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 08:31 — 2026-11-20 08:31(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 118 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:2611.24049

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:2611.22504

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:2611.21844

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: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

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:2611.18396

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

新论文 · v1arXiv:2611.18124

Muon Attains $\mathcal{O}(\varepsilon^{-3})$ Iteration Complexity under Shuffling

Kun Huang, Shi Pu, Karl Henrik Johansson

原文摘要

Muon is a stochastic first-order optimizer for matrix-valued parameters. It maintains an exponential moving average of stochastic gradients in a momentum buffer with coefficient $β$, and orthogonalizes the buffer to obtain the update direction. Muon has been reported to accelerate and stabilize the training of large language models. In practice, it is often used with shuffling (sampling without replacement), where each epoch visits the components of a finite-sum objective in a permuted order. However, its iteration complexity in this setting remains open. We analyze Muon under shuffling, with the momentum buffer orthogonalized by the polar map. For smooth nonconvex finite-sum problems, we establish an $\mathcal{O}(\varepsilon^{-3})$ iteration complexity for finding an $\varepsilon$-stationary point. This guarantee holds for every sequence of permutations, covering random reshuffling, shuffle once, and the incremental gradient method. This complexity matches that of stochastic gradient descent under shuffling in its dependence on $\varepsilon$, and improves on Muon's $\mathcal{O}(\varepsilon^{-4})$ complexity under sampling with replacement. Our guarantee requires a problem-dependent $β$ that approaches one as the number of components grows. In contrast, no fixed $β$ guarantees convergence to stationarity for every number of components. We show this by constructing a family of smooth convex problems on which, for any fixed $β\in[0,1)$, Muon remains bounded away from stationarity once the number of components is sufficiently large. This failure occurs for every sequence of permutations and persists even with small stepsizes. These results suggest two practical tuning rules: if the training loss stops decreasing even after reducing the stepsize, increase $β$; when increasing $β$, reduce the stepsize accordingly.

math.OC · cs.LG

版本更新 · v4arXiv:2610.23170

Chinese Decision: A Family of Language Models for Single-Pass Probabilistic Decision-Making

Qiang Yan, Jiafeng Guo

原文摘要

Many applications need either a probability distribution over a few decisions or a set of typed spans from a text, and both are usually obtained by generating text. We present Chinese Decision, a family of Chinese models that answers both with a single forward pass and no generated token: candidate-letter logits give probabilities for Boolean, categorical, and ordinal decisions, and a small span head reading an echoed copy of the input gives typed character spans. Both readouts share one backbone and one merged LoRA, so a unified model is one weight file. We release decision-only and unified models at 0.8B, 2B, and 4B (Qwen3.5), trained for one epoch on 13.05 million decisions and, for the unified models, on CJ-IE, a 1.2-million-row Chinese extraction mixture. On the full 307,900-decision CJ-Bench, the unified 4B model reaches 86.86% accuracy, above every reported baseline and the decision-only 4B model (85.97%), and extracts spans on CJ-IE with micro F1 of 68.9. Retention has a price: against a 0.8B model continued on CJ-IE alone, which reaches 73.9 F1 but forgets CJ-Bench (71.02%), keeping decision ability costs 5.0 to 10.7 F1 points, shrinking with size. Gains of the unified models over decision-only ones are small, and all comparisons rest on single training runs with paired clustered bootstrap intervals.

cs.CL

版本更新 · v2arXiv:2610.00890

Cross-Benchmark Transfer from RL on Agentic Coding Tasks

Sushant Mehta, Logan Ritchie, Edwin Chen

原文摘要

Coding agents often fail in the last mile: they build most of a feature but drop a requirement, test only the cases their implementation already handles, break behavior that was supposed to stay intact, or validate against an unchecked assumption. We ask whether reinforcement learning (RL) on expert-built agentic coding tasks closes this gap, and whether what the agent learns transfers beyond the training distribution. We post-train Kimi K2.7 Code, a 1T-parameter (32B active) open-weight mixture-of-experts model, with RL alone on 1,700 tasks: 1,000 repository tasks graded by hidden fail-to-pass tests and by pass-to-pass tests of existing behavior, and 700 terminal tasks graded by expert-written hidden verifiers. The reward is the fraction of target checks passed and drops to zero if any pass-to-pass test fails. One epoch of GSPO on a rank-32 LoRA adapter improves pass@1 on each of the six external benchmarks we evaluated, across three agent harnesses: SWE-Bench Pro (60.1 to 64.8), DeepSWE (31.0 to 43.4), Terminal-Bench 2.1 (67.4 to 82.0), Terminal-Bench 3 (1.4 to 12.1), Terminal-Bench 4 (0.0 to 7.6), and SWE-Marathon (5.0 to 25.0). Pooled over the five independent task sets (Terminal-Bench 4 revises Terminal-Bench 3), the improvement is significant (p < 0.001), and it remains significant on the three sets released after the training data was collected (p = 0.004); the model also improves under both harnesses never used in training. Median trajectories on DeepSWE and Terminal-Bench 3 are 24-35% shorter in agent steps. The base model's failed DeepSWE runs are mostly near-misses, and on the tasks the trained model newly solves, paired trajectories show it avoiding each of the four failure modes above.

cs.LG · cs.AI · cs.SE

版本更新 · v3arXiv:2605.11490

Adaptive Calibration in Non-Stationary Environments

Junyan Liu, Haipeng Luo, Lillian J. Ratliff

原文摘要

Making calibrated online predictions is a central challenge in modern AI systems. Much of the existing literature focuses on fully adversarial environments where outcomes may be arbitrary, leading to conservative algorithms that can perform suboptimally in more benign settings, such as when outcomes are nearly stationary. This gap raises a natural question: can we design online prediction algorithms whose calibration error automatically adapts to the degree of non-stationarity in the environment, smoothly interpolating between i.i.d. and adversarial regimes? We answer this question in the affirmative and develop a suite of algorithms that achieve adaptive calibration guarantees under multiple calibration measures. Specifically, with $T$ being the number of rounds, $W$ being the unknown number of i.i.d. segments of the environment, and $C\in[0,T]$ being another unknown non-stationary measure defined as the minimal $\ell_1$ deviation of the mean outcomes, our algorithms attain $\widetilde{\mathcal{O}}(\min\{\sqrt{T}+(TC)^{\frac{1}{3}}, \sqrt{WT}\})$ for $\ell_1$ calibration error and $\widetilde{\mathcal{O}}(\min\{(1+C)^{\frac{1}{3}}, W\})$ for both $\ell_2$ and pseudo KL calibration error. These bounds match the optimal rates in the stationary case ($C=0$ and $W=1$) and recover known guarantees in the fully adversarial regime ($C, W=Ω(T)$). Our approach builds on and extends prior work (Hu et al., 2026; Luo et al., 2025), introducing an epoch-based scheduling together with a novel non-uniform partition of the prediction space that allocates finer resolution near the underlying ground truth.

cs.LG · stat.ML

新论文 · v1arXiv:2611.17684

Representational Geometry as a Diagnostic for Adversarial Robustness

Brandon Ismalej, Alex Cloninger, Gal Mishne

原文摘要

Adversarial training is a common technique for making neural networks more robust to small, intentionally crafted input perturbations, and robustness is commonly measured through accuracy under attack. By exploring inter-network representations across different adversarial training objectives, we can analyze whether multiple networks organize their latent representations similarly. We study Multilayer Perceptrons trained on MNIST under three adversarial training regimes and compare the resulting population training dynamics and geometry to those of a vanilla network. We use M-PHATE to embed data samples across training epochs and examine how the geometry of the data changes during training under adversarial objectives. On penultimate-layer representations we measure displacement between clean and perturbed points, distributional distance through maximum mean discrepancy, and nearest-neighbor recovery. Our visualizations and quantitative analyses show that adversarial training leads to structural changes in how networks organize internal data representations, and robust accuracy and representational stability can rank the same defenses in opposite ways. These findings support a discussion of re-evaluating how practitioners approach the auditing of model robustness by treating latent representations and their training trajectories as diagnostic artifacts across sets of networks.

cs.LG · cs.CR

新论文 · v1arXiv:2611.17576

Beyond a Single Sign: BiTE for Branch-Preserving Binary Threshold Expansion

Siddharth Gupta, Mikail Yayla, Akash Kumar

原文摘要

Binary neural networks (BNNs) reduce model storage and replace many arithmetic operations with efficient bitwise computations, but the single-sign activation limits their representational capacity. Each preactivation direction is compared with one threshold and reduced to one of two values, discarding variation within each sign region. We propose \textbf{BiTE} (Branch-Preserving Binary Threshold Expansion), which evaluates each feature direction against $K$ ordered thresholds and retains the resulting binary responses as separate inputs to the following learned operator. BiTE can distinguish up to $K+1$ ordered activation states while allowing the following operator to learn a separate transformation for each threshold response. It also enables a controllable trade-off between the number of independently constructed feature directions and the number of ordered responses extracted from each direction. On BinaryViT, BiTE improves mean final-epoch Top-1 accuracy from $74.60\pm0.30\%$ to $75.83\pm0.15\%$ on CIFAR-10 and from $42.80\pm0.46\%$ to $44.07\pm0.32\%$ on CIFAR-100, with nearly unchanged trainable parameter counts. A matched uniform-collapse control reaches $75.33\pm0.15\%$ on CIFAR-10, supporting the value of retaining the threshold responses separately relative to the evaluated scalar collapse. Binary VGG-16 experiments further show a favorable observed parameter--accuracy trade-off, including a configuration that achieves $0.64$ percentage points higher mean accuracy with $21.8\%$ fewer parameters than conventional width scaling. Overall, these results support branch-preserving threshold expansion as an effective way to improve binary representations and the observed parameter--accuracy trade-off.

cs.LG

新论文 · v1arXiv:2611.16646

Measurement-Calibrated Synthetic Pretraining for Rapid Adaptation of UAV Channel Predictors

Qiuheng Zhou, Wei Jiang, Donglin Wang, Hans D. Schotten

原文摘要

Unmanned aerial vehicle (UAV) links can change faster than route-specific channel data can be collected, so a channel predictor must often be adapted from only a short target-flight calibration segment. This paper studies measurement-calibrated synthetic pretraining as an offline source prior for rapid adaptation of channel state information (CSI) predictors. The synthetic source is calibrated to flight-only power evolution, temporal shape variation, frequency selectivity, and phase disturbance, and is then combined with measured source-flight fine-tuning before target-flight adaptation. Under chronological held-out flight splits, synthetic-to-real (S2R) fine-tuning reduces the measured-data budget needed to reach useful prediction in the low-data regime. For 50 ms-ahead prediction, it crosses a latest-channel-estimate persistence baseline with 50 measured training windows, roughly 0.5 s of 10 ms-spaced supervised windows, whereas training from scratch requires 600 windows. A target-prefix adaptation study further shows that a lightweight gated recurrent unit predictor can reuse the pretrained source prior with one prediction-layer update epoch, positioning measurement-calibrated synthetic pretraining as a reusable prior for scarce target-flight measurements.

eess.SP · cs.LG