跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

+2新增论文
+2其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-12 21:36 · 全站最近入库：2026-11-12 06:37各信源进度 →

统计口径与数据新鲜度

统计 2026-11-11 22:12 — 2026-11-12 22:12（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：2026-11-12 21:36最近发现新增版本：2026-11-12 06:37库内论文最新更新时间：2026-11-11 08:00

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

21,675 已收录论文18,323 AI 相关6,056 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 12,277 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-12 21:30（北京时间）
版本更新 · v3arXiv:2512.05038

The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail

Cassandra Goldberg, Chaehyeon Kim, Adam Stein, Eric Wong

原文摘要

Concept vectors aim to enhance model interpretability by linking learned internal representations with human-understandable semantics, but their practical utility is often limited by noisy and inconsistent activations. In this work, we discover the SuperActivator Mechanism: a transformer dynamic that amplifies concept activation gaps, concentrating the most reliable concept evidence into a small set of highly activated tokens, which we call SuperActivators. We theoretically characterize this mechanism, proving that concept-aligned attention produces two competing effects: a tail amplification effect, where gaps among already-high activations grow disproportionately fast, and an equalization effect that eventually dominates as attention concentrates on extreme tokens. We validate the predicted tail amplification empirically, finding that in-concept activation distributions develop well-separated upper tails consistently across models, image and text modalities, and concept types. Moreover, we demonstrate the practical implications of SuperActivators for concept detection and localization. First, using only high-activation tokens as concept indicators improves detection by up to 14 F1 points over competing baselines. Second, restricting detection to the extreme activation tail is not merely sufficient but essential: including activations beyond the top 5-10% of the in-concept distribution introduces noise that degrades performance. Finally, using SuperActivators as instance-specific attribution targets yields more accurate and faithful concept localization heatmaps than using global concept vectors.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14312

PSL-RGHA: Parallel Split Learning with Reference Gradient Half-Space Alignment for Mitigating Gradient Divergence

Han Li, Zheng Lin, Miao Yang, Zehang Lin, Jing Yang, Zihan Fang, Qiyang Zhang, Zhaolu Kang 等 12 位作者

原文摘要

The escalating complexity of deep neural networks hinders the deployment of federated learning (FL) on resource-constrained devices, especially for multimedia applications such as on-device image classification and speech recognition. Parallel split learning (PSL) has emerged as a promising solution by offloading a substantial portion of the computational workload to the server through layer-wise model partitioning, making it particularly suitable for resource-limited visual and speech intelligence scenarios. However, the absence of client-side aggregation renders PSL sus ceptible to severe training divergence and potential convergence failure under heterogeneous data distributions. To address this challenge, we propose PSL-RGHA, a gradient-aligned PSL framework that employs reference gradient half-space alignment mechanism to mitigate training divergence among client devices. PSL-RGHA comprises two novel components: reference gradient progressive construction (RGPC) and gradient half-space alignment (GHA). Specifically, RGPC evaluates the directional consistency of client gradients and progressively synthesizes a robust reference gradient via Weiszfeld updates, effectively approximating the global descent direction. Then, GHA constrains client gradients within the reference half-space defined by RGPC to mitigate gradient conflicts and rectify local updates. Extensive experiments demonstrate that our PSL-RGHA framework outperforms existing baselines in various settings.

cs.LG · cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14311

Multimodal Abstention That Preserves Acquired Correct Answers

Jinyuan Zhang

原文摘要

Adding abstention to a task-adapted multimodal model can discard correct answers, including capabilities acquired during adaptation. We formulate abstention repair as maximizing correct abstention on unanswerable questions under a budget on newly lost correct answers. We propose ReFrain (Regression-Free Abstention), which combines a linear probe on first-token logits, threshold calibration on held-out image clusters, and a deterministic veto that replaces rejected outputs with the displayed "none of the above" option while preserving all other responses. "Regression-free" denotes zero loss on the calibration set at the zero-budget target. All abstention methods in our main comparison start from the same answering-SFT checkpoint; we separately track lost correct answers, repaired errors, and retained SFT gains. On Qwen2.5-VL-3B, ReFrain at zero budget retains all 57 SFT-gained answers with no losses and improves correct abstention by 7.30 percentage points. At a 0.5% calibration budget, it reaches 74.05% correct abstention with 8 losses and retains 55 gains; CLIP-UP EmbLoRA reaches 64.65% with 62 losses, 41 repairs, and 40 retained gains. The same probe at its default threshold loses 298 correct answers. With models and thresholds frozen, confirmation on 228 independent question clusters yields 66.05% correct abstention and no losses at the 0.5% point, exceeding EmbLoRA by 32.72 percentage points. Ordinary refusal SFT achieves higher correct abstention at greater regression cost. Code and reproduction materials: https://github.com/ModeLiberaL/ReFrain.

cs.AI · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14309

MMDM: Measuring Massive Multitask Decision Making

Junhao Shen, Qing Zong, Yue Guo, Zhanqiu Zhang, Yiwen Guo, Hong Cheng

原文摘要

System-1 Decision Models directly make structured probabilistic decisions over query-specified options given a state in a single forward pass, without autoregressively generating reasoning trajectories or textual responses. Recent evaluations cover diverse tasks but often rely on existing benchmarks, where prior exposure to test material can obscure generalization. Moreover, real-world decision making often involves long contexts, large option spaces, and complex logical dependencies, challenges that existing benchmarks do not adequately capture together. Thus, we introduce MMDM (Massive Multitask Decision Making), a benchmark of 5,448 high-quality questions across 16 task categories, combining newly constructed tasks with source-grounded recompositions and rewrites for single-select, multi-select, and soft-label decision making in fresh contexts. It covers realistic scenarios such as agent state tracking, tool and skill selection, preference judgments, and rubric scoring, with option spaces ranging from 2 to 1,024 and inputs extending to 64,817 tokens. With MMDM, we conduct a comprehensive quantitative evaluation of 28 decision models, showing that many perform well on common knowledge yet struggle with interdependent options, constrained decisions, and multi-select tasks. For example, Perplexity Decider-V1.2 reaches 78.75% Hard Single-select Accuracy on world knowledge, but only 53.95% on option logic and 47.95% on constraint planning, while the best Hard Multi-select Accuracy across all models is 36.81%. These results highlight joint reasoning, constraint-aware selection, and complete multi-select recovery as key priorities for decision model development, with MMDM providing a testbed for measuring this progress.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.05347

Whose Guardrail? User Identity Shapes the Effectiveness of Model Disclaimers in Mitigating LLM Political Persuasion

Jillian Fisher, Daniel W. Fisher, Jennifer Pan, Yulia Tsvetkov, Katharina Reinecke

原文摘要

Politically biased AI can shift users' opinions, yet it remains unclear whether model disclaimers protect against such persuasion. We report a preregistered experiment (N=1,586) examining how disclaimer design and user characteristics shape susceptibility to politically biased AI. We varied whether disclaimers identified political bias versus potential inaccuracies and whether they included an explanation. Participants completed two decision-making tasks with an LLM biased against their political views, with outcomes assessed immediately and one week later. Disclaimers identifying political bias and including an explanation reduced persuasion, but effects varied across contexts and did not persist. Individual differences were more consistent predictors: Republicans were more persuaded and reported higher trust than Democrats across tasks. Similarly, participants who used AI more frequently were also more persuaded, whereas those with greater self-reported AI knowledge were less persuaded. These findings suggest that generic disclaimers are not enough: effective safeguards must account for user heterogeneity and context.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.37914

Muon Makes the First Mixture-of-Experts Layer Harder to Balance

Marcos Hernanz

原文摘要

Many open mixture-of-experts (MoE) language models train with Muon instead of AdamW. Most balance the load with a bias on each expert's routing score, adjusted after every step. Their recipes disagree on whether Muon should also train the router. In models with 55M and 108M active parameters, we measure how the optimizer changes the span of these biases, the largest minus the smallest in a layer. The span grows when all tokens favor the same experts, so it shows how hard a layer is to balance. At learning rates tuned on shorter runs, Muon raised the span of the first MoE layer at every seed, roughly doubling it on average, while the other layers changed much less. The rise came from Muon on the rest of the network, whichever optimizer trained the router. In those runs, the inputs to the first router shared a direction, and soon after the warmup its busiest expert averaged four to seven times its fair share. Over the first 3,000 steps, subtracting the batch mean from these inputs removed this overload while barely changing the loss. On the smaller model, halving Muon's learning rate removed most of the rise and slightly improved the loss. Moving only the router to AdamW made the loads shift more during the warmup and slightly raised the loss, so at this scale the results favor keeping the router on Muon.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14285

LM-SimBench: A Unified Framework, Dataset, and Benchmark for Large Language Model Training Simulation

Yu Dong, Hong Li, Qiang Sun, Xu Zhou, Jinbiao Huo, Qixiu Cheng, Zhiyuan Liu

原文摘要

Evaluating candidate parallelization strategies through distributed training runs makes strategy selection prohibitively expensive at scale. Performance simulation offers a lower cost alternative, yet controlled comparisons among existing simulators remain difficult because they differ in the training stages they model and the workloads on which they are evaluated. We introduce LM-SimBench, a unified framework, profiling dataset, and benchmark for evaluating LLM training simulators. The framework decomposes simulation into functional stages from model compilation to schedule level aggregation, connecting execution representations and cost estimators to measurable evaluation targets. Following this framework, we profile 23 model settings from 10 dense and Mixture-of-Experts (MoE) LLM families on an Ascend Neural Processing Unit (NPU) cluster. The resulting dataset contains 348 feasible configurations that jointly vary five parallelism dimensions and activation recomputation, with six views spanning configuration, rank, operator, event, and kernel granularity. Evaluations of representative training simulators demonstrate how LM-SimBench supports comparisons of prediction accuracy, assessment of configuration selection, and diagnosis of prediction errors. Matched GPU-NPU experiments validate the cross-platform applicability of the collection and evaluation protocol and demonstrate NPU-guided GPU configuration selection.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14284

Ninety-Six Ways to Measure a Scribe: Fragmented Evaluation of Ambient Scribes in Healthcare

Amama Mahmood, Shiye Cao, Laura Fleig, Junan Jiang, Theodore Jensen, Yee-Yin Choong, Kristen Greene, Chien-Ming Huang

原文摘要

Ambient artificial intelligence (AI) scribes have moved rapidly from experimental pilots to enterprise-wide deployment across health systems, promising reduced documentation burden and improved clinician experience. While research evaluating these tools has expanded quickly, there are no agreed-upon protocols or standardized metrics for assessing their performance, making it difficult to compare findings or cumulatively synthesize evidence across studies. Across 54 recent evaluation studies, we identify ten evaluation dimensions and 40 distinct metrics, operationalized in 96 different ways-35 of them (36%) used by only a single study. Assessment is dominated by documentation efficiency and time, measured in 44 of 54 studies. The other dimensions appear at broadly similar rates (16-24 studies each), and safety and clinical outcome least consistently of all. Ripple effects on the broader care system, such as impact on patients' care outcomes, redistribution of work, changes in billing and coding intensity, and downstream use of notes by other clinicians are rarely assessed. Moreover, the metrics used rely heavily on self-report and are fragmented and inconsistently operationalized, which limits comparability and hinders synthesis across studies. As an effort to support more rigorous and cumulative evaluation, in this paper we review the study designs, data sources, and metrics commonly used to evaluate ambient AI scribes in healthcare settings, discuss the limitations of current evaluation practice, and argue for a more holistic approach grounded in a standardized, multi-dimensional set of metrics.

cs.HC · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14281

UniFlow-RS: Unified Generative Prediction for Heterogeneous Remote-Sensing Tasks

Jianlong He, Liang Liao, Jing Xiao, Chaofeng Chen, Gui-Song Xia

原文摘要

Remote-sensing foundation models increasingly unify representations across sensing modalities and downstream tasks, yet their prediction mechanisms remain largely task-specific. Separate decoders, prediction heads, and objectives leave prediction fragmented across tasks. This naturally raises a question: can heterogeneous remote-sensing tasks share the prediction process? UniFlow-RS answers this question with a single latent flow-matching predictor shared across tasks. This requires addressing two key challenges: unifying heterogeneous prediction spaces and harmonizing joint optimization across tasks. First, we cast heterogeneous task outputs into structured visual targets in a common latent space, allowing them to be modeled by the same pretrained flow predictor. Task-dependent conditioning further accommodates differences in input configurations. Second, we optimize all tasks with a common Flow Matching objective, eliminating task-specific prediction losses. To mitigate optimization mismatch across tasks and modalities, we introduce Task-Modality Adaptive Timestep Sampling (TMAS), which dynamically allocates training timesteps according to the online learning state of each task-modality group. Using a single shared model, UniFlow-RS handles six tasks and thirteen datasets, surpassing recent task-specific state-of-the-art methods on several benchmarks while remaining competitive on the others. Beyond these benchmarks, the same checkpoint demonstrates strong zero-shot transfer across unseen datasets, task settings, occlusion conditions, and near-infrared false-color imagery, without target-specific adaptation.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14279

AutoThreshold: Joint Confusion-Profile Learning for Adaptive Mask Binarization

Shaokai Wu, Xunchu Zhou, Pinzhi Wang, Bo Dong, Xiao Cui, Qi Kong, Yue Ding, Hongtao Lu

原文摘要

A single validation-tuned threshold can become brittle when dense-score distributions shift. We introduce AutoThreshold, a post-hoc policy that predicts the joint mass of positive and negative pixels over score bins. This target directly parameterizes threshold-indexed confusion counts, avoiding products of independently estimated prevalence and class-conditional rates. Softmax normalization and cumulative decoding yield coherent, monotone confusion profiles; a plug-in decoder then selects a threshold for any $F_β$ objective without retraining the head. Across three independently trained Kvasir pipelines transferred to four polyp datasets, Joint exceeds continuous Otsu by $0.0080 \pm 0.0046$ external macro Dice, with positive gains in 3/3 runs. On the reference pipeline, three head seeds achieve $0.6324 \pm 0.0027$, 0.0085 above Otsu; direct-utility Ridge achieves 0.6342, with the paired difference interval spanning zero. The same Joint checkpoints outperform Otsu for $F_{0.5}$, Dice, and $F_2$. On developmental KITTI Road leave-one-corruption-family-out evaluation, Joint improves over scalar regression by 0.0082 [0.0064, 0.0101], while direct utility is 0.0022 higher. These results establish joint confusion prediction as a useful, metric-retargetable inductive bias, without claiming Bayes-optimal $F_β$ decisions.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14272

Federated Learning for Cross-Regional Epidemic Forecasting with Asynchronous Outbreaks

Ruibin Liu, Francisco Fernandes, Xuanfeng Li, Zige Liu, André Salgado, Chitin Hon, Zifeng Yang, Arlindo Oliveira 等 9 位作者

原文摘要

Objective: Epidemic outbreaks are often asynchronous across regions, yet collaborative forecasting is hampered by privacy laws and heterogeneous public health interventions. We developed and evaluated, as a proof of concept, a federated learning (FL) framework for cross-regional COVID-19 forecasting under asynchronous outbreaks among Guangdong, Macau, and Portugal, while maintaining data sovereignty. Methods: Using daily case data from WHO and China CDC for the three regions, whose outbreaks were asynchronous and interventions heterogeneous, we trained Long Short-Term Memory networks via FL for short-term forecasting, benchmarked against localized and centralized training using Root Mean Square Error, Mean Absolute Error, and Symmetric Mean Absolute Percentage Error. All experiments used the Flower FL framework with consistent hyperparameters across sites. Publicly available, aggregated case-count data were used so that the centralized benchmark could be computed as a reference. Results: The dataset comprised 1,233 daily observations (411 days) of new confirmed COVID-19 cases from November 24, 2021, to January 8, 2023. The earlier Omicron wave in Portugal supplied transmission dynamics that improved forecasts in the later-onset regions of Macau and Guangdong. The FL model achieved a normalized Root Mean Square Error of 0.028, an 88.3% improvement over the local model (0.240) and comparable to the centralized model, with network overhead mainly determined by model size and aggregation rounds. Conclusion: FL achieved short-term forecasting accuracy close to centralized training while maintaining data residency, with acceptable overhead. Leveraging asynchronous outbreaks across regions may offer a practical path to privacy-preserving collaborative forecasting, though prospective validation is required.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v9arXiv:2502.18770

Reward Shaping to Mitigate Reward Hacking in RLHF

Jiayi Fu, Xuandong Zhao, Chengyuan Yao, Heng Wang, Qi Han, Yanghua Xiao, Yuxia Wang

原文摘要

Reinforcement learning from human feedback (RLHF) is widely used to align large language models with human preferences, but it remains vulnerable to \emph{reward hacking}, whereby a policy exploits flaws in the reward function at the expense of the intended behavior. Reward shaping can stabilize training and partially mitigate reward hacking, yet its design principles remain underexplored. Our systematic study of common shaping methods suggests that shaped rewards should be bounded and should rise rapidly before gradually saturating. We introduce \emph{Preference as Reward} (PAR), which applies a sigmoid to centered rewards to produce a signal that reflects the reward model's latent preferences. We show that PAR has a variance-reduction property that stabilizes training and substantially widens the window for effective early stopping. Using Proximal Policy Optimization (PPO) and Gemma2-2B, PAR consistently outperforms the other shaping methods evaluated and demonstrates high data efficiency and robustness. Comparisons with unshaped rewards across four base models and four reinforcement learning algorithms show that PAR is effective across models and particularly beneficial for actor--critic methods when value estimates become unstable. The code is available at https://github.com/PorUna-byte/PAR.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14267

Achieving Robust Channel Estimation Neural Networks on Doppler effects by Designed Training Data

Dianxin Luan, John Thompson

原文摘要

Channel estimation is crucial in wireless communication systems. Many existing works train and test their models using the same or similar channel. However, practical channels are infinitely diverse and time-variant while data-driven algorithms often degrade on new and previously unseen channels. This prohibits the practical implementation of neural networks for channel estimation, particularly in high speed scenarios characterized by rapidly channel profile changes and very high Doppler shifts. Online training can fine-tune models to adapt to new channels, but requires high computation resource and incurs significant latency for physical-layer devices. Moreover, online training cannot exhaustively cover all possible channels because there are infinitely many possible channels. Therefore, we investigate the ability of neural networks to generalize to wireless channels. This paper proposes design criteria to generate synthetic training data, which guaranty that the resulting networks perform robustly across wireless channels, especially for very high Doppler shifts and different Doppler spectra. It ensures that offline-trained neural networks require no prior information or online training to precisely estimate the new channels. To demonstrate general applicability, we use neural networks with different levels of complexity to show that the generalization achieved appears to be independent of architecture. From simulation results, neural networks achieve a certain performance across wireless channels with different unseen power delay profiles (PDP) and Doppler shifts.

eess.SP · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.10398

Measuring Tabular Data Formats Cold: A Replicated Cold-Cache Benchmark of Serialization, Scan, and Index Performance on Real Datasets

Asra Fathima, Kristoffer Roberts

原文摘要

Choosing a file format for tabular data is a routine engineering decision, yet published comparisons often time reads served from the operating-system page cache, use one session, or rely on a single synthetic dataset. This article benchmarks fifteen format and access-path configurations (CSV, JSON Lines, Pickle, Feather, Parquet, ORC, DuckDB, and SQLite, with several access paths) on two real public datasets, New York City taxi trips and United States airline on-time records, at 50,000 to 3 million rows. Every measurement uses an explicitly cold cache, randomized execution order, and three independent sessions (with restarts on the laptop), and is analyzed with bootstrap intervals and Holm-adjusted permutation tests. Parquet answered a filtered aggregation 2.6 to 11 times faster than CSV, while JSON Lines was 10 to 27 times slower. A secondary index made SQLite queries 2.6 to 4.8 times slower on randomly ordered data and helped only on data sorted by the filtered column, at low selectivity. A row filter inside the Parquet reader was significantly faster than a projected scan on flight data from one million rows and on both datasets at three million, and row-group skipping needs several row groups, which the default writer produced only at 3 million rows. A 4 GB Linux host ran out of memory on configurations that a 24 GB laptop completed and reversed some orderings, such as Pickle versus Parquet. Code, derived data, and raw timings are released.

cs.DB · cs.PF · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.00625

NICE: A Framework for Declarative and Machine-Checkable Vulnerability Reproduction

Minh-Luân Nguyen, Olivier Levillain, Julien Malka, Stefano Zacchiroli, Théo Zimmermann

原文摘要

Reproducing software vulnerabilities is fundamental to security researchers, open-source maintainers, and educators. Yet, vulnerabilities are often hard to reproduce, and even when they can be reproduced once, recreating a software environment where the vulnerability can be exploited becomes harder and harder over time. We present NICE, the NIx CvE reproduction framework, which uses declarative recipes to build and automatically validate vulnerable environments. In NICE, a reproduced CVE comprises one or more NixOS virtual machine configurations, a scripted exploitation scenario, and machine-checkable assertions that provide factual evidence of exploitation. This design facilitates sharing, validation, review, and long-term reproducibility. Building on NICE, we construct a public archive of 56 reproduced vulnerabilities spanning multiple CWE categories, attack vectors, and target types (user-space, system software, kernel, and graphical applications), combining manually authored recipes with recipes produced by an LLM-based automated pipeline and merged after human review. We evaluate the feasibility of the automated pipeline on 110 real-world CVEs, achieving fully automated reproduction in 54.5% of the cases, at an average cost of $0.73 per CVE. The evaluation demonstrates that NICE provides a practical target for LLM-assisted recipe generation, while also identifying where human refinement or additional automation remains necessary.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14257

Elastic-WAM: Adaptive Spatiotemporal Imagination for Efficient Robot Control

Haitian Li, Tianfu Li, Xuxi Zhao, Zizheng Liu, Yangcheng Yu, Yiwen Hou, Zeyu Xiao, Mutian Xu 等 11 位作者

原文摘要

World-Action Models improve robot control by predicting future visual dynamics, but iterative video denoising incurs substantial inference overhead. Recent approaches reduce this cost through partial future denoising, yet typically rely on fixed refinement budgets. Our empirical observations reveal that preferred refinement depths vary across tasks and states, while different future regions exhibit varying relevance to action generation. Motivated by these findings, we propose Elastic-WAM, which adaptively allocates world refinement computation across temporal denoising time and spatial future space. A unified spatiotemporal refinement demand field governs when to stop world refinement, how far to advance each denoising step, and which regions to refresh. We parameterize this field with a shared temporal basis and spatial amplitudes, and learn it through a three-stage action-grounded supervised procedure. At inference, the learned field guides recurrent sparse world refinement to improve task success while reducing inference overhead. Evaluations across diverse simulation benchmarks and real-world long-horizon manipulation demonstrate state-of-the-art control performance with reduced inference latency.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14246

SinkState: On-the-Fly SVD of Recurrent States for Efficient Hybrid LLM Serving

Haolin Jiang, Weihang Li, Zhongzhu Zhou, Jinwen Pan, Santosh Pandey, Hang Liu

原文摘要

Hybrid models combine softmax attention with linear attention, which compresses history into fixed-size recurrent states to balance model quality and inference efficiency. However, linear attention has not pushed this compression to its limit: we find that the queries, keys, and values of linear layers concentrate in a stable, low-dimensional subspace, a phenomenon we call the linear attention sink, so each state is effectively low-rank, with a rank that varies across states. Yet existing serving systems keep these redundant states dense, reading and rewriting them in full at every decoding step, so their memory traffic grows with the batch size and dominates the decoding cost. Thus SinkState stores each recurrent state in an adaptive low-rank form throughout inference with buffered updates and a local SVD restricted to the top subspace. SinkState further consolidates the remaining components asynchronously on the CPU. On four hybrid models with Mamba-2 and Gated DeltaNet (GDN) layers, from 4B to 120B parameters, SinkState reduces the peak memory of recurrent states by up to 2.6x (1.9x on average) and speeds up decoding by up to 1.58x (1.25x on average) over Mamba-SSM and FLA, while maintaining accuracy.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14239

On Federated Averaging with Partial Participation under a General Variance Condition

Ziming Wang, Kun Huang, Karl Henrik Johansson, Shi Pu

原文摘要

In this paper, we study the convergence of Federated Averaging (FedAvg) with partial participation under a general variance condition. In each communication round, the server samples $S$ of the $n$ clients uniformly at random without replacement. The stochastic gradients are assumed to satisfy the so-called ABC condition, which allows their variance to grow with the local objective gaps. For smooth nonconvex objectives, we establish a finite-time stationarity bound in terms of the heterogeneity measure $σ_f^\star:=f^\star-\frac{1}{n}\sum_{i=1}^n f_i^\star$ and the client sampling factor $I_S:=(n-S)/(n-1)$. Here, $f^\star$ and $f_i^\star$ denote the infima of the global average objective and client $i$'s local objective, respectively. The bound exhibits a linear speedup in the number of sampled clients $S$ and recovers the full-participation result when $S=n$. Under diminishing stepsizes, we further prove that the gradient norm converges to zero both in expectation and almost surely. Notably, compared with existing analyses of FedAvg with partial participation, our results require no additional data heterogeneity assumption such as bounded gradient dissimilarity (BGD), and the sampling-induced term in our bound is not amplified by the number of local updates at the leading order. The importance of removing the BGD assumption is illustrated by an example that is smooth and lower bounded but violates BGD, yet is covered by our analysis.

math.OC · cs.DC · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.13414

FUTON: Fourier Tensor Networks for Implicit Neural Representations

Pooya Ashtari, Pourya Behmandpoor, Nikos Deligiannis, Aleksandra Pizurica

原文摘要

Implicit neural representations (INRs) have emerged as powerful tools for encoding signals, yet dominant MLP-based designs often suffer from slow convergence, and how their accuracy depends on their size is known only empirically. We introduce FUTON (Fourier Tensor Network), which models signals as generalized Fourier series whose coefficients are parameterized by a low-rank tensor decomposition, read out by a linear or MLP head. FUTON combines complementary inductive biases: Fourier bases capture smoothness and periodicity, while the low-rank parameterization enforces low-dimensional spectral structure. Beyond universal approximation, we show that with a linear head, the best FUTON's error splits exactly into the truncation of the signal's series and the best low-rank error of its coefficients, which we bracket from the samples before training, with a FUTON that attains the upper bound. On image fitting, occupancy volumes, and novel view synthesis, against twelve INRs of matched size, FUTON achieves the best average quality, reaches the final quality of each task's strongest baseline 4-34x sooner than that baseline, infers fastest, and trains in the least memory.

eess.IV · cs.CV · cs.LG · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14221

Stagewise and interpretable emergence of inside-outside computation in Transformer-based language models

Jack T. Parley

原文摘要

Variability in syntactic structure and parsing ambiguity are fundamental aspects of natural language which modern LLMs have to learn to deal with proficiently. Previous "post-mortem" studies have shown that fully trained Transformers indeed approximate canonical parsing algorithms such as inside-outside, but little is established theoretically about how this is actually learned. Here, we make a first step towards addressing this by studying the learning dynamics in synthetic context-free grammars with variable parse tree topology. The stagewise learning curves are fully interpretable, in the sense that all of the loss stages a) can be computed analytically, and b) can be clearly associated to the representation of a hidden latent tree variable, which allows to lift ambiguity and utilize information from wider contexts. By probing representations, we visualize the emergence of inside-outside computation across depth and during training: while during early stages local (bigram/trigram) information is used and involves only a few initial layers, gradually the Transformer develops an encoder-decoder structure where the most abstract latent information is encoded in the middle, and the latter half of the network is used to progressively refine the final token prediction. This organization of computation is reminiscent of findings in real-world LLMs, and importantly applies here to a synthetic model which allows full analytical control of the data statistics, thus opening the door to theoretical progress.

cs.CL · cond-mat.dis-nn

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.27947

Edit in Sync: Unified End-to-End Audio-Visual Editing for Human-Centric Videos

Ziye Yuan, Minghong Cai, Xu He, Ruchang Yao, Xiao Fu, Kaixin Ding, Ming Zhang, Xiangyu Du 等 11 位作者

原文摘要

Human-centric audio-visual editing requires precise alignment of lip movements, gestures, and expressions with speech. Existing methods process inputs through independent video and audio pipelines, preventing cross-modal interaction between visual editing and audio dubbing. Many of these pipelines further rely on mask-based inpainting. As a result, they suffer from poor lip-audio synchronization, cumulative pipeline errors, and an inherent mask-size dilemma. We present AVE, the first unified end-to-end framework that jointly performs reference-guided person swapping, insertion, and deletion across both audio and video modalities without requiring spatial masks. To overcome data scarcity, we design a synthesis pipeline and introduce AVE-Dataset, the first audio-visual editing dataset to provide 100K pairs with appearance and voice references. By combining Synthetic-to-Real reconstruction with preliminary audio warm-up, our framework transcends synthetic pipeline limits and mitigates audio-video token imbalance. AVE outperforms modality-separate audio-visual editing pipelines in editing realism, temporal consistency, and audio-visual alignment.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14211

Verifiable Agentic Traffic Class: A Policed Quality-of-Service Mechanism for Agentic AI Traffic, Evaluated from Simulation to Real-Kernel Adversarial Testing

Naveen Babu Narayanan Nair, Sajay Kurup

原文摘要

Software agents built on large language models generate traffic unlike human web traffic, yet routers have no class for it and cannot verify a sender's claim to be an agent. This paper proposes the Verifiable Agentic Traffic Class (VATC), which combines a reserved Differentiated Services Code Point (DSCP) value declaring agent traffic, a router-side classifier that demotes flows contradicting the declaration to a class served after best-effort traffic, and a rate-limited priority queue. VATC was compared with static Differentiated Services (DiffServ), a dedicated class that trusts the marking, and fq_codel, a per-flow fair-queuing scheduler, in two simulators and on a real Linux kernel. VATC matched DiffServ under steady load. In a constructed burst it cut mean agent queuing delay by 98% relative to DiffServ in simulation (assuming an immediate verdict), at a 12% increase in human delay; most of the gain came from the separate class. Under a spoofed flood in the kernel, the rate limit held human latency 11 times below DiffServ's. Without verification, DiffServ and a tightly configured fq_codel gave legitimate agents lower latency than VATC; a live four-feature classifier then demoted all 20 bulk-shaped spoofers and gave agents 0.30 ms, but missed six spoofers that copied the agent pattern. With emulated network delay, a timing feature of the classifier stopped separating agent from human flows. In real agent harnesses on a congested link, router queueing took 13% to 63% of task time, depending on harness and assumed model latency. The traffic was synthetic or sandbox-scale.

cs.LG · cs.AI · cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14210

Tree-Ising: Repairing Language Models with Bit-Level Ising Edits

Hadi Salloum, Ammar Ali

原文摘要

Weight-space programming, introduced in recent MIT work by Takehi et al., enables a frontier LLM agent to read a network's weights and write a repair. Their GPT-6 Astra agent corrected the reasoning loops of Qwen3.5-0.8B without gradients, using 158 agent turns, 89.7 million tokens, and 50 forward-pass requests. Our method, Tree-Ising, casts this repair as a sparse discrete optimization problem over the model's own BF16 weights. Forward statistics define an objective that weakens a loop direction, strengthens a concluding direction, and preserves the layer's output on productive tokens. Within a state-tree representation, where lossless BF16 storage acts as a special case, the admissible edits are sign flips and exponent shifts that preserve all shared group exponents and mantissas. We decompose this objective exactly into independent QUBO (Ising) problems, one per output row, which we solve on a GPU using simulated annealing or quantum-inspired simulated bifurcation. On the agent's two layers, Tree-Ising achieves 54.6% on MATH-500, outperforming the agent's edit (51.7%) under the same evaluation protocol, while the base model scores 7.9% as reported. The simulated bifurcation solver yields a statistically indistinguishable repair at 55.1%. Both solvers outperform the agent edit across all five math benchmarks, with statistically significant improvements on MATH-500 and GSM8K after correcting for multiple comparisons. Our approach modifies 13% to 17% fewer weights and reduces BF16 bit flips by a factor of 2.2 to 2.3. It requires only four forward-pass requests and zero LLM tokens, with the annealing recipe costing about $0.90 in GPU time. On Qwen3.5-2B, with layers and dose selected using only the base model, the same recipe increases greedy GSM8K accuracy from 21.6% to 69.4%. As a proof of concept, we execute an eight-variable repair subproblem using QAOA on an IBM Heron processor.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33267

Scoped Semantic Invariance as a Foundation for LLM Reliability

Rosario Uceda-Sosa, Maria Chang, Karthikeyan Natesan Ramamurthy, Moninder Singh

原文摘要

LLMs often answer semantically equivalent queries inconsistently, even when the underlying facts are known. We formalize consistency as semantic invariance over equivalence classes of queries and show that invariance under arbitrary meaning-preserving transformations is undecidable in general. This motivates scoped semantic invariance, where model behavior is evaluated relative to bounded semantic domains. We operationalize this framework using knowledge graphs (KGs), which act as explicit semantic control structures defining local semantic constraints and grounding contexts. Across the MITRE D3FEND ontology and eight Wikidata- derived domains, we show that inconsistencies are structured rather than random, concentrating in localized hotspot subgraphs organized around recurring TREE, STAR, and CYCLE patterns that remain stable across models and domains. We further show that selective graph grounding improves correctness and cross-model consistency, while indiscriminate grounding introduces regressions. A layered grounding strategy achieves the strongest monotonicity profile, preserving correct knowledge while reducing inconsistency. Finally, we show that hotspot structures discovered from simple consistency probes transfer to more realistic compositional reasoning tasks.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2510.21615

Epipolar Geometry Improves Video Generation Models

Orest Kupyn, Théo Uscidda, Marta Tintore Gazulla, Fabian Manhardt, Federico Tombari, Christian Rupprecht

原文摘要

Video generation models have advanced significantly through the latent diffusion transformers trained with rectified flow techniques. Yet these models still struggle with geometric inconsistencies, unstable motion, and visual artifacts that break the illusion of realistic 3D scenes. 3D-consistent video generation could significantly impact numerous downstream applications in generation and reconstruction tasks. We explore how epipolar geometry constraints improve modern video diffusion models. Despite using massive training data, these models fail to capture fundamental geometric principles. We align diffusion models using pairwise epipolar geometry constraints via preference-based optimization, directly addressing unstable trajectories and geometric artifacts through mathematically principled geometric enforcement. Our approach efficiently enforces geometric principles without requiring end-to-end differentiability. Evaluation demonstrates that classical geometric constraints provide more reliable preference signals than the video-quality and geometry metrics based on foundational models. We construct preferences from static scenes with camera motion, where the epipolar metric is most reliable, while the aligned model generalizes to dynamic scenes. By bridging data-driven learning with classical computer vision, we reduce epipolar error by 31% and improve human-rated consistency from 54% to 72% without compromising visual quality.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14207

DailyWildfireCAN: A Dataset and Benchmark for Next-Day Wildfire Spread Prediction in Canada

Mahacine Ettahri, Hager Radi Abdelwahed, Toluwaleke Olutayo, Daniel Aloise, Gaétan Marceau Caron

原文摘要

Wildfires represent a critical ecological and socio-economic challenge in Canada, where vast boreal forests and a warming climate have amplified the frequency and severity of extreme fire seasons. Predicting next-day wildfire spread can support fire management, but requires capturing complex interactions among weather, fuels, and terrain. Deep learning has emerged as a promising approach to learning these relationships from heterogeneous environmental data, yet its development and evaluation depend on representative datasets. Existing deep learning research on wildfire spread relies predominantly on US-focused datasets, leaving Canadian fire environments underrepresented. To address this gap, we present DailyWildfireCAN, a multi-modal, multi-temporal dataset and benchmark for predicting next-day wildfire spread across Canada. The dataset tracks continuous fire progression over multi-day events at a high spatial and temporal resolution of 90-m and 24-hour, respectively. This resolution preserves fine-scale information relevant to fire-edge geometry, local fuel variations, and terrain effects, supporting research toward improved daily wildfire spread forecasting. DailyWildfireCAN covers 2,440 wildfire events across eight fire seasons 2017-2024 and integrates 33 features across diverse modalities, including topography, meteorology, land cover, vegetation and forest structure, human influence indices, and satellite imagery. We establish a comprehensive benchmark comparing mono-temporal and multi-temporal prediction models, accompanied by a multi-dimensional evaluation framework assessing robustness across wildfire characteristics, geographic regions, and temporal conditions, spatial prediction quality, and sensitivity to reference label variations.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.27932

Binary Quantized Neural Network Training Is W[1]-Hard Parameterized by Input and Output Dimensions

Tao Jiang, Minbo Gao, Shaowei Cai

原文摘要

When the weights and biases of a neural network range over a fixed finite alphabet, training the network to fit a data set exactly becomes a finite combinatorial problem, and parameterized complexity asks which structural quantities of an instance make this problem tractable. Ganian, Sommer, and Sorge (ICLR 2026) showed that training quantized networks is fixed-parameter tractable when parameterized jointly by the input dimension $α$, the output dimension $ω$, and the treewidth of the architecture, and they asked whether $α+ω$ alone suffices. We show that it does not: training binary quantized networks is W[1]-hard parameterized by $α+ω$, so it admits no algorithm with running time $f(α+ω)\cdot|I|^{O(1)}$ for any computable $f$ unless FPT = W[1]. Hardness holds already for exact fitting of $k+1$ examples whose inputs equal their targets and form a coordinatewise prefix chain, and also when all biases are fixed to zero. The proof rests on a one-flip routing equivalence. On such data, nonnegative binary weights force every neuron to switch on at most once, and a network fits the data exactly if and only if the architecture contains vertex-disjoint paths that link each changing input to the corresponding output. Every neuron therefore has one of only $k+1$ activation profiles, yet deciding whether these profiles can be realized simultaneously is as hard as disjoint-path routing. Small input and output dimensions thus limit what each neuron can do locally, but not how the architecture forces neurons to share resources globally.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.10595

Design and Evaluation of Secure Distributed Chaotic Image Encryption on ESP32-S3

Mohammed Almozaini, Fazal Noor, Sohail Alhazmi

原文摘要

The limited computational resources of Internet of Things (IoT) devices present challenges for secure image processing. This paper presents a distributed chaotic image encryption system using independent Wi-Fi-connected ESP32-S3 microcontrollers. A master-worker architecture distributes image blocks through master-coordinated chaotic sequence management, maintaining one logically continuous chaotic sequence by assigning block-specific starting states independently of worker assignments. The implemented system uses reversible chaotic substitution (SUBSTITUTE), while Elliptic Curve Digital Signature Algorithm (ECDSA)-signed discovery messages and Transport Layer Security (TLS) 1.3 with mutual authentication secure device communication. Experimental evaluation using one, two, and four workers demonstrates a reduction in execution time from 43.215 to 15.878 seconds, achieving a speed-up of 2.72 times. The encrypted image achieves a Shannon entropy of 7.999940 bits/byte and near-zero adjacent-pixel correlation. Exact image recovery is verified through matching Secure Hash Algorithm 256-bit (SHA-256) hashes and a Structural Similarity Index (SSIM) value of 1.0. Additional experiments demonstrate successful encryption and decryption using different worker counts and block sizes, automatic task reassignment following worker failure, and rejection of a mismatched private key during TLS authentication. These findings demonstrate the feasibility of secure, flexible, and distributed chaotic image processing across independent resource-constrained IoT devices.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.09767

Listen to the Features: Voice Anonymization Driven by Content Embedding Matching over Signal Reconstruction

Adrien Schneider, Kacper Zabkowski, Anderson Augusma, Fr{é}d{é}rique Letu{é}, Maria Camila Pinzon, Dominique Vaufreydaz

原文摘要

The paper presents a voice anonymization model focusing on preserving content rather than producing realistic speech. It relies on content embeddings extracted from a frozen pretrained wav2vec2 encoder. These embeddings are decoded into an anonymized signal using vector quantization and a HiFi-GAN vocoder, both trained on LibriTTS without any waveform reconstruction loss or speaker embedding mapping. The training objective enforces that embeddings of the anonymized signal match those of the original one. While training, an auxiliary speaker classification branch with a gradient reversal layer is used to discard speakerspecific information. Results show that this straightforward embedding-based approach achieves very low WER (2.53) with an anonymization performance (EER 13.39) ranking within first level for VPC. Notably, emotions are partially preserved (UAR 43.91), even without a supporting training objective, while the anonymized voice is audible without reconstruction loss.

eess.SP · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14204

Performance Portability Explained: Insights from accelerating ICON microphysics

Faveo Hörold, Georgiana Mania, Panagiotis Adamidis, Harshada Balasubramanian, Jörg Behrens, Yakup Budanaz, Alexandru Calotoiu, Nicoletta Farabullini 等 18 位作者

原文摘要

Scientific computing is under increasing pressure to adapt to HPC hardware that is shaped by AI workloads. In these modern ecosystems, extracting reasonable performance without investing major engineering effort is a central issue for domain scientists. Correctness constraints and intricate reference implementations represent further impediments to development. Instead of using a double-precision implementation as a reference, considering the underlying scientific problem directly opens more opportunities for performance improvements when updating and rewriting applications. We take seven different portability frameworks---covering pragma-based, DSL, and data-centric approaches---and evaluate them on a microphysics kernel of the ICON climate model. Our performance benchmarks show that each different HPC system benefits from a different combination of optimizations, so we develop the measure of framework expressivity to gauge how easily each framework can customize portable implementations in this way.

cs.DC · cs.PF · cs.PL

查看论文
arXiv ↗PDF ↗