguistic variation or end-to-end neural models that lack interpretability and fail to enforce operational constraints. This paper presents a hierarchical multi-agent framework where Large Language Model (LLM) based agents autonomously decompose natural language intents, consult domain-specific specialists, and synthesise technically feasible network slice configurations through iterative reasoning-acting (ReAct) cycles. The proposed architecture employs an orchestrator agent coordinating two specialist agents, namely Radio Access Network (RAN) and Core Network agents, via ReAct-style reasoning, grounded in structured network state representations. Experimental evaluation across diverse benchmark scenarios demonstrates that the proposed system outperforms monolithic agents, rule-based systems, and direct LLM prompting, with architectural principles applicable to Open RAN (O-RAN) deployments. The results also demonstrate that whilst contemporary LLMs possess substantial general telecommunications knowledge, structured prompt engineering encoding domain-specific decision thresholds and operational policies is essential for reliable network automation performance.

cs.AI · cs.NI

版本更新 · v2arXiv:2605.22168

Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability

Joël Roman Ky, Salah Ghamizi, Maxime Cordy

原文摘要

Vision-Language Models (VLMs) map complex visual inputs to semantic spaces, but interpreting the cross-modal reasoning of VLMs currently relies on post-hoc explainers evaluated via unimodal perturbation metrics. We expose a limitation in this paradigm: because multimodal datasets contain language priors and modality biases, VLMs frequently exhibit cross-modal redundancy, allowing them to answer visual queries using text alone. Consequently, unimodal metrics penalize faithful explainers, triggering an evaluation collapse where visual and textual rankings fundamentally contradict each other. To resolve this, we introduce Synergistic Faithfulness ($\mathcal{F}_{syn}$), a scalable metric rooted in the Shapley Interaction Index that strictly isolates the joint Harsanyi dividend between modalities, serving as a highly accurate surrogate ($ρ= 0.93$) while achieving up to $88\times$ computational speedup. Evaluating 9 distinct XAI methods across 3 VLM architectures and 3 benchmark datasets, reveals that explainers proposed for VLMs heavily over-index on visual salience and significantly underperform adapted attention-based methods in capturing true cross-modal synergy. By decoupling visual plausibility from cross-modal faithfulness, this work provides a rigorous evaluation framework required to safely audit VLM reasoning in high-stakes deployments. Code: https://github.com/serval-uni-lu/xai-vlms-benchmark

cs.AI · cs.LG

版本更新 · v4arXiv:2407.03155

The Complexity of Data-Free Nfer

Sean Kauffman, Kim Guldstrand Larsen, Martin Zimmermann

原文摘要

Nfer is a Runtime Verification language for the analysis of event traces that applies rules to create hierarchies of time intervals. This work examines the complexity of the evaluation and satisfiability problems for the data-free fragment of nfer. The evaluation problem asks whether a given interval is generated by applying rules to a known input, while the satisfiability problem asks if an input exists that will generate a given interval. By excluding data from the language, we obtain polynomial-time algorithms for the evaluation problem and for satisfiability when only considering inclusive rules. Furthermore, we show decidability for the satisfiability problem for cycle-free specifications with a NExpTime lower bound and undecidability for satisfiability of full data-free nfer.

cs.LO

版本更新 · v2arXiv:2605.16893

NGM: A Plug-and-Play Training-Free Memory Module for LLMs

Yuwen Qu, Wenhui Dong, Camil Hamami, Ming Zhao, Chenyang Si, Caifeng Shan

原文摘要

Recent studies have introduced memory-augmented architectures that decouple knowledge storage from neural computation, enabling more direct access to stored representations. However, existing approaches often rely on learned memory embeddings or explicit memory and retrieval components, requiring additional training or increasing architectural complexity. To address these limitations, we propose N-gram Memory (NGM), a training-free, plug-and-play module that repurposes a backbone model's pretrained token embedding space as memory. NGM consists of a Causal N-Gram Encoder and a Cosine-Gated Memory Injector. The former constructs N-gram representations by directly aggregating pretrained token embeddings, while the latter uses cosine similarity with ReLU gating to adaptively control the amount of retrieved memory injected into contextual representations. Unlike conventional memory-augmented architectures, NGM requires neither additional embedding training nor a separately learned memory bank or external retrieval infrastructure. We evaluate NGM on ten benchmarks across six language-model backbones spanning two model families and multiple scales, including four Qwen3 models (0.6B, 1.7B, 4B, and 8B) and two Llama-3.2-Instruct models (1B and 3B). NGM consistently improves the ten-task average across all six backbones. Notably, it improves HumanEval by 4.26, HumanEval+ by 2.41, and GPQA-Diamond by 6.56 percentage points. Furthermore, NGM extends beyond text-only language models to vision-language models, with Qwen3-VL-2B achieving improvements across all five VLM benchmarks. Project page: https://pioneerqyw.github.io/ngm-project/

cs.AI

版本更新 · v2arXiv:2610.32822

On the Limits of Sparse Linear Model with Shuffled Differential Privacy

Yan Zhang, Jiong Tuo, Meng Ding, Yuheng Ma, Di Wang

原文摘要

Sparse linear regression is a fundamental problem in high-dimensional statistics, and its private counterparts leave a large gap between the central and the local model of differential privacy. Shuffled differential privacy (SDP) sits between the two, offering accuracy closer to the central model without the trust requirement of a central curator. This paper studies sparse linear regression under both non-interactive and interactive SDP protocols. In the non-interactive setting, any non-interactive $(ε,δ)$-SDP protocol is shown to incur an $\ell_2$-norm estimation error of $Ω( \frac{\sqrt{dk}}{nε} )$ with dimension $d$, sparsity $k$, and $n$ users, revealing an inherent dimensionality barrier. In addition, a non-interactive algorithm is proposed that achieves an $\ell_2$-norm upper bound of $\tilde{\mathcal{O}}( \sqrt{\frac{k}{n}} + \frac{d\sqrt{k}}{nε})$. To overcome this barrier, we turn to the interactive user-level setting, where each user holds $m$ samples. A two-round interactive algorithm is developed that first recovers the support through a heavy hitter step and then estimates the parameter, achieving an error of $\tilde{\mathcal{O}}( \sqrt{\frac{k}{nm}} + \frac{k}{n\sqrt{m}ε} )$ with no polynomial dependence on $d$. Furthermore, by extending the score attack framework to user-level data, a new lower bound $Ω( \sqrt{\frac{k\log(d/k)}{nm}} + \frac{k\log(d/k)}{n\sqrt{m}ε} )$ is established for any user-level $(ε,δ)$-DP, showing that the proposed algorithm is near-optimal with only a gap of the factor $\log(d/k)$.

cs.LG

版本更新 · v3arXiv:2610.03363

Geometry Meets Physics: Data-Efficient Pre-Training for Unstructured Neural PDE Solvers

Luis Medrano-Navarro, Giacomo Baldan, Qiang Liu, Benjamin Holzschuh, Jan Hagnberger, Mathias Niepert, Nils Thuerey

原文摘要

Neural surrogate models for Partial Differential Equations (PDEs) on unstructured 3D geometries are often limited by poor generalization and the high cost of generating large-scale training datasets. Consequently, pre-training on massive datasets of related PDE dynamics has emerged as a critical alternative to enhance the robustness and scalability of these models. However, this strategy is neither compute- nor data-efficient, as it relies on massive pre-computed data that is very costly to generate. In this work, we introduce a disk-data-free pre-training framework tailored to both steady-state and transient regimes. For steady-state problems, we propose a geometry-driven strategy that leverages intrinsic shape descriptors to learn representations of complex 3D domains. For transient problems, we introduce a physics-driven approach based on online generation of synthetic PDE data, enabling scalable pre-training without reliance on expensive datasets. Across multiple experiments, our approach achieves faster convergence, greater data efficiency, and higher accuracy during fine-tuning, particularly under realistic low-data regimes. This methodology provides a practical pathway toward data-efficient neural emulators for large-scale simulations. Code and models are available at https://github.com/tum-pbs/GMP.

cs.AI

版本更新 · v2arXiv:2610.22543HF 社区推荐

On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction

Eliezer Shlomi, Eliron Rahimi, Avi Mendelson, Chaim Baskin

原文摘要

Diffusion language models (DLMs) promise parallel text generation, but in practice face an unresolved speed-quality trade-off. Exact decoding fills in only one masked position per model pass, while faster multi-token decoding schemes are lossy. Speculative decoding is the standard lossless acceleration for autoregressive models. However, it does not transfer directly to DLMs, which must choose both what to generate and where. We show that this order is the missing piece: the model's own predictions from the previous pass already give the right token at over $90\%$ of positions, but not which position comes next. We introduce Speculating Positions Order Trajectory (SPOT), a 0.62M-parameter model that reads only the target's output distributions, predicts this order and proposes a tree of candidate continuations, which the target verifies in a single pass by state equality. Coupled-noise match, which shares Gumbel noise between drafter and target, keeps this verification exact at any temperature. This approach also inspired us to introduce SPOT-Sets for dynamic threshold decoding, where a pass commits several positions: SPOT-Sets drafts whole commit sets together with their tokens. Our comprehensive experiments show that SPOT cuts target passes by up to $6.8\times$ and reaches up to $3.4\times$ the throughput of standard decoding on SDAR-8B, matching or beating the calibrated and training-free drafting baselines in every task and budget at $T=0$ and $T=1$. In addition, we show that SPOT's learned drafter transfers across models, demonstrating successful transfer across six different DLMs; with a light calibration, the SPOT-Sets drafter transfers as well. On top of dynamic threshold decoding, SPOT-Sets improves the throughput of SDAR-8B by 59% on average over the threshold decoder alone. Project page: https://eliezer318.github.io/SPOT-dLLM/

cs.LG

版本更新 · v2arXiv:2603.28064CVF · CVPR 2026

\textit{4DSurf}: High-Fidelity Dynamic Scene Surface Reconstruction

Renjie Wu, Hongdong Li, Jose M. Alvarez, Miaomiao Liu

原文摘要

This paper addresses the problem of dynamic scene surface reconstruction using Gaussian Splatting (GS), aiming to recover temporally consistent geometry. While existing GS-based dynamic surface reconstruction methods can yield superior reconstruction, they are typically limited to either a single object or objects with only small deformations, struggling to maintain temporally consistent surface reconstruction of large deformations over time. We propose ``\textit{4DSurf}'', a novel and unified framework for generic dynamic surface reconstruction that does not require specifying the number or types of objects in the scene, can handle large surface deformations and temporal inconsistency in reconstruction. The key innovation of our framework is the introduction of Gaussian deformations induced Signed Distance Function Flow Regularization that constrains the motion of Gaussians to align with the evolving surface. To handle large deformations, we introduce an Overlapping Segment Partitioning strategy that divides the sequence into overlapping segments with small deformations and incrementally passes geometric information across segments through the shared overlapping timestep. Experiments on two challenging dynamic scene datasets, Hi4D and CMU Panoptic, demonstrate that our method outperforms state-of-the-art surface reconstruction methods by 49\% and 19\% in Chamfer distance, respectively, and achieves superior temporal consistency under sparse-view settings.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

版本更新 · v3arXiv:2511.22459

Gaussians on Fire: High-Frequency Reconstruction of Flames

Jakob Nazarenus, Dominik Michels, Wojtek Palubicki, Simin Kou, Fang-Lue Zhang, Sören Pirk, Reinhard Koch

原文摘要

We propose a method to reconstruct dynamic fire in 3D from a limited set of camera views with a Gaussian-based spatiotemporal representation. Capturing and reconstructing fire and its dynamics is highly challenging due to its volatile nature, transparent quality, and multitude of high-frequency features. Despite these challenges, we aim to reconstruct fire from only three views, which consequently requires solving for under-constrained geometry. We solve this by separating the static background from the dynamic fire region by combining dense multi-view stereo images with monocular depth priors. The fire is initialized as a 3D flow field, obtained by fusing per-view dense optical flow projections. To capture the high-frequency features of fire, each 3D Gaussian encodes a lifetime and linear velocity to match the dense optical flow. To ensure sub-frame temporal alignment across cameras, we employ a custom hardware synchronization pattern -- allowing us to reconstruct fire with affordable commodity hardware. Our quantitative and qualitative validations across numerous reconstruction experiments demonstrate robust performance for diverse and challenging real and simulated fire scenarios.

cs.CV

版本更新 · v2arXiv:2602.13444

FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation

Huajian Zeng, Lingyun Chen, Jiaqi Yang, Yuantai Zhang, Fan Shi, Peidong Liu, Xingxing Zuo

原文摘要

Recent vision-language-action (VLA) models can generate plausible end-effector motions, yet they often fail in long-horizon, contact-rich tasks because the underlying hand-object interaction (HOI) structure is not explicitly represented. An embodiment-agnostic interaction representation that captures this structure would make manipulation behaviors easier to validate and transfer across robots. We propose FlowHOI, a two-stage flow-matching framework that generates semantically grounded, temporally coherent HOI sequences, comprising hand poses, object poses, and hand-object contact states, conditioned on an egocentric observation, a language instruction, and a 3D Gaussian splatting (3DGS) scene reconstruction. We decouple geometry-centric grasping from semantics-centric manipulation, conditioning the latter on compact 3D scene tokens and employing a motion-text alignment loss to semantically ground the generated interactions in both the physical scene layout and the language instruction. To address the scarcity of high-fidelity HOI supervision, we introduce a reconstruction pipeline that recovers aligned hand-object trajectories and meshes from large-scale egocentric videos, yielding an HOI prior for robust generation. Across the GRAB and HOT3D benchmarks, FlowHOI achieves the highest action recognition accuracy and a 1.7$\times$ higher physics simulation success rate than the strongest diffusion-based baseline, while delivering a 40$\times$ inference speedup. We further demonstrate real-robot execution on four dexterous manipulation tasks, illustrating the feasibility of retargeting generated HOI representations to real-robot execution pipelines.

cs.RO · cs.AI · cs.CV

版本更新 · v3arXiv:2504.02321

On shallow feedforward neural networks with inputs from a topological space

Vugar Ismailov

原文摘要

We study feedforward neural networks with inputs from a topological space (TFNNs). We prove a universal approximation theorem for shallow TFNNs, which demonstrates their capacity to approximate any continuous function defined on this topological space. As an application, we obtain an approximative version of Kolmogorov's superposition theorem for compact metric spaces.

cs.LG · math.FA

版本更新 · v2arXiv:2605.18553

StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video

Huajian Zeng, Chaohua Yao, Yuantai Zhang, Jiaqi Yang, Rolandos Alexandros Potamias, Xingxing Zuo

原文摘要

Recovering world space 4D motion of two interacting hands from egocentric video is a fundamental capability for supervising robot policy learning, where wrist trajectories track the end-effector and finger articulations specify the grasp pose. Two major challenges arise in this setting: hands frequently leave the camera view for extended periods due to head motion, and persistent hand-object interactions cause severe occlusions of one or both hands. Existing methods uniformly condition on noisy hand motion observations without accounting for their per-frame reliability, leading to substantial performance degradation. Our key insight is that accurate world space hand motion estimation is tightly coupled with the quality of per-frame hand observations. To this end, we decompose the quality of hand motion observations extracted from an off-the-shelf hand pose estimator into four channels: wrist global translation and finger articulations for both hands. We propose StableHand, a quality-aware flow-matching framework conditioned on these four-channel quality signals, which are predicted by a learned quality network. We naturally incorporate the quality signals into the flow-matching process through a per-channel forward schedule, a quality-adjusted velocity target, AdaLN modulation of the DiT denoiser, and a quality-aware ODE initialization. This unified generative process preserves high-quality observations while reconstructing unreliable ones using a learned bimanual motion prior. Experiments on HOT3D and ARCTIC, two egocentric benchmarks featuring long missing-hand spans and persistent hand-object occlusions, show that StableHand achieves state-of-the-art performance across all reported metrics, reducing W-MPJPE by 20-25% compared to the strongest baseline, with the largest gains on heavily occluded ARCTIC sequences.

cs.CV · cs.AI

版本更新 · v2arXiv:2610.32229

Training an MoE LLM in MXFP4: How We Closed the Gap to BF16

Han Wang, Zhitao Wang, Natalia Frumkin, Xuanwu Yin, Alireza Khodamoradi, Dong Li, Emad Barsoum

原文摘要

Training large language models (LLMs) in sub-8-bit arithmetic promises substantial gains in memory bandwidth and compute throughput, yet FP4 formats introduce quantization error severe enough to destabilize optimization if left unaddressed. We present ALTO, an open-source training recipe for GPT-OSS-20B, a 20-billion-parameter mixture-of-experts (MoE) model, on the MLPerf Small MoE Training benchmark under the MXFP4 microscaling format. The recipe combines established techniques from Abecassis, Felix et al. [arXiv:2509.25149] (hybrid 1D/2D block quantization, randomized Hadamard transforms, and stochastic rounding) with a simplified weight de-oscillation scheme adapted from TetraJet-v2 [arXiv:2510.27527]. On C4 validation at global batch size 16, MXFP4 + RHT + SR + de-oscillation reaches a validation loss of 3.3350 at 16,128 steps, only 0.007 above the BF16 baseline (3.3283), closing roughly 50% of the gap left by MXFP4 without de-oscillation (3.3418). Measured by steps to reach the MLPerf quality target (validation loss 3.34), de-oscillation cuts the FP4 convergence overhead relative to BF16 from +20.0% to +5.0%. We also report negative end-to-end results from differential gradient estimation, outlier clipping, and macro-block scaling, despite each showing operator-level SNR gains. All experiments use simulated MXFP4 kernels on AMD MI300X hardware and wall-clock speed has not been optimized.

cs.AI

版本更新 · v2arXiv:2609.30383

Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems

Zihao Zhu, Siwei Lyu, Adel Bibi, Baoyuan Wu

原文摘要

A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load at runtime to extend its capabilities for a specific task. Skill-based agent systems therefore enable flexible reuse of third-party capabilities, but the openness of this skill ecosystem also opens up a new attack surface. Prior work has focused on vulnerabilities within individual skills, but little attention has been paid to risks that arise from interactions across skills. In this paper, we introduce skill cascading attacks, a threat paradigm in which a malicious objective is distributed across multiple skills so that each modification looks benign in isolation, yet their combined execution is harmful. For instance, in a prescription-review pipeline, the first skill weakens signals of recently discontinued medications in the extracted history, the second downgrades the severity of any drug interaction tied to them, and the third suppresses the resulting low-priority alert in the final summary, so that a severe drug-interaction warning silently disappears before reaching the physician. To systematically study this safety blind spot, we develop SkillCascade, an automated multi-agent red-teaming framework, and release SkillCascade-Bench, a benchmark of 213 validated cascading test cases across multiple agent systems and domains. Across representative agents (e.g., OpenClaw, Claude Code, Codex) and LLM backbones, cascaded interactions reliably induce harmful behaviors while evading existing per-skill scanners and runtime monitors. Our findings highlight a gap between component-level integrity and system-level safety, and call for defenses that reason over cross-skill interactions rather than individual skills in isolation.

cs.AI

版本更新 · v2arXiv:2610.31824

A Topology-Aware Quantum-Classical Framework for Multi-Target Active Debris Removal using Gaussian Boson Sampling

Komal Pandya, Saiyam Sakhuja, Nagaraj Kattaian

原文摘要

The continued growth of orbital debris threatens the safety and sustainability of near-Earth space, making Active Debris Removal (ADR) an important mitigation strategy. Selecting $k$ targets from $N$ candidates yields a combinatorial search space of size $\binom{N}{k}$, making joint target selection and mission sequencing computationally demanding. We present a topology-aware quantum-classical framework integrating orbital mechanics, weighted orbital-transfer graphs, Gaussian Boson Sampling (GBS), and multi-objective evolutionary optimization. Seven target-prioritization strategies represent physical consequence, orbital persistence, conjunction risk, network centrality, community structure, inferred source families, and random selection. GBS generates candidate target subsets from the weighted graph, which are then evaluated using PyGMO-based evolutionary optimization to identify servicing sequences that jointly minimize total velocity increment ($Δv$) and mission duration, accounting for modeled timing, propulsion, and mass feasibility. We evaluate the framework across three benchmark environments, SOCRATES Minefield, Collision Cloud, and Random, with candidate-pool sizes $N\in\{15,18,22,25\}$ and target cardinalities $k\in\{3,5\}$. The experiments characterize how benchmark topology, prioritization strategy, and problem scale relate to sampling behavior and downstream mission performance. By separating candidate-subset generation from detailed trajectory optimization, the framework offers a topology-aware approach to focusing computational effort on a limited set of candidate ADR missions.

cs.CE · cs.ET · quant-ph

版本更新 · v3arXiv:2503.19549

Unified Robust and Convergent Over-The-Air Federated Learning under Channel Noise and Heterogeneity

Zubair Shaban, Nazreen Shah, Ranjitha Prasad

原文摘要

Federated learning (FL) has emerged as a key enabler of distributed model training across ubiquitous wireless edge devices while preserving data privacy in next-generation wireless systems. One communication-efficient approach to realize this is leveraging Over-the-Air Federated Learning (OTA-FL), which exploits the superposition property of wireless multiple access channels (MAC) to perform low-latency model aggregation. However, practical OTA-FL deployments are significantly affected by the joint effects of channel noise at the server, fading, and both data and system heterogeneity across participating edge devices, which can degrade the model performance and thereby convergence. In this work, we propose the novel Robust and Convergent Federated Learning (RoCo-FL), a framework that jointly handles these challenges in federated wireless networks. RoCo-FL formulates local updates through inexact optimization, capturing the effects of wireless noise, partial participation, and heterogeneous system capabilities via structured inexactness conditions. These conditions naturally manifest as a proximal constraint at the edge devices that stabilizes local updates and mitigates the impact of channel impairments, data heterogeneity, and stragglers. We establish convergence guarantees for non-convex objectives under the proposed zeroth- and first-order inexactness models, providing theoretical insight into the interplay between channel impairments, data, and system heterogeneity. Experimentally, we validate RoCo-FL on real-world datasets, including CIFAR10, CIFAR100, and FEMNIST, demonstrating its robustness in noisy and heterogeneous environments. Compared to state-of-the-art baselines, RoCo-FL achieves significantly more stable convergence and higher accuracy, particularly in the presence of stragglers.

cs.LG · eess.SP