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

+1958新增论文
+1549其中 AI 相关
+212已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 19:15 · 全站最近入库:2026-11-17 20:18各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 22:28 — 2026-11-17 22:28(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:2026-11-17 19:15最近发现新增版本:2026-11-17 20:18库内论文最新更新时间:2026-11-17 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。

25,785 已收录论文21,490 AI 相关7,725 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 176 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 19:14(北京时间)
新论文 · v1arXiv:2611.21335

Anchoring Motion, Refining Trajectories: Generalizable Continuous Neural Decoding

Fanqi Shen, Junru Chen, Surui Cheng, Jiahe Li, ZhiZhang Yuan, Gaorui Zhang, ZhiYuan Cao, Xiaoquan Shen 等 9 位作者

原文摘要

Brain activity encodes motor information across multiple temporal scales, enabling continuous neural control beyond discrete action recognition. However, existing methods are typically tailored to specific subjects and tasks, with direct neural-to-kinematic mappings that can entangle subject-specific neural variability with task-dependent motion patterns, limiting generalization. To address these limitations, we introduce AMRT, a shared neural decoding framework for heterogeneous electrode configurations and movement paradigms. Motivated by cortical encoding of movement direction and speed, AMRT adopts a two-stage design that anchors local motion through velocity estimation and refines the resulting trajectories over longer horizons, encouraging reuse of local motion tendencies across subjects and tasks. Across three datasets, AMRT generalizes to unseen trials and subjects and demonstrates transfer potential across neural recordings and movement paradigms, highlighting the potential of shared neural representations and anchor-and-refine decoding for generalizable continuous neural control.

q-bio.NC · cs.LG

版本更新 · v2arXiv:2606.31411

Linguistic Bias Mitigation for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck

Anh-Tuan Dao, Driss Matrouf, Mickael Rouvier, Nicholas Evans

原文摘要

Rapid advancements in generative speech technology have compromised the reliability of voice biometrics. While current spoofing detectors excel when assessed under in-domain conditions, generalisation to out-of-domain settings is often poor. We show that this can be due to linguistic bias. A reliance on linguistic cues observed in training data can then compromise robustness to cross-data. We propose a linguistic-invariant spoofing detection framework utilizing teacher-student adversarial learning. The linguistic-aware teacher model, pre-trained on linguistic content of an external dataset, guides the student detector via gradient reversal to minimize the linguistic information. To prevent the inadvertent removal of non-linguistic cues, we incorporate a Variational Information Bottleneck to enable suppression of principal cues. Across nine DF Arena datasets, our method achieves up to a 36.2% relative reduction in the EER compare to the baseline.

cs.CL · cs.LG

新论文 · v1arXiv:2611.21079

SemiNovo: Learning Beyond Search-Identified Spectra for De Novo Peptide Sequencing

Pan Liu, Dongxin Lyu, Yusen Tan, Yifan Li, Hai-tao Yu, Yunhua Zhong, Zikun Wang, Tianze Ling 等 9 位作者

原文摘要

Sensitive peptide identification is fundamental to protein characterization and novel protein discovery, for which de novo peptide sequencing (DNPS) from tandem mass spectra provides an important database-independent approach. Although deep learning has substantially advanced de novo sequencing, existing models are predominantly trained on high-confidence peptide-spectrum matches obtained through database search. This search-conditioned supervision excludes a large fraction of unidentified spectra, creating a distribution mismatch between the selectively labeled training data and the complete spectrum stream encountered at inference time, thereby limiting peptide identification performance. To address this challenge, we propose SemiNovo, a semi-supervised framework that learns jointly from identified and unlabeled spectra. SemiNovo first constructs DarkSpec, a large-scale quality-controlled corpus of unlabeled spectra collected from diverse public proteomics projects, thereby extending training beyond search-identified spectra and mitigating the resulting shift in DNPS supervision. It then combines stepwise mass-constrained autoregressive decoding with cumulative path confidence to derive reliable supervision from unlabeled spectra. Moreover, SemiNovo introduces head-wise chemical-evidence gating to improve spectral evidence aggregation under noisy and incomplete fragmentation. Experiments show that SemiNovo performs favorably against state-of-the-art methods on multiple benchmarks. Code and dataset are publicly available.

cs.LG · cs.AI

版本更新 · v3arXiv:2607.11505

Proxy OPD: On-Policy Distillation with Transferable Relative Proxy Update for Large Language Models

Daocheng Fu, Rong Wu, Yu Yang, Jianbiao Mei, Licheng Wen, Xuemeng Yang, Yong Liu, Botian Shi 等 10 位作者

原文摘要

Reward-based reinforcement learning (RL) improves large language models but incurs substantial costs when repeated across targets. On-policy distillation (OPD) reuses experts by matching their distributions on target-generated trajectories, yet differing base policies can confound reward-induced updates with pre-existing policy differences, potentially distorting transferred update directions. We propose Proxy OPD (P-OPD), a post-training method that transfers reward-induced relative policy updates using the target's frozen base policy as a reference. A proxy undergoes reward-guided exploration, yielding token-level log-probability changes between its initial and optimized policies. These signals guide learning on target-generated trajectories, with calibration controlling signal absorption, enabling reuse of reward-induced improvements across targets. Experiments on Qwen3-family targets in mathematical reasoning, code generation, and instruction following show that P-OPD improves targets and outperforms conventional OPD in most settings. For 1.7B-to-8B transfer, average Math Mean@16 and Code Mean@8 scores exceed OPD by 8.3 and 3.4 points, respectively. Mechanism analyses show more faithful reward-induced supervision and controllable adaptation. Cross-scale and cross-generation experiments confirm signal transferability and reusability, while multi-domain distillation reveals synergistic gains and cross-domain interference. In the measured 4B-to-8B setting, target adaptation after proxy exploration takes approximately 15\% of direct target RL time; repeated signal reuse amortizes the one-time exploration cost across compatible models. These findings support relative policy updates as effective, transferable, and composable supervision for an ``explore once, transfer multiple times'' post-training paradigm.

cs.LG · cs.AI

版本更新 · v2arXiv:2608.27259

LEON: Operator-Structured Latent Evolution for World Modeling

Xiaoxiao Lu, Jiahao Shi, Yunlong Dong, Ye Yuan

原文摘要

Modeling action-conditioned physical evolution is fundamental to latent world models. World Action Models (WAMs) couple such models with policy learning through predictive supervision or future-conditioned action generation. Yet their latent transitions typically rely on transformer-based predictors, leaving dynamical structure to be learned implicitly from data. We derive a latent-transition formulation from controlled mechanical evolution. A common finite-dimensional projection of observable dynamics yields a shared operator family affine in physical control and an explicit projection residual. Guided by this principle, we introduce the Latent Evolution Operator Network (LEON), which adapts pretrained visual features into learned observables and evolves them through an affine family of shared operator matrices and complementary additive updates. Coefficients inferred from evolving observables and action-related context modulate the operators. We instantiate LEON in two WAM architectures while preserving their distinct original prediction targets and policy interfaces. Across single-arm and bimanual manipulation, LEON improves average policy success over corresponding WAM baselines, including under diverse perturbations. Ablations support its observable adaptation and operator-structured evolution, while controlled-system evaluations demonstrate improved extrapolation beyond training conditions.

cs.LG · cs.AI · eess.SY

版本更新 · v2arXiv:2611.03390

Progressive Multi-Scale Super-Resolution via Cascaded Bicubic Anchors and Inter-Scale Mutual Refinement

Chun-An Lin, Yu-Chia Chang, Chi-Mao Fan, Yen-Chieh Ouyang, Tsung-Jung Liu

原文摘要

Super-resolution networks are trained for one magnification factor, so several output resolutions require several models. We propose PMS-SR, a progressive single-input multiple-output network that produces x2, x4, and x8 results in one forward pass, with a Transformer backbone on the low-resolution grid. In Stage 1, each scale is predicted as a residual over the detached bicubic upsampling of the previous scale's prediction. With Dirac and zero initialization, training starts exactly from the bicubic cascade, and each head adds only the band the previous scale lacks. In Stage 2, inter-scale mutual refinement couples the scales in both directions through space-to-depth feedback, deformable alignment, and per-pixel fusion, so x8 features refine the x2 output. Trained on DF2K, the 7.95M-parameter model achieves a higher PSNR than every compared multi-scale method at x4 and x8 on all five standard benchmarks. At x8, it outperforms the x8-specific DRN-L on all of them, leads all compared methods on Urban100, and is within 0.13 dB of the best result elsewhere. Against three single-scale SwinIR-M models, PMS-SR uses 22% of the parameters, runs 2.9x faster on BSD100 inputs, and its outputs agree 6.7-12.4 dB more closely. Code and pretrained models will be released at https://github.com/julian135707/PMS-SR upon acceptance.

cs.CV · cs.LG · eess.IV

版本更新 · v2arXiv:2611.02688

Accelerating LLM Pretraining with Zeroth-Order Curvature on Idle Serving Compute

Mingchuan Ma, Dongqi Cai, Daqian Yang, Zhenyan Lu, Chen Chen, Teresa Lv, Yan Gao, Shangguang Wang 等 11 位作者

原文摘要

LLM pretraining is increasingly compute-intensive, while substantial inference serving compute remains idle during off-peak periods. However, such serving hardware is difficult to use for conventional first-order training due to its memory, networking and other system requirements. Zeroth-order (ZO) optimization offers a natural interface to this forward-only compute resource, but its gradient estimates break down in pretraining. Unlike fine-tuning, which can confine updates to a small parameter subspace, pretraining must update every parameter, and the alignment of a ZO gradient estimate with the true gradient shrinks as the number of updated parameters grows. We make a different observation: noisy ZO estimates can still provide useful curvature information, even when they are too inaccurate to serve as gradients. Based on this insight, we propose ZO-Curv, which leverages idle forward-only devices to estimate curvature and uses it to adapt and refine the update used during first-order training, thereby accelerating the process. We provide convergence guarantees that characterize the effect of finite-query curvature estimation. Experiments on LLMs from 125M to 1.5B parameters show that ZO-Curv consistently accelerates pretraining. At 770M parameters, ZO-Curv reaches AdamW's 20K-step validation loss in 3.9 hours instead of 7.5 hours, while achieving a lower final loss of 2.70 versus 2.84 under the same step budget. These results show that idle model serving compute can accelerate LLM pretraining when zeroth-order queries are used to estimate curvature rather than gradients directly.

cs.LG · cs.AI

版本更新 · v2arXiv:2411.15036

Safe Multi-Agent Reinforcement Learning with Convergence to Generalized Nash Equilibrium

Zeyang Li, Navid Azizan

原文摘要

Multi-agent reinforcement learning (MARL) has achieved notable success in cooperative tasks, demonstrating impressive performance and scalability. However, deploying MARL agents in real-world applications presents critical safety challenges. Current safe MARL algorithms are largely based on the constrained Markov decision process (CMDP) framework, which enforces constraints only on discounted cumulative costs and lacks an all-time safety assurance. Moreover, these methods often overlook the feasibility issue (the system will inevitably violate state constraints within certain regions of the constraint set), resulting in either suboptimal performance or increased constraint violations. To address these challenges, we propose a novel theoretical framework for safe MARL with $\textit{state-wise}$ constraints, where safety requirements are enforced at every state the agents visit. To resolve the feasibility issue, we leverage a control-theoretic notion of the feasible region, the controlled invariant set (CIS), characterized by the safety value function. We develop a multi-agent method for identifying CISs, ensuring convergence to a Nash equilibrium on the safety value function. By incorporating CIS identification into the learning process, we introduce a multi-agent dual policy iteration algorithm that guarantees convergence to a generalized Nash equilibrium in state-wise-constrained cooperative Markov games, achieving an optimal balance between feasibility and performance. Furthermore, for practical deployment in complex high-dimensional systems, we propose $\textit{Multi-Agent Dual Actor-Critic}$ (MADAC), a safe MARL algorithm that approximates the proposed iteration scheme within the deep RL paradigm. Empirical evaluations on safe MARL benchmarks demonstrate that MADAC consistently outperforms existing methods, delivering much higher rewards while reducing constraint violations.

cs.LG · eess.SY

版本更新 · v4arXiv:2505.17760

But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectors

Leon Eshuijs, Archie Chaudhury, Alan McBeth, Ethan Nguyen

原文摘要

LLM-as-a-judge is widely used as a scalable substitute for human evaluation, yet judges are least reliable on subtle dishonesty such as sycophancy and manipulation, where a judge scoring a response in isolation lacks a reference point. We introduce Judge Using Safety-Steered Alternatives (JUSSA), a framework that reduces this evaluator uncertainty using the assessed model's own internal representations. An honesty-promoting steering vector, optimized from a single training example, generates a contrastive alternative against which each response is judged. On a new manipulation dataset with human-validated response pairs, JUSSA improves AUROC for both GPT-4.1 (0.893$\rightarrow$0.946) and Claude Haiku (0.859$\rightarrow$0.929) judges. The gains concentrate almost entirely on the pairs a judge would otherwise misrank. They reverse once a judge has saturated a task and for the weakest judge we test, so contrastive evaluation helps most when a judge is capable enough to use the reference but has not yet saturated the task. A layer-wise analysis further locates steering effectiveness in the middle layers, where model representations of honest and dishonest prompt processing diverge. Our work demonstrates that steering vectors can serve as tools for evaluation rather than for improving model outputs at inference, opening a new direction for white-box auditing.

cs.LG · cs.AI

新论文 · v1arXiv:2611.20445

Explainable Federated Learning via Global-Local Attribution Alignment

Dawood Wasif, Terrence J. Moore, Chang-Tien Lu, Jin-Hee Cho

原文摘要

Federated learning enables on-device training without centralizing data, yet existing systems still struggle to provide explanations that are both locally faithful and globally consistent under strict privacy and bandwidth constraints. Prior approaches either keep explanations siloed across clients, transmit heavy or sensitive artifacts, or replace expressive task models with interpretable surrogates that sacrifice accuracy. We propose xFedAlign, a model-agnostic framework that decouples task optimization in parameter space from explanation coordination in a compact group space. Each client distills a lightweight surrogate to produce private, per-class top-k attribution artifacts, which are robustly aggregated by the server into a Global Explanation Prior that softly aligns client explanations without constraining task learning. Across image, text, and tabular benchmarks with IID and non-IID partitions, xFedAlign matches FedAvg accuracy while consistently reducing explanation drift and improving deletion and insertion AUC relative to Local-XAI, FedAttr-Agg, and Fed-XAI, with only a few kilobytes of additional communication per round. Privacy and robustness evaluations further demonstrate reduced membership inference advantage and increased resistance to attribution poisoning, enabling consistent and trustworthy explanations in federated learning.

cs.LG · cs.AI

新论文 · v1arXiv:2611.20244

Right Goal, Wrong Body: Re-grounding Frozen VLAs under Actuation Shift

Umer Siddique, Peilang Li, Yongcan Cao

原文摘要

Vision-language-action (VLA) models are capable of producing desired robotic behaviors in ideal settings. However, they often fail when the robot's actuation changes at deployment. For example, remounting, mechanical wear, or command latency changes can lead to failed tasks and unsafe behaviors. To address the inevitable actuation shift, we propose ReGround, an inference-time method that keeps the VLA frozen and re-grounds its intended motion. ReGround learns the deployed robot's dynamics from task-agnostic motor babbling, and then tracks the policy's intended motion while staying close to the policy's own plan. ReGround activates only upon detecting a shift, and needs no rewards, demonstrations, or retraining. We show via two VLAs, eight LIBERO tasks, and five shift settings that ReGround can restore near-oracle success, such as raising $π_{0.5}$'s success from 0.16 to 0.90 under 400 ms latency, while remaining safer than a linear-calibration baseline. Project website and open-source code: https://umersiddique94.github.io/ReGround/.

cs.RO · cs.AI · cs.LG

版本更新 · v4arXiv:2504.15564

OpenClassGen: A Large-Scale Corpus of Real-World Python Classes for LLM Research

Musfiqur Rahman, SayedHassan Khatoonabadi, Emad Shihab

原文摘要

Existing class-level code generation datasets are either synthetic (ClassEval: 100 classes) or insufficient in scale for modern training needs (RealClassEval: 400 classes), hindering robust evaluation and empirical analysis. We present OpenClassGen, a large-scale corpus of 324,843 Python classes extracted from 2,970 engineered open-source projects. Each entry pairs a human-written class with its corresponding skeleton, which comprises class and method signatures with associated docstrings, and is enriched with 27 static code metrics covering complexity, coupling, cohesion, and inheritance properties. Unlike prior benchmarks that require repository-level context resolution, OpenClassGen provides self-contained class skeletons that serve as complete generation specifications. We demonstrate the corpus's utility by evaluating three LLMs (GPT-o4-mini, Claude-4-Sonnet, Qwen-3-Coder) on a curated, executable subset of 300 classes, enriched with test suites achieving 58% branch coverage. Results show strong semantic similarity (CodeBERTScore-F3: 0.89) but moderate functional correctness (pass rate: 0.33), with substantial variance across models. This variance, along with diverse class characteristics, confirms that OpenClassGen enables meaningful differentiation of LLM capabilities. The dataset supports diverse use cases, including fine-tuning, retrieval-augmented generation, difficulty modelling, and failure mode analysis. The complete dataset and curation scripts are publicly available at https://zenodo.org/records/18409150.

cs.SE · cs.AI · cs.LG

新论文 · v1arXiv:2611.20058

SWAN-Rx: Efficient and Bandwidth-Scalable Neural Reception for MIMO-OFDM

Zhoubin Kou, Cong Shen

原文摘要

We present a Scalable Windowed Axial-attention Neural Receiver (SWAN-Rx) for multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) systems. The receiver improves reception accuracy and reduces forward-pass computation while supporting frozen-weight reuse across bandwidth allocations and channel conditions. It combines a common resource-element representation of received observations and pilot context with alternating time-axis and local frequency-axis attention. Shared parameters and relative positional information permit soft detection across allocation lengths without inference-time parameter updates. At fixed subcarrier spacing, model configuration, and symbol count, bounded frequency neighborhoods give linear growth of forward-pass computation with bandwidth. Evaluations compatible with the 5G New Radio physical layer reuse weights trained on four physical resource blocks (PRBs) at up to 273 PRBs and on unseen channels. At the training bandwidth, SWAN-Rx achieves lower pre- and post-decoding bit error rates than the implemented three-step neural receiver (NRX) and DeepRx-MIMO baselines, with 16.9% and 39.7% fewer parameters and 56.3% and 35.7% fewer forward-pass operations, respectively. The same weights achieve lower pre-decoding error rates than these baselines throughout the evaluated bandwidth-extrapolation and 16-PRB channel-transfer tests, with an estimated 0.4-0.9 dB signal-to-noise ratio reduction relative to NRX at a pre-decoding error rate of $10^{-2}$ in the 16-PRB tests.

eess.SP · cs.IT · cs.LG

版本更新 · v5arXiv:2610.20585

Learnable Hodge-Laplacian Driven Mixture of Experts for Steady-PDE Surrogates on Coarse Unstructured Meshes

Stavros Nousias, Akis Nousias, Konstantinos Gkrispanis

原文摘要

Surrogate models approximate the solutions of partial differential equations (PDEs) for given geometries and boundary conditions. Conventional Transformer-based approaches typically employ a common feature-mixing mechanism across the solution domain, despite the presence of spatial variations at different scales. In this paper, we propose a mixture of transformer experts that combines a routing mechanism with multiscale supervision. Specifically, the individual experts are routed through a controller that utilizes learnable Laplacian matrices to compute weights, used to define a weighted sum of the experts for the output feature vectors at each point of the domain. Subsequently, a decoder receives the weighted sum of the experts output and predicts the solution fields. During training, the reference fields are decomposed into components at different spatial scales by repeated smoothing with a mesh Laplacian. We evaluate our approach on the official AirFRANS dataset using remeshed solution domains leading to unstructured triangular meshes of $4.9$k vertices. The experimental outcomes reveal lower mean relative $L_2$ error and interior mean squared errors among the compared models of this study. Code and data are publicly available in https://github.com/snousias/hodge-moe-pde

cs.LG · cs.CV

版本更新 · v3arXiv:2601.22259

Tabular Foundation Models Can Do Survival Analysis

Da In Kim, Wei Siang Lai, Kelly W. Zhang

原文摘要

While tabular foundation models have achieved remarkable success in classification and regression, adapting them to model time-to-event outcomes for survival analysis is non-trivial due to right-censoring, where data observations may end before the event of interest occurs. In this work, we systematically study a variety of approaches to utilize off-the-shelf tabular foundation models originally designed for classification for discrete-time survival modeling. We evaluate existing classification formulations, including hazard modeling and multi-class classification approaches, and introduce a new formulation that directly models cumulative failure probabilities at discretized time points, treating censored observations as examples with missing labels at certain time points. We prove that under standard censoring assumptions, minimizing the weighted cross entropy loss recovers the true survival probabilities as the training set size increases. Across $60$ real-world datasets ($54$ static and $6$ dynamic), we find that TFMs paired with classification reductions often outperform or are competitive with classical and deep learning survival baselines on average across multiple survival metrics. Our results show that off-the-shelf TFMs provide a flexible approach to survival modeling, allowing time discretization to be adapted at inference without training. Our comparison provides practical guidance on when to use these models and which survival formulation to choose.

cs.LG

版本更新 · v4arXiv:2505.11294

双向信息流(BIF):一种用于贝叶斯优化的样本高效分层高斯过程

Bidirectional Information Flow (BIF) - A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization

Juan D. Guerra, Thomas Garbay, Numa Dancause, Guillaume Lajoie, Marco Bonizzato

AI 速读 基于摘要

提出双向信息流(BIF)分层高斯过程,通过父子模型间连续双向通信提升贝叶斯优化的样本效率与模块复用性。

cs.LG

查看原文摘要

Hierarchical Gaussian Process (H-GP) models divide problems into different subtasks, allowing for different components to address each part, making them well-suited for problems with inherent compositional structure. However, existing H-GP frameworks typically employ one-way information sharing - either top-down or bottom-up - which limits sample efficiency and slows convergence. We propose Bidirectional Information Flow (BIF), which establishes continuous two-way communication. BIF retains the modular structure of hierarchical models - the parent conditions its own posterior on child summaries, treating them as structured priors - while introducing top-down feedback to softly decompose environment observations from the parent into sub-responses. This mutual exchange improves sample efficiency, enables robust training, and allows modular reuse of learned subtask models. We prove analytically the regret of a GP with a learned kernel scales linearly with the mismatch to the true kernel, tightening in the hierarchical case to the sum of child-level errors. Ablation shows removing the downward pathway collapses child $R^2$ by up to 58%. Across synthetic, neurostimulation, and HPO benchmarks, BIF achieves up to $4\times$ higher parent $R^2$ and roughly 100% AUC improvement over vanilla GPBO, and outperforms or is the runner-up in 38/40 tests compared to the state-of-the-art baselines while supporting modular child transfer to novel composite tasks.

新论文 · v1arXiv:2611.18417

CoPre-MoE: Consolidating and Preserving MoE for Multimodal Continual Instruction Tuning

Tao Hu, Ling-Xiang Zhang, Da-Wei Zhou

原文摘要

Multimodal continual instruction tuning requires multimodal large language models to sequentially acquire new capabilities without catastrophic forgetting. Mixture-of-experts (MoE) architectures offer a promising way to mitigate task interference through expert specialization and combination. However, while existing MoE-based methods avoid overwriting shared parameters by allocating separate experts for each task, this progressive expansion incurs severe cross-task redundancy and linear parameter growth. Specifically, experts across tasks often learn overlapping functions alongside task-specific capabilities. For instance, ScienceQA and TextVQA both locate relevant image regions. To curb parameter redundancy without inducing forgetting, we propose Consolidating and Preserving MoE (CoPre-MoE). For each incoming task, CoPre-MoE first learns task-specific MoE to capture specialized capabilities. To eliminate redundancy and reduce parameter growth across tasks, we design a shared-and-private expert architecture. Specifically, we first evaluate functional overlap to selectively consolidate overlapping experts across tasks into a fixed-capacity generic expert pool. We then factorize the remaining task-specific experts into shared projection bases and compact task-specific cores within a private expert pool. To mitigate forgetting, we construct the router by pairing each expert with learnable retrieval keys, where historical keys remain frozen during continual updates while newly added keys are regularized with an orthogonality penalty. At inference, input-dependent routing dynamically combines both pools without test-time task labels. Extensive experiments demonstrate that CoPre-MoE achieves superior performance while substantially reducing parameter overhead.

cs.CV · cs.AI · cs.LG

新论文 · v1arXiv:2611.18372

Vision-Language-Action Models: A Life-Cycle Survey of Design, Training and Deployment

Suvarna Kadam, Soran Parsa

原文摘要

Vision-language-action (VLA) models adapt web-pretrained vision-language models to output robot actions, so that web knowledge carries over to physical control. In under 4 years the field has moved from RT-2, the first VLA, to open models that fine-tune on a single consumer GPU and to proprietary generalists that clean unseen homes. This survey reviews 88 works from December 2022 to October 2026, mainly on manipulation and navigation, plus humanoid control, world-action models and evaluation. We follow a VLA through its life cycle, from model design to training and deployment, along seven axes. Model design covers (a) inputs and memory, what the model observes; (b) architecture, how its pipeline is built; (c) action output, how it produces motor commands; and (d) intermediate predictions, what else it predicts, from reasoning steps to future observations. Training covers (e) pretraining data, the mix of robot, web, human and simulated data, and (f) post-training, adaptation to the target robot. Deployment covers (g) real-time execution, keeping pace with the robot. We analyse 22 models on these axes and report their training data, model size, inference speed and hardware. Three trends emerge: (i) training data has broadened, from about 10,000 hours of teleoperated robot data ($π_0$) to 23,000 community-collected episodes (SmolVLA) and 20,000 hours of egocentric human video (GR00T N1.7); (ii) model sizes have split: most recent models have 3-7 billion parameters, while a new group under one billion runs on consumer GPUs; and (iii) generalist VLAs are emerging that handle both manipulation and navigation, such as UniVLA and Qwen-VLA. We also compare VLAs with world-action models, which predict future observations as well as actions. We review evidence that some VLAs with near-perfect benchmark scores fail when objects or the camera move slightly, and open up further research questions.

cs.RO · cs.AI · cs.ET · cs.LG

新论文 · v1arXiv:2611.18235

NeoResearch: Literature- and Experience-Guided Autonomous Time Series Model Discovery

Ze Guo, Mingyue Cheng, Xiaoyu Tao, Shuo Yu, Shangtong Ye

原文摘要

Developing effective forecasting models for diverse time-series domains requires substantial expert knowledge, evidence from scientific literature on the web, and iterative experimentation. However, translating this knowledge and research experience into model designs requires preserving source context and testing applicability under task-specific assumptions. In this paper, we propose NeoResearch, a literature- and experience-guided autonomous research framework that leverages large language models (LLMs) as researchers to discover lightweight, domain-specific forecasting models. Specifically, NeoResearch establishes an expert-inspired dual-loop research workflow, coupling hypothesis-driven architecture exploration with iterative training and hyperparameter optimization through experimental feedback. To enable knowledge-grounded discovery, the agent autonomously mines scientific literature from the Web, extracting modeling mechanisms, empirical evidence, and applicability conditions to formulate task-grounded, testable architecture hypotheses. Furthermore, a hierarchical experience memory links literature findings to experimental outcomes and consolidates conditional lessons, guiding architecture discovery and training optimization while supporting reuse across forecasting tasks. Experiments on ten datasets show competitive performance and support dual loops, literature extraction, and memory reuse. Our code is available.

cs.LG

新论文 · v1arXiv:2611.18163

On the Limits of Sufficient Explanations

Klaus Weinbauer, Peter F. Stadler, Thomas Gärtner, Sagar Malhotra

原文摘要

We formally characterize the conditions under which sufficient explanations exist for classifiers on structured data such as graphs and strings. We focus on post-hoc explainers that select parts of the input as sufficient explanations. An explanation is sufficient if the selected part alone ensures the predicted label. Sufficient explanations have been widely adopted across data modalities, including graphs, strings, and images. However, a unified formal analysis of sufficient explanations remains missing. We bridge this gap with four main contributions: (i) We define a general explanation formalism consisting of an instance space, a classifier, and a select relation. The select relation specifies which potential sub-instances or feature subsets can be selected as explanations from each instance; (ii) We show that the existence of sufficient explainers is fully characterized by the interplay between the classifier and the select relation; (iii) We extend this analysis to practically relevant variants of sufficiency, including probabilistic sufficiency and deletion sufficiency; (iv) Based on the formal analysis, we devise statistics that bound the maximum achievable sufficiency for a given task. We evaluate these statistics on language, protein, and molecular classification datasets and find that full sufficiency is unattainable on most of them. Since these bounds hold for every explainer, they provide a task-level reference against which any explainer's sufficiency can be judged in absolute terms.

cs.LG

版本更新 · v3arXiv:2508.00910

Cyber-Zero: Training Cybersecurity Agents without Runtime

Terry Yue Zhuo, Dingmin Wang, Hantian Ding, Varun Kumar, Zijian Wang

原文摘要

Large Language Models (LLMs) have achieved remarkable success in software engineering tasks when trained with executable runtime environments, particularly in resolving GitHub issues. However, such runtime environments are often unavailable in other domains, especially cybersecurity, where challenge configurations and execution contexts are ephemeral or restricted. We present Cyber-Zero, the first runtime-free framework for synthesizing high-quality agent trajectories to train cybersecurity LLMs. Cyber-Zero leverages publicly available CTF writeups and employs persona-driven LLM simulation to reverse-engineer runtime behaviors and generate realistic, long-horizon interaction sequences without actual environments. Using trajectories synthesized by Cyber-Zero, we train LLM-based agents that achieve up to 11.4% absolute performance gains over baseline models on three prominent CTF benchmarks: InterCode-CTF, NYU CTF Bench, and Cybench. Our best model, Cyber-Zero-32B, establishes new state-of-the-art performance among open-weight models, matching the capabilities of proprietary systems like DeepSeek-V3-0324 and Claude-3.5-Sonnet while offering superior cost-effectiveness, and demonstrating that runtime-free trajectory synthesis can effectively democratize the development of state-of-the-art cybersecurity agents.

cs.CR · cs.CL · cs.LG

版本更新 · v4arXiv:2510.19244

Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments

Yiyu Qian, Liyuan Zhao

原文摘要

Deep reinforcement learning (RL) achieves remarkable performance but lacks interpretability, limiting trust in policy behavior. The existing SILVER framework (Li, Siddique, and Cao 2025) explains RL policy via Shapley-based regression but remains restricted to low-dimensional, binary-action domains. We propose SILVER with RL-guided labeling, an enhanced variant that extends SILVER to multi-action and high-dimensional environments by incorporating the RL policy's own action outputs into the boundary points identification. Our method first extracts compact feature representations from image observations, performs SHAP-based feature attribution, and then employs RL-guided labeling to generate behaviorally consistent boundary datasets. Surrogate models, such as decision trees and regression-based functions, are subsequently trained to interpret RL policy's decision structure. We evaluate the proposed framework on two Atari environments using three deep RL algorithms and conduct human-subject study to assess the clarity and trustworthiness of the derived interpretable policy. Results show that our approach maintains competitive task performance while substantially improving transparency and human understanding of agent behavior. This work advances explainable RL by transforming SILVER into a scalable and behavior-aware framework for interpreting deep RL agents in high-dimensional, multi-action settings.

cs.LG

版本更新 · v3arXiv:2605.04081

Time series causal discovery with variable lags

Bruno Petrungaro, Anthony C. Constantinou

原文摘要

Causal Bayesian Networks (CBNs) are a powerful tool for reasoning under uncertainty about complex real-world problems. Such problems evolve over time, responding to external shocks as they occur. To support decision-making, CBNs require a cause-and-effect map of the variables under consideration, known as the network's structure. Learning the graphical structure of a causal model from data remains challenging; learning it from time-series data is even harder because dependencies may arise at different time lags. We construct a method that jointly learns a temporal ordering and a dominant lag for each selected ordered variable pair. Our contribution is a decomposable BIC-style objective score for mixed data that combines node-specific sample sizes with a penalty favouring recent lags. We optimise this objective using a Tabu search augmented with change-lag moves and greedy per-child lag tuning, while its node-wise decomposition supports cached and parallel neighbourhood evaluation. We establish acyclicity and complexity results and derive recovery limits when effects are distributed across multiple lags. In simulations, we show that the proposed method outperforms an inflexible lag-1 score-based learner in most evaluated settings, whereas most specialised methods achieve higher recovery accuracy on data that satisfy their assumptions. On a real-world UK COVID-19 dataset, the method learnt an expected short-lag-skewed structure; nevertheless, 46.8% of selected edges had lags greater than one, showing that longer delays can be retained when their improved fit offsets the penalty. Under its no-contemporaneous-edges and causal-sufficiency assumptions, the method provides a computationally tractable subroutine for edge-specific single-lag optimisation, complementing score-based causal discovery methods.

cs.LG · cs.AI

新论文 · v1arXiv:2611.17560

Generative Design with Real-time Physics Explainability: Towards Product Definition in the Age of AI

M. de Campos, C. Drygala, E. Ross, A. Bruce, M. Bohon, H. Gottschalk

原文摘要

In this article, we explore opportunities from using generative AI in mechanical engineering. On the one hand, generative methods based on invertible neural networks have been recently proposed for the solution of inverse design problems, allowing to infer design parameters from performance labels. On the other hand, generative AI models have shown that they can act as real time capable surrogates for physics based simulations. Here we suggest that these two streams should be combined in a unified framework, where INN are used to control the design process from the customer requirements perspective and the generative simulation of the systems physics adds a layer of explainability, why the proposed design fulfils the requirements. As generative design is prone to hallucinations, we propose uncertainty quantification to fend off physically infeasible requests. Finally, validation with classical tools is a requirement for generative design process. To demonstrate the capabilities of our novel generative design paradigm, we develop two interactive environments, one for airfoil design based on simulator data and one for the combustor design space exploration based on measured data.

cs.LG · physics.comp-ph

版本更新 · v3arXiv:2510.10140

Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction

Yue Deng, Francisco Santos, Pang-Ning Tan, Lifeng Luo

原文摘要

Deep learning-based weather forecasting (DLWF) models leverage past weather observations to generate future forecasts, supporting a wide range of downstream applications, including tropical cyclone (TC) prediction. In this paper, we investigate the vulnerability of these models to adversarial attacks, where subtle perturbations to upstream forecasts can alter downstream TC trajectory predictions. Crafting perturbed inputs to steer downstream outputs toward attacker-specified trajectories is a challenging problem for several reasons. First, conventional TC detection systems are opaque, non-differentiable black boxes, making standard gradient-based attacks infeasible. Second, the extreme rarity of TC events leads to a severe class imbalance problem, making it difficult to develop attack methods that produce realistic-looking cyclone paths aligned with target trajectories. To overcome these limitations, we propose Cyc-Attack, a novel method for perturbing the forecasts of DLWF models to generate adversarial trajectories. The proposed method uses a differentiable surrogate model to approximate the TC detector's output, enabling the application of gradient-based attacks. Cyc-Attack also employs a skewness-aware loss function with a kernel dilation strategy to address the severe class imbalance problem. Distance-based gradient weighting and regularization strategies are also introduced to constrain perturbations to eliminate unrealistic-looking TC paths. Our experiments show that Cyc-Attack achieves a higher true positive rate in matching the target trajectories, along with lower false alarm rates and stealthier perturbations than conventional attack methods. We further demonstrate that the adversarial upstream forecasts generated by Cyc-Attack can be leveraged as initial guidance to train an end-to-end model for learning adversarial input samples that would induce target trajectories.

cs.LG · cs.CR · stat.ML

版本更新 · v2arXiv:2609.38540

When a Flatness Proxy Is Not a Function: Robustness Certificates and Training Interventions

Vicente Opazo

原文摘要

A valid curvature upper bound need not justify either a robustness certificate or an intervention on an intrinsic predictor property. We demonstrate this distinction for a last-layer relative-flatness proxy used in both settings. First, empirical-risk stationarity does not eliminate pointwise first-order loss terms: at a finite global empirical-risk minimum, the retained certificate expression underestimates a loss increase by over $210\times$. We derive a globally valid, gauge-invariant feature-space repair. Second, common-row softmax shifts preserve predictions and the exact contraction while making the proxy unbounded. Even standard reference-class choices double it on average relative to the centered representation. For a single fixed-feature example with at least three classes, scalar retuning generically cannot align the induced probability updates. Row centering gives the orbit-minimized bound and restores value and full-model gradient invariance under this symmetry. Across 45 paired one-step tests on algorithmic and image models, amplified shifts separate raw-regularized predictors while quotient-regularized predictors remain aligned. Long-horizon CIFAR-10 experiments show substantial, reversible suppression of generalization, while evidence for selective delay after memorization is less consistent. Together, these results show that validity as a curvature upper bound does not by itself justify either inversion into a robustness certificate or differentiation into an intrinsic training intervention.

cs.LG

新论文 · v1arXiv:2611.17297

大语言模型中的目标编码

Goal Encoding in LLMs

Arnab Sen Sharma, Eric Todd, Sheridan Feucht, Andy Arditi, Rohit Gandikota, Natalie Shapira, Gabriele Sarti, Constanza Fierro 等 10 位作者

AI 速读 基于摘要

作者在编程任务设定中定位到LLM对下一子目标的稀疏注意力头编码,并验证其因果性与可迁移性,进而提出非递归目标寻求(NRGS)解释。

cs.CL · cs.AI · cs.LG

查看原文摘要

We investigate whether and how LLMs encode goals: internal neural representations that precede and guide action, and that are flexible enough to be realized through many different execution paths. We construct a coding setting with multiple sub-tasks that allows us to evaluate goal-seeking behavior and the selection of sub-goals. In this setting, we localize an encoding of the next sub-goal in the outputs of a sparse set of attention heads. The same heads can be used to decode the LM's future actions in natural language (e.g., "I'm checking if a word is a palindrome"). We verify that this encoding is causal for next action and is plastic: transplanting it into a different environment, e.g., another programming language, triggers the same operation realized with a different sequence of tokens. The LM also sustains the encoding throughout the action's execution, which is puzzling because a transformer LM without recurrence cannot carry a state forward for more tokens than it has layers left. We propose that it does not need to. Under a non-recurrent goal-seeking (NRGS) account, the LM frequently re-reads the goal from the task specification, compares it with the progress visible in the growing context, and pursues what remains. We test the predictions of this account with targeted causal interventions.

版本更新 · v2arXiv:2606.09949

学习在哪里模拟:面向在线PDE代理训练的生成式主动采样

Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Training

Pierre Cesar, Sofya Dymchenko, Abhishek Purandare, Bruno Raffin

AI 速读 基于摘要

提出在线生成式主动采样(OGAS),在PDE代理模型训练过程中用条件扩散模型动态挑选高难度配置参数,以缓解均匀采样导致的难例覆盖不足问题。

cs.LG · cs.AI

查看原文摘要

Paper published at NeurIPS 2026. For data-driven PDE surrogates, generalizing across a wide range of initial conditions and physical coefficients requires a training set of numerical simulations that consistently covers the resulting dynamics. Yet uniform sampling of these configuration parameters can leave challenging regimes insufficiently covered, leading to high prediction errors and large error variance in the trained surrogate. To address this sampling imbalance, we introduce the Online Generative Active Sampling (OGAS), which continuously adapts configuration sampling during surrogate training, as an alternative to classical round-based active learning. As the surrogate learns from a stream of simulation data generated online, OGAS trains a fast diffusion model in parallel to sample configuration parameters conditioned on a training difficulty signal, such as loss or uncertainty. This conditional sampler enables OGAS to parametrize subsequent simulations to generate challenging training data by prioritizing configurations with high difficulty values. We evaluate OGAS on 2D PDEs with distinct challenging dynamics-Kuramoto--Sivashinsky, Navier--Stokes, and Gray--Scott-using multiple surrogate architectures and up to 308 configuration parameters. Across the tested PDEs and architectures, OGAS consistently reduces the 99th-percentile prediction error and overall error dispersion compared with uniform sampling, while wall-clock overhead is negligible. Code and experiments are available at https://github.com/melissa-sa/ogas.

版本更新 · v3arXiv:2606.25832

MiniOpt:有限资源下通过推理建模与求解通用优化问题

MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources

Ke Zhao, Zixiang Di, Hong Qian, Xiang Shu, Yaolin Wen, Qitao Shi, Bingdong Li, Xingyu Lu 等 12 位作者

AI 速读 基于摘要

MiniOpt 是一种轻量级优化专用大语言模型,通过“推理到建模与求解”范式和两阶段 RLVR 训练,在有限参数与数据下提升跨优化结构的泛化能力。

cs.LG · cs.AI

查看原文摘要

Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented large language models (LLMs). Existing learning-based methods, however, typically require large-scale supervised data, expensive intermediate step verification, and extensive computational resources, while exhibiting limited optimization generalization across diverse optimization structures. In this paper, we propose \textsc{MiniOpt}, a lightweight optimization-specialized LLM trained through a reasoning-to-model-and-solve paradigm and a two-stage training framework with reinforcement learning with verifiable rewards (RLVR). MiniOpt encourages structure-oriented optimization learning by reinforcing the completeness of optimization formulations and optimization outcomes. Extensive experiments on eight optimization benchmarks demonstrate that MiniOpt consistently outperforms existing learning-based optimization models while requiring substantially fewer parameters and training data. To further understand optimization generalization, we introduce a complementary parameter-decoupled evaluation protocol that disentangles optimization structure understanding from numerical parameter processing. The results reveal that MiniOpt preserves optimization capability under parameter-decoupled settings significantly better than previous optimization-specialized models, suggesting that its performance gains primarily originate from stronger optimization structure understanding. These findings demonstrate an effective pathway toward efficient and generalizable optimization-specialized LLMs. The code is available at https://github.com/Hsiang-1/MiniOpt.

版本更新 · v2arXiv:2608.14198

Multimodal Zero-Shot Prediction for Transaction Data at Scale

Parameswaran Kamalaruban, Viktor Drobnyi, Maeve Madigan, Julia Rozanova, David Sutton, Stuart Burrell

原文摘要

Sequential financial transaction data are increasingly being used by financial institutions to train payment foundation models at scale, producing rich contextual embeddings that support applications such as fraud prevention, credit risk assessment, and offer personalization. However, such models are not designed for flexible instruction-following reasoning and require bespoke downstream models for each application. In contrast, large language models (LLMs) provide a natural-language interface for flexible transaction reasoning, yet naively serializing transaction histories into text representations is inefficient and costly. Multimodal fusion architectures bridge these paradigms, injecting transaction embeddings directly into flexible language reasoning pipelines. In this work, we present a systematic study of how transaction embeddings, pretrained at the scale of a global payments network, interact with LLM-based reasoning through embedding injection, transaction-language alignment, and instruction tuning. To do so, we train the Multimodal Instruction Network for Transactions (MINT), which combines a transaction encoder pretrained on billions of real-world payments with multimodal instruction tuning on millions of transaction question-answering examples. We evaluate predictive and extractive question answering, zero-shot generalization to unseen question types, and inference efficiency. Our results reveal a consistent trade-off: compact transaction embeddings improve predictive QA accuracy while substantially reducing input tokens, latency, and memory relative to a text-serialized baseline, whereas serialized histories remain highly competitive for extractive QA. Overall, our empirical findings provide a set of actionable insights and practical guidance for building multimodal transaction-aware language systems at network scale.

cs.LG · cs.CL