跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1111新增论文
+874其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 07:46 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 07:53 — 2026-11-20 07:53(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:2026-11-20 07:46最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 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。

27,982 已收录论文23,249 AI 相关8,559 有修订112 HF 社区发现

浏览论文库

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 140 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 07:44(北京时间)
新论文 · v1arXiv:2611.24782

Learning Trajectories Leave Decodable Traces in Neural Network Weight Space and Internal Representations

Patrick Krauss, Achim Schilling, Andreas Maier, Thomas Kinfe, Claus Metzner

原文摘要

Neural networks trained on the same task develop related weight-space structures, yet remain distinguishable after learning. Do these differences merely reflect alternative solutions, or do they preserve information about individual learning histories? We tested whether final weights reveal initialization, task order, and earlier trajectory states. Training reorganized the ensemble: initial pairwise distances did not consistently predict final distances. Nevertheless, all 30 trained networks were correctly matched to their initial weights among ten candidates per dataset. Networks sharing an initialization also developed recognizable final hidden representations across different batch schedules, although direct comparisons with initial activity did not recover identity. Learning order remained readable as well. A linear probe decoded the order of two earlier tasks with 100% accuracy on 80 held-out networks after ten epochs of a common final task. Earlier intermediate weight states were partly predictable, but individual initial weights could not be reliably reconstructed. Final weights thus retain selective historical information rather than a complete trajectory record. Perturbed networks recovered classification performance without returning to their unperturbed training paths. This separation persisted across datasets, intervention times, and network layers. Moreover, 2,157 of 2,160 aligned endpoint pairs showed no positive loss barrier at sampled interpolation points, indicating low-loss connections between distinct solutions rather than convergence to one weight vector. Together, these findings show that a shared task constrains networks to related successful solutions without erasing their individual histories. Final weights reflect not only what a network has learned, but also where learning began and how it unfolded.

cs.LG · cs.AI · q-bio.NC

新论文 · v1arXiv:2611.24451

EviScope: Evidence-Conditioned Sampling for Long-Range 3D Detection

Mingyang Lyu, Yinqian Sun, Gongce Cao, Chujie Tang, Yuhao Zhang, Lu Jia, Qian Zhang, Bo Wang 等 9 位作者

原文摘要

Query-based camera-radar detectors choose where and over which frames each object query samples from the query's position or feature. We test whether radar evidence around the query should also set these choices at the 150 m range of MAN TruckScenes, where recall differs across object-level radar-return counts within every range band. EviScope is a minimal test: the current frame's returns form a non-learned bird's-eye evidence field, which each query reads at its decoded centre to scale its radial sampling extent and to weight eight frames. It adds 5,450 parameters (0.009%) to RaCFormer, with no latency increase in our timing. Our module-free recipe exceeds the published TruckScenes mAP (25.9 over seven runs against 24.1), so we measure the module only against its own baseline at matched seeds. The evidence a query reads rises with its object's return count (Spearman 0.51) but captures zero-return objects only in part, and the learned radius tracks it ($ρ\approx-0.91$ in four runs). Over seven four-epoch pairs the module changes NDS by $+0.31\pm0.36$ and mAP by $-0.27\pm0.22$ (mean $\pm$ SE). Against a geometry-only conditioner with the same parameter count, trained at three matched seeds, it is higher by $+1.25\pm0.72$ NDS and $+0.87\pm0.21$ mAP, on mAP in every pair, and the control's mean NDS is near the baseline's. An exploratory far-range gain failed an internally pre-specified held-out test, and large inference-time substitution penalties also occur without query-local evidence: neither learned allocation nor inference-time dependence substitutes for matched end-to-end comparisons.

cs.CV

新论文 · v1arXiv:2611.24276

When Shuffling Fails: Token Recovery from Obfuscated KV Caches

Chengzhi Yi, Xiao Cheng, Wei Song, Haoyu Wang

原文摘要

LLM serving systems store, offload, and share KV caches, exposing token-level representations to infrastructure operators and co-tenants. Shuffled obfuscation combines secret linear transforms with fresh permutations, claiming security from b! possible shufflings. We show that input symmetry invalidates this counting argument: security depends on distinguishable outputs under chosen inputs. Repeated tokens produce identical first-layer Value rows, making every row permutation leave the data unchanged. Only auxiliary structures such as a single-row recovery marker vary, reducing the effective state space from b! to b. We construct Repeat-to-Reveal. The attacker collects the b distinguishable states from its own probes and exploits their rank-one differences to recover an equivalent denoiser without knowing the defender's secret parameters. A one-time calibration transfers across requests sharing the same secret epoch, enabling passive token-multiset recovery from subsequently observed cache blocks through public-model dictionary matching. We instantiate the attack on official KV-Cloak and evaluate 3,000 real WildChat user prompts across nine models and eleven configurations. The attack recovers the secret parameters with high accuracy and achieves 100 percent token-multiset recovery on GPU. Refreshing row-level secrets between epochs interrupts cross-request transfer, confirming secret reuse scope as the operative vulnerability. We further confirm orbit collapse on two other open-source defenses: the sequence-permutation implementation of Thomas et al. and PermLLM. The KV-Cloak developers invited a detailed report through their private vulnerability reporting channel.

cs.CR

新论文 · v1arXiv:2611.24049

A Hybrid RAG Framework for Deceptive Review Detection: Integrating RoBERTa-LoRA, FAISS-Based Retrieval, and LLM Reasoning

Andrei Kostin, José Ángel Diaz-Garcia, Karel Gutiérrez-Batista

原文摘要

The growth of deceptive online opinions poses a critical risk of misinformation and fraud. This paper proposes a Retrieval-Augmented Generation (RAG) system to automatically distinguish spam reviews. The architecture integrates RoBERTa with Low-Rank Adaptation (LoRA) classification, FAISS semantic vector retrieval, and a Large Language Model (LLM) for final reasoning. The system was evaluated across balanced and severely imbalanced real-world scenarios. Results demonstrate that five epochs of fine-tuning enable robust domain transfer, achieving an F1-score of 0.90 in cross-domain evaluation, outperforming baselines (OpenAI Detector,F1 = 0.82) and demonstrating competitive performance against specialized in-domain SOTA models (fakeRoBERTa,F1 = 0.97). The proposed architecture provides evidence-backed explainability and statistically significant precision gains while maintaining comparable overall detection performance.

cs.CL

版本更新 · v2arXiv:2411.02871

Survival of the Fittest Perturbations: Uncertainty-Aware Evolution of Adversarial Distributions for Robust Generalization

Junhao Dong, Zicheng Yu, Xinghua Qu, Z. Jane Wang, Yew-Soon Ong

原文摘要

Despite deep learning's broad successes across diverse scenarios, its vulnerability to adversarial examples impedes deployment, making adversarial training a leading approach to improve robustness. However, pointwise adversarial training maps each clean sample to a single adversary, overlooking surrounding adversarial variability and the associated shifts in feature statistics. To address these issues, we propose Evolutionary Uncertainty-Aware Distributional Adversarial Training (EvoUAD-AT). Specifically, we design an evolutionary adversarial uncertainty modeling module that maintains an instance-wise search distribution over adversarial feature statistics around an adversarially generated anchor. Candidates are evaluated under the current model, selected by their threat to a benign reference, and used to adapt the distribution; strategy parameters are retained across epochs. To avoid anchoring on misclassified clean samples, we refine the alignment reference and match benign and adversarial distributions. Introspective gradient matching further regularizes input gradients without external supervision. Our analysis characterizes the elite fitness surrogate and gives a conditional certificate for latent adversarial features. Extensive evaluations across multiple benchmarks demonstrate that our approach consistently outperforms existing state-of-the-art methods in both clean accuracy and robustness, with thorough analyses confirming the effectiveness of each proposed component.

cs.LG · cs.CV

版本更新 · v2arXiv:2611.22140

Synthetic Crystal Data Generation for Diffusion Pretraining in Material Property Prediction

Aamod Varma, Shuyi Jia, Victor Fung

原文摘要

Diffusion-based pretraining has emerged as a powerful strategy for learning transferable representations in graph neural networks for materials property prediction without requiring quantum-mechanical labels such as energies, forces, and stresses for every pretraining structure. However, the method retains a critical dependency: it requires structures residing near local minima of a potential energy surface, which have traditionally been obtained through costly DFT relaxations of known or physically synthesized compounds. This reliance constrains both the scale and the structural diversity of available pretraining data, leaving large regions of crystal structure space unexplored. In this work, we connect diffusion-based pretraining with synthetic structure generation to reduce this bottleneck. We introduce a synthetic data generation pipeline combining three complementary strategies: perturb-and-relax, generative sampling via MatterGen, and protostructure enumeration. Where structural relaxation is required, we use fast machine-learned interatomic potentials instead of performing a new DFT relaxation for each generated structure. We further compare a coordinate-denoising control with continuous-time variance-preserving (VP) and sub-VP diffusion objectives using a randomly initialized Orb-v2 backbone. The source comparison covers seven MatBench property-prediction tasks, and an eighth task, \texttt{mp\_gap}, is included in the protostructure scaling study. Every synthetic-pretraining condition numerically outperforms random initialization on all seven source-comparison tasks. Scaling the protostructure corpus from 20k to 165k under a fixed 400-epoch schedule numerically matches or exceeds MP-20k pretraining on most tasks; because this protocol increases both data diversity and optimization updates, the result reflects joint data-and-compute scaling.

cs.LG · cond-mat.mtrl-sci

版本更新 · v4arXiv:2609.31620

Rethinking the Reconstruction-Generation Gap in Representation Autoencoders

Hongyang Du, Yunfei Xie, Junjie Ye, Jiawei Yang, Xiaoyan Cong, Haodong Zhang, Yongchao Huang, Haiyu Wu 等 16 位作者

原文摘要

Fusing shallower encoder layers into a Representation Autoencoder (RAE) sharpens pixel reconstruction but degrades diffusion generation. Prior studies and the research community commonly attribute this trade-off to the latent content itself, assuming detail-rich features are harder to model. We show that this gap stems from geometric mismatch at the encoder-decoder interface. Freezing a foundation encoder preserves rich visual information, but imposes an encoder-native Euclidean metric shaped without pixel decoding, whereas the decoder amplifies sampling errors sharply along sensitive directions. At fixed information, reducing pixel error admits two dual geometric interventions: regularizing the decoder to flatten its sensitivity to latent variations, and aligning diffusion coordinates with the frozen decoder's metric at identical clean reconstruction. On ImageNet-256, aligning diffusion coordinates largely closes the guided generation penalty of multi-layer fusion and reaches state-of-the-art 0.984 gFID and 2.14 FDr6 in 80 epochs. RAEs should take information from the encoder and geometry from the decoder.

cs.CV

新论文 · v1arXiv:2611.23746

ZERITH V2.5: From Predictive Power to Policy Learnability

Chenxi Han, Ruby, Epoch, Orion, Luke, Bin, Dusk, Lyra 等 21 位作者

原文摘要

When humans learn to manipulate an unfamiliar object, they may already be able to anticipate how its state will change while still being unable to control it skillfully. This gap between prediction and control motivates us to study how the priors acquired by video generation models can be used effectively by an action policy. We present ZERITH V2.5, a video-action model (VAM) in which the action policy reads intermediate features of a video generation model, and use it to study, under fixed demonstrations and a fixed total number of updates, what kind of predictive training improves subsequent action learning. We find that the way video predictive training is supervised affects subsequent action learning. In our experiments, adapting at many noise levels yields a large gain, while adapting only at the noise level used at deployment yields none. Weight-transfer experiments further show that the gain stays with the adapted weights when they remain in the video generation model and disappears when they are used only to initialize the action policy. Initial loss and gradient measurements at the start of joint training indicate that target-domain predictive training gives the video model a better starting state, making subsequent joint learning of prediction and action easier. Under matched data and training budgets, predictive adaptation improves control. We evaluate the complete policy on LIBERO, LIBERO-Plus, Meta-World MT50, and real-robot tasks.

cs.RO

版本更新 · v2arXiv:2608.25903

MetaSieve: Faster Relational Deep Learning through SQL-Based Metapath Selection

Fahim Shahriar Khan, Ashraf Aboulnaga

原文摘要

Relational Deep Learning (RDL) is an effective approach to machine learning over multi-table relational databases. In RDL, a database is modeled as a graph in which each row is a node and each foreign-key relation is an edge, and a graph neural network (GNN) is trained on this graph. Training a GNN requires sampling a subgraph around every seed node in the training set, and the cost of training is largely determined by the size of these subgraphs. This paper aims to reduce subgraph size by leveraging the join and aggregation capabilities of relational database systems. We observe that sampled subgraphs are obtained by following metapaths composed of foreign-key links, and that many of these metapaths can be pruned without loss of accuracy. We present MetaSieve, a metapath selection layer that determines which metapaths to retain and which to prune. For each candidate metapath extension, MetaSieve computes statistics via SQL join and aggregation queries and evaluates the extension based on a novel scoring function that prefers lightweight but informative candidates. Metapaths whose scores fall below a threshold are deemed uninformative and pruned. Metapath selection in MetaSieve is lightweight since it relies only on database statistics and task labels, and it is independent of GNN parameters, so it integrates with diverse GNN architectures for classification and regression. Our evaluation on the RelBench benchmark with multiple GNN backbones shows that MetaSieve consistently reduces per-epoch training time by large margins while maintaining and often improving accuracy.

cs.DB · cs.LG

新论文 · v1arXiv:2611.23446

Where Global Context and Weight Sharing Work in Compact Vision Backbones

Michael Schroeder

原文摘要

Compact convolutional backbones such as EfficientNet achieve strong parameter efficiency through local depthwise separable convolutions, yet two structural questions remain central to hybrid design: where does global self-attention improve recognition over pure convolution, and can repeated blocks share weights without losing representational capacity? We investigate both questions on ImageNet-1k (50,000-image validation) using controlled EfficientNet-B0 experiments. First, we show that wrapping a classification backbone in multi-scale feature pyramids (BiFPN) fails to outperform a plain MBConv trunk (69.99% - 71.81% vs. 72.86% plain B0) until paired with stage attention (73.15%). In contrast, keeping the MBConv trunk intact and inserting lightweight zero-gated residual self-attention adapters at stages P3 (28x28 windowed), P4 (14x14 global), and P5 (7x7 global) reaches 74.02% standalone and outperforms a bit-for-bit matched plain-B0 control by +0.954 percentage points (73.88% vs. 72.92%) across an 88-epoch stateless replay schedule, with learned attention amplitude rising monotonically with semantic depth (27.2% at P3 -> 45.4% at P4 -> 66.3% at P5). Second, we evaluate recurrent weight sharing across repeated MBConv blocks with pass-specific BatchNorm statistics (+1,536 parameters per pass). While post-hoc kernel averaging degrades accuracy to 17.03% and single-template stage tying (-27.6% parameters) plateaus at 66.10%, alternating two shared block templates ([B1, A, B, A]) in Stage 6 cuts total model parameters by 10.9% (582K weights) and recovers by +10.82 points in a single epoch to 70.92% (-1.84 points vs. unshared control).

cs.CV · cs.AI · cs.LG

新论文 · v1arXiv:2611.22581

FAST: Functional Adaptive Sensing and Testing for Quickest Change Detection

Peiyao Liu, Jie Guo, Zhijun Wang, Xueru Zhang, Nan Chen

原文摘要

Quickest change detection (QCD) is studied for partially observed functional data streams. At each sampling epoch, a function is realized over a continuous domain, but its values can be observed at only a fixed number of locations. At an unknown change point, the functional mean undergoes a shift that is assumed to admit a sparse representation in a localized basis. We propose Functional Adaptive Sensing and Testing (FAST), which jointly estimates the unknown post-change parameter, selects sensing locations, and performs sequential detection. A minimax lower bound on the worst-case detection delay is derived under an average-run-length constraint. A non-asymptotic estimation-error bound is established for the policy-dependent observations induced by adaptive sensing. Under the stated regularity conditions, FAST is first-order asymptotically optimal when sensing subsets are optimized exactly. Simulations and a wildfire case study demonstrate the performance of the proposed procedure.

stat.ME · cs.IT

新论文 · v1arXiv:2611.22504

Efficient Self-Supervised Adaptation of 3D Abdominal Vision-Language Model for Institution-Specific HCC Classification via Full Fine-Tuning and PEFT

Febryan Putra Kartika, Cheng-Yu Ma, Ying-Jia Lin, Chi-Tung Cheng, Kuan-Fu Chen

原文摘要

Medical vision-language models (VLMs) capture cross-modal relationships between image and text, yet their adaptation to institution-specific clinical tasks remains underexplored. In this study, we fine-tuned a pretrained 3D medical VLM for hepatocellular carcinoma (HCC) classification using paired abdominal CT scans and radiology reports from a different institution with acquisition characteristics that differ from the model's original pretraining corpus. We compared two adaptation strategies: full fine-tuning and parameter-efficient fine-tuning (PEFT), motivated by the common use of PEFT to reduce computational cost and enable adaptation under limited-data constraints. Both approaches achieve strong downstream HCC classification performance despite the cross-institutional domain shift, with PEFT reaching an AUC of 0.79 and F1 of 0.70, and full fine-tuning achieving an AUC of 0.82 and F1 of 0.71. Although these results remain below the performance reported by supervised HCC classification approaches, our method achieves improvements over the pretrained model through CT-report contrastive learning without requiring lesion-level annotations or HCC classification labels as training targets. Full fine-tuning converges rapidly but overfits within a few epochs, whereas PEFT (ConvLoRA for the image encoder and LoRA for the text encoder) attains comparable performance while updating approximately 1% of the model parameters, although requiring more training steps. We also examine the role of contrastive temperature, observing that temperature initialization significantly affects classification performance. This study demonstrates that a 3D medical VLM can be efficiently adapted to institution-specific HCC classification using self-supervised CT-report contrastive learning, while highlighting the practical trade-offs between full fine-tuning and parameter-efficient fine-tuning.

cs.CV · cs.LG

版本更新 · v2arXiv:2510.26185

Cross-Epoch Bias in SGD-based Leave-One-Out Influence: Analysis and Accumulative Correction

Yunxiao Shi, Shuo Yang, Yixin Su, Rui Zhang, Min Xu

原文摘要

Training-data influence estimates support data selection and cleansing by predicting the effects of removing individual examples. The standard multi-epoch SGD-Influence Estimator (SGD-IE) aggregates contributions from a sample's repeated appearances along the recorded trajectory. When used to approximate finite deletion, it omits an interaction: later removals act on the parameter displacement accumulated from earlier removals. We introduce the Accumulative SGD-Influence Estimator (ACC-SGD-IE) to account for how earlier removals change the effect of removing the same sample again. It uses the sample's Hessian at subsequent appearances to correct the estimated parameter change. Our non-convex analysis shows that this correction removes SGD-IE's additional interaction contribution from the finite-horizon error bound: the omitted interaction produces a local error linear in the accumulated parameter change, while the remaining Taylor remainder is bounded quadratically under Lipschitz-Hessian assumptions. The bounds characterize how training propagates the remaining error. In non-convex experiments across clean and noisy tabular, text, and vision datasets, ACC-SGD-IE reduces validation-loss-change RMSE by 10.8% and improves Jaccard@10% by 15.2% on average relative to SGD-IE. These gains also translate into lower test misclassification rates after data cleansing on MNIST and CIFAR10 at the evaluated removal budgets. On noisy industrial datasets, it reduces aggregate parameter RMS error with a mean relative reduction of 53.4%. We further discuss computational tradeoffs, provide complementary theoretical analysis and experimental evaluation for strongly convex objectives, and explore potential extensions of the accumulative correction mechanism to other influence estimators.

cs.LG · cs.AI

新论文 · v1arXiv:2611.21883

Bajillion: Cryptographic Clearing for Micropayments

Patrick O'Grady, Guru-Vamsi Policharla

原文摘要

Much of the web is funded by advertising, a model that erodes as humans delegate browsing to AI agents acting on their behalf. A natural replacement is for agents to pay for what they consume, often a fraction of a cent per request. At the scale of web traffic, this could mean tens or even hundreds of millions of payments per second. We present Bajillion, a clearing protocol for scalable micropayments. A sender signs a payment request, and an untrusted operator answers with a preconfirmation, which promises the receiver that it will be paid. Periodically, the operator closes an epoch by posting only the net effect of its payments on chain. Bajillion guarantees that a malicious operator can only omit payments -- it can never debit a sender beyond what it signed, nor misdirect a transfer. Posted balances are therefore finalized immediately and can be withdrawn. By design, senders never have to raise disputes, making it suitable for ephemeral AI agents. A receiver that is shortchanged can prove that a close omitted a preconfirmed payment, which halts the protocol and lets every user exit with its finalized balance. Requests from different senders can be processed independently, allowing the operator to parallelize up to the number of senders. We capture these guarantees in an ideal functionality for accountable clearing and prove that Bajillion realizes it.

cs.CR

新论文 · v1arXiv:2611.21844

Bias-Reduced and Parallel Heavy-Tailed Stochastic Convex Optimization in $\ell_p$ Geometries

Zhengyun Nie, Anant Shyam, Brian Bullins

原文摘要

We consider the fundamental problem of parallel stochastic convex optimization (SCO), whose aim is to approximately minimize a convex objective when given the ability to query a moment-bounded stochastic gradient oracle multiple times in parallel per round. Whereas most previous results have focused on the variance-bounded Euclidean ($\ell_2$-norm) setting, meaning the objective is Lipschitz with respect to the $\ell_2$-norm over an $\ell_2$-bounded feasible set in $\mathbb{R}^d$, in this work we study parallel SCO in $\ell_p$ settings for $2 \le p < \infty$ under a heavy-tailed noise model. We begin by introducing a new class of $\ell_p$-optimal-distance-convergence (ODC$_p$) algorithms, drawing on prior stochastic bias-reduced techniques [ACJ+21], which combine with multilevel Monte Carlo methods to efficiently estimate the optimum of uniformly convex objectives. As a consequence of our ODC$_p$ algorithms, we first establish rates for projection-efficient $\ell_p$-Lipschitz optimization, composite convex minimization, and efficient $\ell_p$-proximal point estimation. Combining our ODC$_p$ algorithms with a new $\ell_p$-generalized Gaussian-based stochastic gradient estimator ($p$-GREG), we provide two efficient $\ell_p$ parallel algorithms, EpochDA and $\ell_p$-AC-SA, which achieve optimization error $ε> 0$ with at most $\tilde{O}(d^{\frac{p}{2p + 2}} ε^{-\frac{p}{p + 1}})$ query depth, improving upon the sequential heavy-tailed stochastic query depth of $O(ε^{-p})$ for $ε\leq \tilde{O}(d^{-1/(2p)})$. We also establish dimension-dependent lower bounds of $Ω\bigl(\min\{ε^{-p},d^{p/(3p-2)}\}\bigr)$ adaptive rounds for nonsmooth convex optimization over a subset of the unit $\ell_p$ ball. Our results improve upon the $Ω(\min\{ε^{-p},ε^{2/3}d^{1/3}\})$ bounds of [DG19], when adapted to the same feasible set.

math.OC · cs.LG · stat.ML

版本更新 · v3arXiv:2605.30556

Supervised Training Rapidly Degrades Early Visual Cortex Alignment Across Biologically Plausible Learning Rules

Nils Leutenegger

原文摘要

CORRECTION (August 2026): the central finding of this paper is not supported. An evaluation-mode defect left the batch-normalisation layers of the predictive-coding and STDP conditions in training mode during feature extraction, producing their apparent preservation of V1 alignment. With the defect repaired, predictive coding degrades V1 alignment more than backpropagation does, not less. The finding that training degrades V1 alignment for every rule tested does survive. [Revision note: not robust to the analysis choices examined in arXiv:2611.15533.] See the correction note on page 1; the original abstract below and the body are unchanged from v1. Corrected analysis: arXiv:2608.12408. Revision note: see Comments. Random, untrained neural networks consistently match or exceed trained networks in representational similarity to early visual cortex. This puzzling finding challenges the assumption that learning improves brain alignment. We investigate it by tracking representational similarity analysis (RSA) alignment to human fMRI data across training for four learning rules: backpropagation (BP), feedback alignment (FA), predictive coding (PC), and spike-timing-dependent plasticity (STDP). Using 720 object images from the THINGS database and fMRI data from three subjects across six visual ROIs, we measure Spearman correlations between model and brain representational dissimilarity matrices at eight training checkpoints (epochs 0-40). We find that (1) a single epoch of training reduces V1 alignment by 25-90%, depending on the learning rule; (2) backpropagation reduces V1 alignment most severely (delta r = -0.080), while predictive coding and STDP preserve substantially more (delta r ~ -0.04); and (3) a weaker, opposite tendency appears in object-selective cortex (LOC), where BP shows the largest increase in alignment during training, although the absolute change is small.

cs.LG · q-bio.NC

新论文 · v1arXiv:2611.21596

SADL: On the Demand-Supply Geometry of Representation Collapse

Junhan Sun, Yigui Feng, Mingzhe Liu, Haoyan Xu, Lei Ye, Ziqi Han, Hanru Bai, Yanzhao Zhang 等 10 位作者

原文摘要

In Joint-Embedding Predictive Architectures (JEPAs), a well-constrained projector output does not by itself prevent representation collapse. We find that, from initialization, the encoder representation is dominated by a component shared by different inputs. A batch-normalized projector removes this component, so regularization after the projector cannot correct it, and the differences between representations shrink until they collapse. We propose SADL (Supply And Demand Loss), which keeps the original training objective and constrains the encoder directly when needed. SADL compares the representation differences that the projector output demands with the differences the encoder can retain and pass on to the projector, and adds a constraint on the encoder only when supply falls short of demand. It works with different Demand Regularizers and introduces no auxiliary networks, additional trainable parameters, or architectural changes. In single-task and jointly trained four-task LeWorldModel (LeWM) and INTACT experiments, SADL lowers the collapse rate over ten random seeds from 50% to 0%. After one epoch of training, encoder effective rank is 3.4-6.4 times that of the corresponding baseline without SADL, and latent prediction error falls to 1/20-1/303 of it. Without additional tuning, SADL stays robust as its loss weight spans orders of magnitude, and with several Demand Regularizers INTACT exceeds 95% mean search-free control success. On four image datasets, SADL also consistently improves accuracy and stability across random seeds. These results show that matching the representation differences a regularizer demands with the differences the encoder can supply leads to faster and more stable representation learning in control and image classification.

cs.RO · cs.LG

新论文 · v1arXiv:2611.20493

A Temporal Convolutional Network with Multi-Head Attention Model: A Surrogate for Parallel DEVS Semiconductor Fab Simulation

Vamsi Krishna Pendyala, Hessam S. Sarjoughian, Edward J. Yellig, Bharadhwaj Balasubramaniam

原文摘要

Semiconductor factories process many kinds of wafers organized into lots of various sizes and configurations. Different kinds of machines, each with its own operations, process wafers for hours to days, and the wafers undergo many incremental fabrication steps (with re-entry) and flows spanning days to weeks across connected machines. Fast and accurate predictions of throughput ($TH$) and turnaround time ($TA$) dynamics for individual machines and their combinations are essential for factory operations. To use machine learning methods for this purpose, this paper presents a Temporal Convolutional Network with Multi-head Attention (TCNA) architecture. It uses simulated datasets from a benchmark Parallel DEVS (PDEVS) semiconductor fabrication factory model. The factory processes configurable wafer lots with uniform and sinusoidal wafer arrival profiles and may undergo preventive maintenance. The wafer lot size, arrival profile, and factory maintenance policy are used as static covariates. TCNA is applied to a selected set of simulated discrete-event throughput and turnaround time trajectories. The $TH$ and $TA$ time series predicted by TCNA, evaluated with the common $MAPE$, $MSE$, and $R^2$ measures, show comparable or higher accuracy relative to other model architectures, with similar parameter counts and epoch times; the TCNA model size and execution time are similar to those of other architectures such as the Temporal Fusion Transformer. Although time series predictions are less accurate than high-resolution simulations, they can be deployed at a much lower computational cost. The TCNA achieves orders-of-magnitude speedup over PDEVS simulation with an acceptable loss of accuracy, enabling frequent product scheduling, capacity planning, and maintenance planning.

cs.LG

新论文 · v1arXiv:2611.20404

Latent Feedback Is a Compute and Data Amplifier

Benhao Huang, Chaitanya Dwivedi, Xuezhe Ma, Alexander Moreno, Hector Liu

原文摘要

When high-quality data runs out, a common practice is to train on it for several epochs, but each repeat is worth less than the last. Latent feedback, which feeds each token's top-layer state into the next token's input, is another way to spend that compute, yet it has not been tested against a vanilla Transformer that spends the same compute on more epochs. We run this test across a ladder of model sizes, unique data and epochs, tuning both models at every size and amount of unique data. Latent feedback makes every FLOP and every token count for more except when unique data is scarce relative to model size, a regime that today's models are far from. We find that latent feedback serves as an amplifier: with unique data fixed, it reaches a Transformer's loss with less compute; with epochs fixed, it reaches that loss with less unique data. Furthermore, both savings grow with unique data per parameter and with repetition, and downstream tasks agree. To go beyond our grid, we fit one scaling law to both models, in which latent feedback enters as a Transformer with more parameters; it predicts that both savings keep growing with unique data and repetition. Fitted on models from 60M to 271M parameters, the law predicts the losses at a held-out 778M size to within 0.3% and the gap between the two models to within 0.05%. At most, latent feedback saves 48% of the compute and 47% of the unique data. When data, not compute, is the limit, latent feedback is the better use of a FLOP for a model of a given size.

cs.LG

版本更新 · v11arXiv:2606.11171

Bellman-sufficient Information Complexity

Yunbei Xu

原文摘要

We introduce Bellman-sufficient information complexity for minimax analysis of sequential decision problems. A Bellman-sufficient state retains the history needed for the controlled recursion; an index $Y=χ(Ω)$ specifies which information the bounds charge. A log-penalized Bellman program gives the upper bound, and a Bellman--Fano comparison with an algorithm-dependent reference trajectory gives the lower bound. When admissibility, calibration, and growth conditions hold and the bounds match at a common localization scale, they yield an information-risk sandwich. UCB bounds the immediate decision loss through calibration and optimism, while AMS/EBO gives a robust relaxation of the AIR Bellman program. Our main application gives a negative answer to a widely studied form of the GP--UCB minimax-optimality question. For every $0<α<1/4$, we construct a fixed bounded continuous kernel with minimax regret $Θ(T^{1-α})$ along an infinite sequence of horizons. At those horizons, two globally calibrated GP--UCB rules incur linear regret under one fixed truth. A policy that applies action-index AMS to a predetermined finite set in each epoch attains the minimax order; EBO gives a dual interpretation. Many low-value directions inflate the global exploration multiplier even though ignoring them is inexpensive. Through the canonical RKHS feature map, the same construction gives a finite-horizon polynomial minimax gap for the specified maximal-information-calibrated LinUCB rule. A numerical experiment illustrates the mechanism.

cs.LG · cond-mat.stat-mech · cs.IT · math.OC · math.ST

新论文 · v1arXiv:2611.20035

U-HamGNN: a universal model for magnetic Hamiltonians conditioned on spin and Hubbard U

Hongyu Yu, Yinze Hu, Yizhou Chen, Yang Cheng, Yingwei Chen, Xingao Gong, Yang Zhong, Hongjun Xiang

原文摘要

The electronic structure of a magnetic crystal depends jointly on its spin configuration and the on-site Hubbard correction U, requiring a separate DFT+U calculation for each combination. We introduce U-HamGNN, an equivariant network that takes these two inputs directly and predicts spin-resolved Hamiltonians across diverse crystal chemistries. A spectral-hybrid optimizer that weights each update direction by how consistently the gradient points along it reaches 8% lower Hamiltonian error than Muon and 26% lower than AdamW in a ten-epoch benchmark. The predicted bands reproduce U-dependent gap opening and altermagnetic spin splitting within the trained window and beyond it; exchange couplings and magnetic-order calls derived from the Hamiltonian agree with DFT+U on a calibration set. This universal model provides a new tool for magnetic research.

physics.comp-ph · cond-mat.mtrl-sci · cs.LG

新论文 · v1arXiv:2611.20025

acuSimNet: Multi-View Self-Occlusion-Awared Visibility Learning for Cranio-Cervical Acupuncture Points

Jiatao Ma, Qilei Sun

原文摘要

The localization of acupuncture points (acupoints) in Traditional Chinese Medicine (TCM) presents unique challenges since they are defined by abstract principles rather than distinct anatomical landmarks. Existing approaches are typically constrained to single view or rely on indirect calculations of relative positions with respect to other landmarks, thereby overlooking human anatomical variations. Furthermore, acupoint visibility assessment, which determins whether points are occluded by human itself, hair, clothing, or other objects, has received limited attention in practical applications. Acupoint localization itself does not require 3D reconstruction, but inferring their occlusion relationships with anatomical surfaces does, which adds computational cost and limits real-time inference. In this work, we introduce acuSimNet, an efficient hierarchical multi-task learning architecture for multi-view, self-occlusion-aware visibility prediction of acupoints, achieving 99.97% accuracy on the validation set. Our approach also addresses the challenges of high-dimensional classification (174 acupoints in cervicocranial region), negative convergence issues for visible acupoints, and inter-task scheduling optimization, resulting in substantially accelerated convergence. We improved the training efficiency from the exisiting methods of 3000 epochs to achieve 99% validation accuracy, to our optimized framework achieving 90% accuracy in 39 epochs and 99% accuracy in 86 epochs. This architecture overcomes the limitations of existing methods, could enable practical applications in acupoints detection and visualization, advancing the automation of TCM.

cs.CV · cs.AI

版本更新 · v2arXiv:2611.12807

Suppression Is Not Erasure: Mechanistic Analysis and Reactivation Boundaries of Subspace Projection for LoRA Backdoor Defense

Junsheng Fu, Shuangshuang Gao

原文摘要

Low-Rank Adaptation (LoRA) is widely used to customize large language models, but third-party adapters create supply-chain backdoor risks with under 1% modified parameters. Recent analytical null-space and subspace projection defenses report near-zero static Attack Success Rates (ASR), equating static silence with erasure. We audit subspace-projection defenses across four scales (Qwen2.5-0.5B/1.5B/3B/7B), three architectures (Qwen2.5, InternLM2.5-1.8B, Spark-X2.6-4B), and five trigger families (suffix, natural phrase, prefix/in-sentence, double-negation syntax, and composite triggers). Statically, module-wise rank-1 trigger-difference projection cuts ASR from 60.4% to 0.0% on standard suites and 70.3% to 0.0% on 1,000 uncontaminated prompts (p = 3.055e-299) in under 5 s. By Theorem 1 (11,880/11,880 module-sample pairs), low-rank bottleneck amplification aligns benign polite-suffix probes with u_1(B) (median cosine 0.8934-0.9705), reaching 0.0% ASR without trigger knowledge. However, static suppression is not erasure. Under 5-sample reactivation, single-round weight-editing baselines rebound to 91.7%-100.0% ASR in Epoch 1 (Fine-Pruning, ANP, NEEDLE, LoRA-Patch; 48.7% for single-round dual projection) and 100.0% by Epoch 2. Theorem 2 and Corollary 1 prove single-sided projection leaves non-zero gradients along u_1 across 168/168 modules (27.2x-31.1x above random expectation), while Haar orthogonal rotation shows Epoch-2 immunity depends on semantic alignment rather than Frobenius norm. Guided by Theorems 1-2, we propose Single-Shot Rank-k Dual-Subspace Erasure (DSE) and Benign Subspace Anchoring (DSE-BA), achieving 0.0% static ASR and 0.0% Epoch-1 reactivation across all five trigger families and Qwen2.5-0.5B/1.5B, while cutting Epoch-2 ASR to 25.0% (43.33% +/- 2.49% on 50 prompts x 3 seeds) and benign PPL to 6.54.

cs.CR

版本更新 · v2arXiv:2510.00524

Two stage GNSS outlier detection for factor graph optimization based GNSS-RTK/INS/odometer fusion

Baoshan Song, Penggao Yan, Xiao Xia, Yihan Zhong, Yuan Li, Weisong Wen, Li-Ta Hsu

原文摘要

GNSS pseudorange outliers severely disturb carrier-phase ambiguity resolution and positioning, particularly during signal blockages and recovery. Temporal Doppler consistency provides a reliable short-term range-change reference, but requires valid measurements at both endpoints and becomes unavailable upon signal re-acquisition. This paper presents a two-stage pseudorange screening framework that complements Doppler consistency with joint IMU-odometer motion prediction. The second stage compares predicted and measured temporal changes of double-differenced pseudoranges against an accepted anchor epoch without using current GNSS observations in the motion reference. A first-order error model separates anchor, relative-motion, and measurement uncertainties to propagate factor-graph covariance into the chi-square detection gate, and both stages adjust code weights through a closed-form minimum-inflation rule. Under continuous tracking, Doppler screening reduces RTK 3D RMSE by 96.18% and outperforms the a-contrario baseline by 58.56%. When Doppler checks are unavailable, joint IMU-odometer prediction detects a 10-m outlier change in 99.58% of trials after 30 s and 73.72% after 60 s, reducing RIO 3D RMSE by up to 78.51% after outages while RI screening outperforms an inertial-aided baseline by 70.42% in simulation and 39.11% in deep urban canyons.

cs.RO

版本更新 · v3arXiv:2610.00896

Seamless Reconfiguration for DAG-BFT (Technical Report)

Michael Yiqing Hu, Leander Jehl, Paul Franke-Bergmann, Jialin Li, Christian Berger

原文摘要

Byzantine Atomic Broadcast in Asynchronous networks has been studied extensively for decades. In a fully asynchronous system with even one possible crash failure, the FLP impossibility result rules out deterministic consensus, motivating randomized protocols that achieve termination with probability one. More recently, DAG-Rider popularized a new abstraction in which processes continuously reliably broadcast blocks to construct a Directed Acyclic Graph (DAG) and then locally derive a total order using a randomized perfect coin. This separation of dissemination from ordering has renewed interest in asynchronous DAG-based Byzantine Fault Tolerance (BFT) and inspired numerous protocols that improve expected latency or throughput. Reconfiguration, however, remains largely unexplored. Existing DAG-based BFT protocols generally assume a static set of processes, whereas deployed systems must occasionally add or remove nodes in response to operational demands. Existing solutions are not seamless; they either pause the system or delay membership changes until a predetermined epoch boundary. This may be impractical and can introduce downtime. A single agreed switching round is difficult to use seamlessly: by the time processes learn it, the dissemination layer may already have advanced beyond it. In this work, we present a seamless reconfiguration protocol for Asynchronous DAG-based Byzantine Atomic Broadcast. Our protocol allows the DAG to continue growing while the membership and corresponding quorum thresholds change, without halting the system. To the best of our knowledge, ours is the first protocol to provide seamless reconfiguration for DAG-based Byzantine atomic broadcast in a fully asynchronous network.

cs.DC

新论文 · v1arXiv:2611.19692

MathaMAGICal: Validating Trajectory Data Attribution During Capability Acquisition

Jason Lee, Dikshanta Pokhrel, Phonn Nay Khant, Victor Lee, Moritz Weckbecker, Sebastian Lapuschkin, Wojciech Samek, Mark Riedl 等 9 位作者

原文摘要

Influence-function-based methods like MAGIC provide exact first-order scores for trajectory data attribution, yet only retraining indicates whether those scores accurately predict data removal. We evaluate MAGIC on $86$M- and $152$M-parameter GPT-2-style models learning multistep arithmetic from scratch on filtered web text and four synthetic math families. Full-run attribution at $86$M suffers from numerical overflow, and even with metagradient clipping, scores correlate near chance with retraining (linear datamodeling score, LDS, $0.17$--$0.22$). In contrast, short checkpoint windows yield stable, accurate predictions at both scales (LDS $0.86$--$0.99$ across four $100$-step windows at $152$M), whereas a single-checkpoint gradient-dot baseline shows near-zero correlation. Rankings of individual training blocks predict retraining only within that single run and do not transfer across seeds or hyperparameters ($ρ\le 0.09$), whereas format-level patterns replicate across runs. Two data families, worked examples and primitive facts, occupy $2.1$--$2.6\times$ their corpus share in both the helpful and harmful $5\%$ score tails, reflecting strong bidirectional local sensitivity distinct from net benefit under multi-epoch family deletion. These results show that trajectory attribution is reliable within short, validated windows and yields family-level insights that generalize across runs.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.19551

TrustBound: Mechanized Completeness for Payment Epochs Initiated by AI Agents

Sandip Nandi, Aishwarya Bose, Apurba Bose, Soovadeep Bakshi

原文摘要

Payment operations requested by an AI agent may remain executable, or their outcomes unresolved, after the agent has stopped. We study when a trusted payment service can account for every payment in an epoch and exclude further payments under earlier authority. We give a Lean model in which operations are recorded before they receive execution authority and both actions are serialized with an admission fence. We prove that fencing fixes a journal that covers every modeled effect and outstanding right; that discharging those rights prevents further effects; and that truthful outcomes for the recorded identities then give exact accounting. A provider-contract model, mapped to the admission model, makes created payment objects inert until registered. Premise-removal mutations confirm that each key premise is needed. We connect the models to an executable service: six service histories are checked against the model in Lean, and bounded schedules, scripted clients and concurrent workers exercise its reconciliation. The concurrent experiments uncovered a conflict caused by reordered provider reads, which serializing retrieval with journal updates removes in all tested cases. The result separates two obligations that are easily conflated in practice - preventing future payments and accounting for past ones - and states precisely which service guarantees establish each.

cs.CR · cs.LO

新论文 · v1arXiv:2611.19264

Read Boundaries in Agent Memory: Consistency, Completeness, and Repair

Haoting Qiu, Qibai Chen

原文摘要

Agent-memory services assemble evidence through several reads across connections or stores. An update between those reads can pair an assertion with source content from another revision. We protect the complete recall, including enrichment and materialization, and evaluate the resulting evidence and service behavior in Hindsight and Cognee. A 600-run Cognee study compares unprotected recall, a repeated recall, a read/write lock, and optimistic epoch validation under default incremental updates and full rebuilds. At approximately 20 recalls/s, unprotected default updates yield 199 conflicting responses among 12,010 scheduled recalls with spaced writes and 284 among 12,010 with bursts. The lock and epoch validation each deliver complete, compatible evidence for all 24,020 default-update recalls. With default bursts, epoch validation reduces update p95 by 109 ms while adding 290 ms to recall p95 relative to the lock. A separate 160-run incremental-failure study distinguishes mixed revisions from complete new derived content whose canonical source record remains old. Both protected policies refuse service after failure; the first default retry restores all 80 fault runs through native full-rebuild fallback. In Hindsight, a shared PostgreSQL snapshot removes the mismatch in ten controlled pairs, with recall p95 rising from 19 ms to 29 ms. These results identify the read boundary needed for coherent evidence and the publication and recovery conditions governing service after an update fails.

cs.DB

新论文 · v1arXiv:2611.18396

Deep Neural Networks Training Efficiency: Does Grokking Modify its Dynamics?

Eduardo Cueto-Mendoza, John D. Kelleher

原文摘要

We study whether grokking, the delayed emergence of out-of-distribution generalization after apparent overfitting, alters training efficiency in deep neural networks, where efficiency is measured as accuracy per unit energy. Using two canonical settings, modular arithmetic and MNIST, we analyze two neural network models under 16-, 32-, and 64-bit precision and use Orthograd to test whether grokking produces noticeable deviations from the typically decreasing dynamics of training efficiency. We consider both short training runs of up to 500 epochs and long training runs of up to 20,000 epochs, and in both cases identify grokking as a sharp improvement in test accuracy after a sustained train-test gap. In the short-horizon experiments, applying Orthograd at progressively stronger levels during early training does not induce grokking, and efficiency remains smoothly decreasing. In the long-horizon experiments, Orthograd induces grokking, but the efficiency curves remain approximately monotonic and show no appreciable local increase at the grokking transition. These results suggest that, in our setting, grokking does not materially alter overall training-efficiency dynamics.

cs.LG

新论文 · v1arXiv:2611.18238

Small Is Not Dead: Distance-Aware Cluster Revival for e-means

Eyal Weiss

原文摘要

e-means (Bessa et al., 2026) is a recent mini-batch k-means algorithm, now part of the FAISS library, that reaches the error of Lloyd's algorithm about an order of magnitude faster on large embedding datasets. Every five mini-batches, it removes every cluster whose running point count falls below a tenth of the average and reuses its centre to split a large cluster. In the authors' ablation, removing this mechanism, called dead-cluster revival, raises the error more than removing any other component added to the moving-average update. The rule, however, considers only cluster size: it cannot distinguish a cluster that is small because it is redundant from one that covers a rare, isolated group of points, and on data with such groups it repeatedly removes centres whose removal is costly. We add a second condition, based on the distance between centres: a small cluster is removed only if its centre is close to another centre, relative to a running estimate of the mean squared error. When a centre equals the mean of its points, this squared distance is an upper bound on the average increase in squared error, per point of the cluster, caused by removing the centre. The condition costs one nearest-centre search for the small clusters every five mini-batches and adds no measurable running time. On the e-means paper's embedding benchmarks, it never prevents a removal, so the results are identical to those of FAISS. On datasets with small isolated groups not used during development, it reduces the test error after two epochs by roughly 10% to 80% relative to count-based revival, and it preserves the advantage of k-means++ initialization; on the other evaluation datasets, it stays within about 1% of the better of revival enabled and disabled. We also report two failure modes that the analysis predicts. This is a CPU proof of concept; GPU implementations are left to future work.

cs.LG · stat.ML