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

+729新增论文
+575其中 AI 相关
+82已有论文修订
+95新增 AI 导读

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

统计口径与数据新鲜度

统计 2026-11-20 15:48 — 2026-11-21 15:48(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

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

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

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 419 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
版本更新 · v6arXiv:2510.24736

RNAGenScape:基于流形朗之万动力学的性质引导优化mRNA序列生成

RNAGenScape: Property-Guided, Optimized Generation of mRNA Sequences with Manifold Langevin Dynamics

Danqi Liao, Chen Liu, Xingzhi Sun, Dié Tang, Haochen Wang, Scott Youlten, Srikar Krishna Gopinath, Haejeong Lee 等 11 位作者

AI 速读 基于摘要

RNAGenScape 提出一种在真实数据学习流形上进行性质引导朗之万动力学的mRNA序列生成框架,旨在保持生物可行性的同时优化目标性质。

q-bio.QM · cs.LG · q-bio.BM

查看原文摘要

Generating property-optimized mRNA sequences is central to applications such as vaccine design and protein replacement therapy, but remains challenging due to limited data, complex sequence-function relationships, and the narrow space of biologically viable sequences. Generative methods that drift away from the data manifold can yield sequences that fail to fold, translate poorly, or are otherwise nonfunctional. We present RNAGenScape, a property-guided manifold Langevin dynamics framework for mRNA sequence generation that operates on a learned manifold of real data. By performing iterative local optimization constrained to this manifold, RNAGenScape preserves favorable computational viability proxies, accesses reliable guidance, and discourages excursions into regions poorly supported by the training data. The framework integrates three components: (1) an autoencoder jointly trained with a property predictor to learn a property-organized latent manifold, (2) a denoising autoencoder that projects updates back onto the manifold, and (3) a property-guided Langevin dynamics procedure that performs optimization along the manifold. Across three real-world mRNA datasets spanning two orders of magnitude in size, RNAGenScape increases median oracle-predicted property gain by up to 267% and success rate by up to 31%, while maintaining good biological viability proxy measures and achieving competitive inference efficiency compared to existing generative approaches.

新论文 · v1arXiv:2611.26514

Hybrid Retrieval for Government Scheme Search in English and Marathi

Aishwarya Gunjal, Kanchan Khemnar, Pawan Poojary, Pranav Kulkarni, Raviraj Joshi, Manish Khodaskar

原文摘要

Retrieving government schemes requires matching citizens' information needs to formal administrative descriptions, often across languages and terminology. We present a bilingual search system for Maharashtra government schemes and public services that combines BM25 retrieval with sentence-embedding similarity through equal-weight score fusion. The system indexes aligned English-Marathi scheme descriptions and supports multilingual, Marathi-focused, and translation-mediated semantic configurations. Evaluation on manually curated bilingual queries compares BM25, dense retrieval, and hybrid retrieval using IndicSBERT and MahaSBERT. BM25 provides a strong baseline with a mean reciprocal rank (MRR) of 0.864. Hybrid retrieval increases MRR to 0.872 with IndicSBERT and 0.879 with MahaSBERT, whereas the corresponding dense-only systems achieve 0.663 and 0.655. MahaSBERT-based fusion also increases precision from 0.781 to 0.808 while matching BM25 recall at 0.946. These results support the complementary use of lexical and semantic signals in this collection, while showing that improvements over a strong lexical baseline are modest and metric-dependent. The study provides an application-focused analysis of hybrid retrieval for bilingual public-service information access.

cs.LG · cs.CL

版本更新 · v3arXiv:2611.09892

论智能体式操作策略

On Agentic Manipulation Policies

Chen Chen, Omid Bagherieh, Naveen Nikamanth Appiah Balaji, Jesse T. Gonzalez, Negin Heravi, Fahad Islam, Xueting Li, Jean-Baptiste Regli 等 13 位作者

AI 速读 基于摘要

作者提出并系统分析智能体式操作策略(AMPs),即用通用AI模型直接控制机械臂,在多个基准和真实任务上零样本超越专用VLA和WAM策略。

cs.RO · cs.AI · cs.CV · cs.LG

查看原文摘要

Recent work on robot manipulation has focused on specialist policies trained on demonstrations. We show that generalist AI models can control manipulators more reliably than specialist policies such as vision-language-action models (VLAs) and world-action models (WAMs). We systematically analyze agentic manipulation policies (AMPs), in which a generalist AI model commands the manipulator directly, adapting its actions as the task unfolds. We present AMP1, a reference harness that runs unchanged across single-arm, bimanual, and mobile manipulation. AMP1 achieves state-of-the-art results on the RoboLab-120 and CaP-Gym benchmarks, with no demonstrations or task-specific training. On RoboLab-120, AMP1 reaches an 85.6% success rate zero-shot, compared to 49.2% and 42.9% for leading VLA and WAM policies. The agent succeeds zero-shot in 104 of 108 real-world trials spanning twelve tasks and three robot instances, reducing failure rates by 20x and 15x relative to strong VLA and WAM baselines. The basic harness supplies no grasping, pushing, or placing skills; the agent develops its own strategies, such as searching for hidden objects, using objects as tools, and calibrating its cameras. With the addition of a persistent memory store, the agent can also learn from experience: an augmented harness with a memory representation that is carried across episodes lowers the failure rate on RoboDojo bimanual manipulation tasks by 4.6x relative to zero-shot deployment. Our analysis suggests that AMPs are substantially more general and robust than specialist manipulation policies, providing a promising foundation for robot manipulation. See https://apple-aiml-research.github.io/ml-amp/ for code and videos.

新论文 · v1arXiv:2611.26419

FEA solver integration of a composite World Model with a Spiking Neural Network memory Block for computationally efficient modelling of defects and variabilities

Bassam El Said, Adam Sobey

原文摘要

Each fibre-reinforced composite structure has a unique material architecture. The manufacturing methods used and the presence of defects lead to local variations which require material-scale models that can resolve the response in real time at every location in the structure. Concurrent multi-scale schemes provide this capability, but at a prohibitive computational cost for large structures as the number of integration points and time increments scales with size. Surrogates have been studied extensively as replacements for material-scale models to mitigate these computational limitations. A surrogate must represent an arbitrary local architecture including defects, track the irreversible material state over an unknown number of increments, remain stable when driven recursively by its own predictions, and fit within the memory available at every integration point. Here, a Composites World Model based on a Multi-Modal Spiking Transformer architecture is designed to meet these requirements. The proposed architecture combines a material encoder, a Spiking Neural Network memory block that tracks the long-term internal state of the material, and transformer blocks that learn the short-term applied strain state. The system is trained in three stages: material architecture encoding, base training on short time windows, and recursive fine-tuning with scheduled sampling to suppress cumulative error drift. The trained model is disassembled at inference and coupled to a non-linear FE solver, enabling structural scale simulation of composites containing embedded defects. Benchmarks against experimental results for IM7/8552 laminates under tension, compression and transverse shear, for pristine and wrinkled composites, show that the SNN memory block successfully tracks the material internal state and results in prediction errors between 0.4% and 4.8%.

cs.LG

版本更新 · v3arXiv:2606.00384

VESTA: Visual Exploration with Statistical Tool Agents

William Rudman, Abhishek Divekar, Kanishk Jain, Sebastian Joseph, Stella S. R. Offner, Matthew Lease, Kyle Mahowald, Greg Durrett 等 9 位作者

原文摘要

Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated. Recent agent-based systems leverage language and vision-language models (VLMs) to propose statistical models, but these systems struggle on challenging modeling tasks. To address these limitations, we introduce VESTA (Visual Exploration with Statistical Tool Agents), a framework that equips VLMs with a dynamically growing toolkit to guide model refinement through data transformations, hypothesis-driven visualizations, and statistical tests. Unlike prior systems that rely on iterative critique alone, VESTA explores data before and during refinement by selecting or creating reusable diagnostic tools. We evaluate VESTA using three toolkit configurations: no tools, static expert-written tools, and dynamic model-written tools. To support this evaluation, we introduce DAWN (Dataset for Automated Workflows and Numerical Modeling), a benchmark targeting distribution fitting and time series modeling with varying difficulty tiers that culminates in real-world astronomy tasks including modeling initial mass functions and gravitational-wave chirp signals. VESTA's dynamic tool creation outperforms prior agentic pipelines for statistical analysis and visual tool creation, with the largest gains on complex and domain-specific tasks. Against strong agentic coding harnesses (Claude Code, Codex, and OpenCode), VESTA is better on all time series tasks and on complex distribution fitting tasks, though the harnesses achieve better fits on simpler distributions. Further, dynamically generated tools are substantially more sophisticated than those produced by existing visual tool-creation systems, covering more diagnostic categories per function and strongly preferring visual outputs that the VESTA VLM critic can reason over directly.

cs.AI · cs.CL · cs.CV · cs.LG · stat.CO

新论文 · v1arXiv:2611.26187

Invertible Transport Between Sample-Only Distributions via Projected Characteristic Functions

Juan Gutiérrez, Victor Gutiérrez-García, José Luis Blanco-Murillo

原文摘要

Many useful latent distributions can be sampled but do not have a tractable density. Such distributions may be represented by empirical collections of real-world observations or generated by scientific simulators and black-box generative models. These sample-only priors cannot be used directly in likelihood-based normalizing flows, which require evaluating the prior density. We propose Projected Characteristic-Function matching (PCF), a density-free framework for learning an invertible map between a data distribution and a prior specified only through samples. Our method aligns distributions using projected empirical characteristic functions, eliminating the need for density estimation, adversarial training, or paired observations. To address the non-uniqueness of the transport map, we introduce an optional transport regularizer that selects lower-displacement transformations while preserving endpoint alignment. We benchmark PCF on controlled transports, sample-efficiency studies, and high-dimensional alignment tasks. PCF matches the accuracy of kernel MMD on the controlled benchmark and on raw-pixel MNIST--USPS at a cost linear in the batch size, and it is more sample-efficient, achieving lower endpoint error than MMD in 13 of 15 paired runs across library sizes. By avoiding pairwise kernel evaluation, it reduces discrepancy memory by 29.8% and trains at batch sizes where kernel MMD exceeds GPU memory. These results show that PCF provides accurate and efficient invertible transport, particularly in sample- and memory-limited settings.

cs.LG · cs.CV

新论文 · v1arXiv:2611.25989

Policy Improvement-Guided Replay for Continual Reinforcement Learning

Qin-Wen Luo, Haoxuan Gao, Sheng Ren, Xiang Chen, Sheng-Jun Huang

原文摘要

Continual reinforcement learning (CRL) requires models to acquire new capabilities while retaining performance on previous tasks. A stability-oriented perspective common in conventional continual learning emphasizes knowledge preservation and interference mitigation. Complementing this perspective, we revisit CRL for vision-language models through policy improvement, a fundamental principle of RL, to preserve acquired performance gains. Using the performance difference lemma, we characterize historical performance changes through the current policy's expected advantages on historical task distributions, motivating replay of historical prompts with the current policy. To allocate limited replay memory, we propose Contrastive Likelihood Replay (CoLiR), which contrasts likelihood gains on correct responses from the final task policy with likelihood reductions on incorrect responses from the initial policy. Our analysis links correct-response likelihood gains to reference-policy advantages under an idealized KL-regularized optimal update and provides an endogenous-reward interpretation for general policy updates. CoLiR estimates scores from finite training rollouts and cached log-likelihoods, selects prompts at task boundaries, and replays them uniformly during subsequent training, with KL regularization restricted to replayed prompts. Memory construction only requires a small amount of additional cross-policy scoring but no additional response generation. Across three Qwen3-VL model sizes on MRCL, CoLiR achieves the highest mean final accuracy and mean task accuracy among the compared methods while maintaining competitive new-task performance.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.25921

A Lightweight Hybrid Approach for Milling Force Reconstruction from Internal Machine Signals

Eric Hirsch, Christian Friedrich

原文摘要

Data-driven monitoring based on milling force can enable advanced manufacturing services including process optimization and condition monitoring. However, industrial implementation is often hindered by costly and intrusive hardware and large training data requirements. This paper therefore presents a hybrid approach using machine-internal signals and machining metadata to enable force-based monitoring on brownfield machines without additional sensors. Commonly available machine signals have relatively low sampling rates and cannot directly represent high-frequency milling-force variations, especially at higher spindle speeds. Instead of learning the complete force signal, which would increase model complexity, data requirements, and overfitting risk, a supervised machine-learning model predicts only the average milling force from selected machine-signal features and machining parameters. This low-frequency estimation parameterizes a static milling force model that reconstructs the force behavior over one spindle revolution. Although the static model does not reproduce all dynamic effects, it captures the force distribution, load levels, and angular regions of highest tool engagement. The approach is evaluated on one milling machine across varying process parameters, engagement conditions, cutting tools, and two workpiece materials. Dynamometer measurements are required only for development and validation. Ridge regression achieves an $R^2$ of $0.984$ and $0.991$ for average-force prediction on the test data ($\bar{F}_x$ and $\bar{F}_y$). The reconstructed force behavior over one spindle revolution achieves an $R^2$ of $0.962$ and $0.982$ ($F_x$ and $F_y$) compared with the reconstruction based on measured force features. The method provides a cost and computationally efficient basis for process monitoring, tool condition assessment, and process optimization on existing machines.

cs.LG

版本更新 · v2arXiv:2605.06404

FRInGe: Distribution-Space Integrated Gradients with Fisher--Rao Geometry

Gabriele Martino, Sebastian Tschiatschek

原文摘要

Although gradient-based attribution methods are model-faithful and scalable, a prominent variant, Integrated Gradients (IG), suffers from high sensitivity to design choices, particularly in baseline selection, path formulation, and discretization, as well as gradient saturation. To address these limitations, we propose Fisher--Rao Integrated Gradients (FRInGe), which defines both the reference and integration paths in the predictive distribution space. FRInGe replaces input baselines with a maximum-entropy predictive reference and follows a Fisher--Rao geodesic on the probability simplex. The corresponding input-space trajectory is realized through the pullback Fisher metric and stabilized by Kullback--Leibler (KL) and Euclidean trust regions; attributions are obtained by integrating input gradients along this trajectory. We further derive FRInGe-B, a variant that binarizes the predictive probability distribution, removing the computationally expensive Fisher products of FRInGe. Across six ImageNet architectures, FRInGe most clearly improves Magnitude Aligned Scoring (MAS), while remaining competitive on perturbation area-under-the-curve (AUC) metrics and infidelity.

cs.LG

版本更新 · v2arXiv:2610.32678

Probing the limits of materials design via a comprehensive crystal database of 14.6 million structures with 140 properties

Zhilong Song, Zijun Pang, Lixue Cheng

原文摘要

Forward screening and inverse design drive materials discovery, yet their limits remain unquantified because records of known crystal structures and properties are fragmented across databases. Consequently, forward screening leaves known crystals underexplored for new functions, whereas generative and autonomous discovery has repeatedly reported known phases or close variants as new materials. Here we match structures across 55 databases to assemble MateriaViva, a unified database of 14.6 million distinct crystals and over one billion property values. To provide the missing properties of every structure, a task we term property completion, we develop an equivariant Crystal Graph Transformer Network with state-of-the-art accuracy on nine benchmark tasks and apply 140 property-prediction models across the database. These predictions reveal the underestimated potential of forward screening, identifying tens of thousands of high-performance candidates among previously synthesized or computationally studied materials that lack recorded target-property values. Conversely, comparison with MateriaViva shows that the novelty of inverse design has been overestimated, as 55-100% of inverse-designed structures are not new. Under equal density functional theory verification budgets for bulk-modulus design, inverse design yields a higher fraction of qualifying candidates, whereas forward screening reaches the higher bulk modulus. MateriaViva thus provides a comprehensive reference for probing the limits of both paradigms, revealing unrecognized performance in known crystals and directing inverse design beyond reported structures.

cond-mat.mtrl-sci · cs.LG

新论文 · v1arXiv:2611.25780

RouteVerify: Routing Interventions for Step-Level Verification in Mixture-of-Experts Models

Yucheng Du, Ryan A. Rossi, Xiyang Hu

原文摘要

Routing states in mixture-of-experts (MoE) models can distinguish correct from erroneous reasoning steps. If changing routing also changes a model's step-level verification judgment, it is tempting to conclude that the judgment follows what routing encodes. We test this inference with RouteVerify, a controlled intervention study that replaces selected internal activations from one solution trace with activations from another, while keeping the evaluated input unchanged. Across nine MoE checkpoints, we compare three intervention interfaces: router logits, MoE outputs, and post-MoE residual states. We vary the layers and token positions at which activations are replaced. We measure changes in a verification margin that quantifies the model's preference for INCORRECT over CORRECT. We also evaluate the same input with activations from correct versus erroneous steps to test whether the resulting judgment depends on the source step's correctness. We report four linked results. First, probes on router logits separate correct from erroneous steps in eight checkpoints (AUROC 0.80-0.88). Second, replacing router logits across all routed layers changes the judgment in all nine checkpoints, and by more than a norm-matched random replacement. Third, this change rarely depends on whether the source step is correct. At one layer, routing from erroneous steps and from correct steps produces indistinguishable margins in all nine checkpoints. Under all-layer routing, their difference is resolved and positive in only one. Fourth, the same difference is positive for local residual replacements in eight of nine checkpoints, so the measure does detect such dependence where it exists. Correctness is therefore readable from routing, and routing replacements move the judgment, but the movement rarely follows correctness.

cs.LG · cs.CL

新论文 · v1arXiv:2611.25632

What One Sample Cannot See: Why Fewer Denoising Steps Can Score Higher on Physics Benchmarks

Yutao Li, Chen Wang

原文摘要

When a storm can head north or south, a forecast down the middle may score better under squared error than either plausible path. The same paradox appears when video generators are tested as world models: fewer denoising steps can raise physics scores even as videos blur or stop moving early. Why? Physics-IQ compares each generated video with one recording, although a scene can have multiple valid futures. An exact decomposition shows its scores can reward reduced variation among generated futures, even when their distribution becomes less accurate. We introduce Kernel Physics-IQ to remove this incentive in expectation, needing only two independent samples per condition. Two-step sampling lowers Kernel Physics-IQ in all five image-to-video models. For CogVideoX, the official score rises by 0.055 while ours falls by 0.131. Changing the sampling schedule reveals further differences official scores miss. In controlled physical systems with known outcome probabilities, our metric favors the true distribution over collapsed predictions. In short, a world model should be judged not only by how closely one video matches what happened, but by how faithfully its predictions represent what could have happened.

cs.CV · cs.LG

版本更新 · v3arXiv:2609.19513

QVAC Genesis III: A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language Model Pre-Training

Davide Vitabile, N. Ranjan, Akshay Nambiar, Kamal K. Gupta, Amril Nazir

原文摘要

High-quality pre-training data is a critical bottleneck for educational and STEM-specific language models targeting edge AI and on-device deployment where token budgets are tightly constrained. While major organizations train ever-larger models on private corpora, the open ecosystem lacks STEM-focused synthetic datasets that deliver high per-token learning value efficiently for small models. To address this gap, we introduce QVAC Genesis III, a 191.43B-token, STEM-focused multi-domain synthetic corpus covering 19 domains across several difficulty levels and different educational styles. QVAC Genesis III is built via a dual generation strategy that performs targeted teacher distillation using a weak edge-scale student model as signal: the student's failures are converted into corrective explanations, while its successes are expanded into contrastive option-level reasoning over all answer choices. We further introduce an LLM-as-a-parser evaluation protocol that extracts final answers from free-form outputs and tracks both accuracy and answer validity. To validate the effectiveness of our QVAC Genesis III data, we conduct controlled from-scratch ablations with 1.7B-parameter models, showing that models trained with QVAC Genesis III consistently outperform both models trained with the open-source synthetic corpus Cosmopedia-v2 and the publicly released Cosmo-1B model across ARC, GPQA Diamond, and MMLU STEM benchmarks, achieving up to +28.57% on ARC-E and +21.35% on ARC-C, while reaching a Valid Answer Rate of up to 99.45%.

cs.AI · cs.LG

版本更新 · v2arXiv:2606.04236

Supportive Token Revealing for Fast Diffusion Language Model Decoding

Giries Abu Ayoub, Mario Barbara, Lluís Pastor-Pérez, Tanja Bien, Aneesh Barthakur, Alaa Maalouf, Loay Mualem

原文摘要

Discrete diffusion language models can generate text efficiently by updating multiple masked positions in parallel, but this parallelism introduces a quality-latency trade-off. Aggressive decoding may commit mutually dependent tokens too early, while conservative decoding requires many denoising steps. Existing methods address this tension by deciding which tokens are safe to reveal using confidence or dependency criteria. However, avoiding unsafe commits does not necessarily make the remaining masked sequence easy to decode, since uncertain tokens may depend on masked tokens, creating a bottleneck for denoising steps. We propose AXON, a training-free module that can be added on top of existing parallel decoding strategies for diffusion language models. Rather than replacing the base decoder, AXON monitors the remaining uncertain masked tokens and intervenes only when their current state suggests that additional context is needed. It then shifts the criterion from which tokens are safest to reveal to which confident reveals would best support later denoising. AXON selects anchors, confident masked tokens that uncertain positions attend to, using attention, uncertainty, and confidence signals. Experiments on reasoning and code-generation benchmarks across multiple diffusion language models show that AXON improves the quality-latency trade-off of existing parallel decoders, often reducing the number of function evaluations while maintaining or improving accuracy.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.25452

FamilySpace: From Emergent Chemical Semantics to Controllable Crystal Generation

Haowei Hua, Irwin King, Wanyu Lin

原文摘要

Latent crystal generative models typically combine a variational autoencoder (VAE) for learning atom-wise representations with a flow model that transports a simple source distribution to the learned latent distribution. However, previous studies have mainly focused on the quality of generated crystals, leaving the structure and generative utility of the atom-wise latent space largely unexplored. In this work, we show that even a vanilla crystal VAE implicitly organizes atom-wise latent representations according to elemental families, with different families occupying largely separated regions of the latent space. We term this phenomenon emergent chemical semantics. This structure suggests that sampling from a family-specific latent region can bias the decoder toward atoms from the corresponding elemental family. Building on this insight, we propose FamilySpace, a framework for controlling the elemental-family composition of generated crystals. FamilySpace assigns each elemental family a distinct source component, forming a family-indexed multi-source distribution, and trains a flow model using source-target pairs matched by family. In inference, a user-specified family template selects the source component for each atom-wise representation, enabling direct control over the family composition of generated crystals. Experiments on MP-20 and MPTS-52 show that FamilySpace achieves competitive crystal-generation performance while matching prescribed elemental-family compositions. Moreover, selected family templates increase the fraction of generated crystals predicted to be stable or metastable, demonstrating that latent-space composition control can support targeted exploration of promising chemical regions without additional optimization techniques such as reinforcement learning. Code is available at https://github.com/hhw11/FamilySpace

cs.LG · cond-mat.mtrl-sci

新论文 · v1arXiv:2611.25422

From Sequence Uncertainty to Phenotype Hypotheses: Uncertainty-Conditioned Inference over Biomedical Knowledge Graphs

Huixin Zhan, Jason H. Moore

原文摘要

Genomic foundation models provide variant-level evidence, but connecting that evidence to phenotype hypotheses requires accounting for uncertainty throughout structured reasoning. We introduce an uncertainty-conditioned path-energy framework that converts sequence predictions and calibrated predictive uncertainty into explicit distributions over graph-supported phenotype hypotheses, without patient-level phenotype supervision. An interpretable learned energy scores admissible gene--disease--phenotype routes, query uncertainty controls the target temperature, and path probabilities are aggregated into phenotype hypotheses. This formulation makes evidence quality an explicit determinant of hypothesis breadth while retaining traceable multi-path support. Exact normalization over enumerable candidate sets provides a reference for evaluating a Hastings-corrected learned revision operator. On AlzKB and Hetionet, phenotype-level entropy tracks upstream uncertainty, with Spearman correlations of 0.951 and 0.878, respectively; ablations identify the contribution of uncertainty conditioning. In masked-edge recovery, the model exceeds chance and degree-matched probability-permutation controls. Training the energy under the uncertainty-dependent temperature yields higher held-out recall@10 than training under a constant temperature of comparable magnitude. Under gene hold-out, recall@10 exceeds that of a trained DistMult embedding on 24 of 30 graph masks (0.183 versus 0.123); this difference is attributable mainly to three genes with many variants and is not established for all genes. These results establish an uncertainty-aware interface from genomic predictions to graph-supported phenotype hypotheses that combines interpretable probability allocation with held-out association recovery of explicitly stated scope.

cs.LG · q-bio.GN

新论文 · v1arXiv:2611.25288

Intelligent Embedding Pruning for Large-Scale Recommendation Models

Anish Khazane, Alex Saad-Falcon, Guanchu Wu, Marcio Porto, Jasper Shan, Fei Yu, Eugene Shulga, Intaik Park 等 12 位作者

原文摘要

Modern recommendation systems face substantial memory pressure, largely from the sparse embedding layer that maps high-cardinality categorical features into dense vectors. In-training embedding pruning (ITEP) removes less important embedding rows during training, yielding end-to-end memory savings but sometimes degrading accuracy because per-table pruning ratios are set by size-based heuristics. We use feature importance (FI) to guide these ratios (FI-ITEP), assigning higher pruning to tables tied to less important features. Across three large-scale recommendation models, FI-ITEP achieves 20--40% total memory reduction while matching or improving accuracy relative to percentile-based ITEP. Because the feature-importance signal requires minimal resources to compute, these memory savings translate into concrete systems benefits: the same models train on fewer GPU trainers (e.g., 112 to 80) with higher per-GPU throughput, saving 1,000+ GPU-hours per model launch. We reproduce these trends on the open-source DLRM (Criteo 1TB) and quantify the end-to-end training-time and GPU-cost tradeoff---including the burden of computing FI---offering practical guidance for embedding pruning in real-world systems.

cs.LG · cs.AI

版本更新 · v2arXiv:2509.14167

Deconstructing Intraocular Pressure: A Non-Invasive Multi-Stage Probabilistic Inverse Framework

Md Rezwan Jaher, Abul Mukid Mohammad Mukaddes, A. B. M. Abdul Malek

原文摘要

We propose the mechanistically hierarchical inverse problem (MHIP) paradigm for biological transport systems, where a macroscopic observation emerges from the multiplicative entanglement of intrinsic micro-scale physics and latent macro-scale geometry. Without in vivo ground truth, solving MHIPs from clinical data is severely underdetermined. Standard statistical sampling degenerates along non-identifiable manifolds, while monolithic machine learning baselines collapse to an uninterpretable conditional mean. We propose a two-stage physics-guided decomposition that turns a globally non-identifiable inverse mapping into conditionally identifiable sub-problems. The first stage is a constrained inverse surrogate that isolates the intrinsic parameter under a fixed reference geometry. The second stage performs empirical structural calibration against population-level clinical data. We also introduce Physics-Calibrated Data Scaling (PCDS), a multi-fidelity strategy that builds large training sets from few high-fidelity simulations without patient-specific 3D modeling. In a glaucoma case study, the framework deconstructs a single intraocular pressure (IOP) measurement to estimate trabecular permeability ($\hat{K}_{TM}$) and conventional outflow facility ($\hat{C}_{trab}$). In retrospective validation against published in vivo data, the non-invasive $\hat{C}_{trab}$ estimates showed low bias against measured outflow facility. In an ablation over 27 clinical cohorts, naive monolithic baselines reach 37.0% diagnostic accuracy. Adding the isolated $\hat{K}_{TM}$ estimate raises this to 85.2%. The full two-stage framework reaches 88.9%. The framework also returns a probabilistic profile of the latent hydrodynamic state, offering a general computational blueprint for MHIPs.

cs.LG · q-bio.QM · stat.AP · stat.ME

新论文 · v1arXiv:2611.25141

CAIMS: Scalable Cross-Array In-Memory Search

Yi-Chun Liao, Liu Liu, Ruiyang Qin, Yiran Chen, X. Sharon Hu

原文摘要

Search, especially top-k similarity search, plays a vital role in many applications, but its performance can be severely limited by memory access overhead. In-memory search (IMS), an alternative to CPU/GPU-based approaches, exploits massive parallelism within a content-addressable memory (CAM) array to perform search in situ and provides both low latency and high energy efficiency. However, the capacity of a single CAM array is often insufficient for modern workloads, requiring data to be distributed across multiple arrays. Deploying scalable top-k similarity search across multiple CAM arrays poses a fundamental problem that existing designs fail to address: how to accurately and efficiently reduce local binary match results to global top-k results. This work introduces CAIMS, a cross-array IMS framework that is agnostic to memory technologies and applications, enabling scalable and efficient top-k similarity search while preserving accuracy. To enable accurate top-k result reduction, CAIMS leverages the existing threshold match functionality with a combined offline and online parameter selection approach to transform local binary match results that lack globally comparable similarity information into global coarse-grained similarity scores. To further improve efficiency, CAIMS conducts hierarchical reduction and transfers only the selection results and necessary control signals with lightweight local peripherals. Implemented on a 3D NAND Flash model and demonstrated using the retrieval phase of retrieval-augmented generation, CAIMS improves throughput by up to $22.3\times/10.1\times$ and energy efficiency by $426.6\times/23.7\times$ compared to the server-class CPU baseline and prior 3D NAND Flash accelerators, respectively, while maintaining comparable accuracy.

cs.AR · cs.ET · cs.LG

新论文 · v1arXiv:2611.24839

Kaer: Security-Aware Replanning for Multi-Agent Systems

Tushin Mallick, Evan Rose, Matthew Laws, Alina Oprea, Cristina Nita-Rotaru

原文摘要

One popular architecture for multi-agent systems (MAS) relies on an orchestrator that generates an initial plan, coordinates its execution, and dynamically revises the plan based on agent feedback when tasks cannot be fully specified in advance. This dynamic replanning introduces a critical vulnerability: malicious agents can embed instructions within their feedback to hijack the replanning process. Existing defenses focus exclusively on per-tool access control or static, pre-execution policy enforcement, leaving the replanning phase unsecured. We introduce Kaer, a multi-agent framework featuring security-aware replanning. Kaer shields the planner from untrusted agent feedback by conveying diagnostics to the replanning procedure strictly through abstract templates. Plan revisions are restricted to a set of deterministic repair operators, and all modified plans must satisfy preset policies. We create Cintra, a benchmark of simulated user tasks requiring replanning paired with adversarial objectives targeting the replanning phase. Using Cintra, we evaluate both task completion rates and system vulnerability to replanning exploits by malicious agents. Evaluating Kaer on Cintra against Magentic-One (an undefended MAS) and ControlValve (the state-of-the-art defense) demonstrates that Kaer achieves higher robustness than both systems while maintaining comparable utility to ControlValve. Although abstract failure templates slightly constrain utility on select tasks, Kaer enables MAS to perform secure, dynamic plan revisions without exposing the orchestrator to untrusted agent feedback.

cs.MA · cs.LG

版本更新 · v2arXiv:2610.40362HF 社区推荐

Your LR Schedule May Not Be Principled: Effective Learning Rate Scheduling in Weight-Normalized Training

Qifan Yu, Xinyu Ma, Xingyan Bin, Di He

原文摘要

Weight-normalized (WN) training is emerging as a compelling alternative to conventional weight decay (WD), with recent studies reporting substantial pretraining loss gains. We find that the effective learning rate (ELR) trajectory accounts for most of the loss dynamics difference between WN and WD. Matching blockwise ELR trajectories step by step closely aligns their loss curves. Schedule design should therefore target ELR rather than the nominal learning rate (LR). Building on this principle, we model directional-alignment dynamics under WN and derive $1/\sqrt{t}$ decay as the optimal schedule. For finite-horizon pretraining, we propose AIR (Affine Inverse-square-Root decay) to match prescribed peak and terminal LRs. Experiments on 128B- and 500B-token Mixture-of-Experts pretraining under WN show that AIR outperforms cosine and alternative schedules in loss, downstream performance, and hyperparameter robustness, reducing terminal training loss by 0.01 relative to cosine. We further identify late-stage scheduling as the primary source of this gain through controlled stage interventions, and demonstrate that a shared late schedule progressively attenuates alignment differences left by earlier LRs. Finally, transferring AIR's ELR trajectory to WD reproduces the same improved loss dynamics, demonstrating that these gains come from ELR scheduling itself and extend beyond fixed-norm training.

cs.LG

版本更新 · v2arXiv:2609.27917

When Does Reallocating a Sampling Budget Pay? Instance-wise Allocation for Neural Routing Solvers

Jinhyung Bae

原文摘要

Neural routing solvers sample many solutions per instance and keep the best, with the same number of samples for every instance. We measure how much a non-uniform split of the same total budget is worth and which property of a workload decides it. Best-of-k curves estimated by averaging random orderings of stored samples overstate the gain, and deciding on one half of the samples while evaluating on the other understates it; we use exact best-of-k curves, a U-statistic over all orderings. For three pretrained solvers (POMO, the Attention Model and Sym-NCO) on the traveling salesman problem, reallocation reduces the total optimality gap by at most 2.5% on the training distribution, so uniform allocation is close to optimal there. On workloads that mix in out-of-distribution instances it reduces the gap by 11.8-13.3% (1.1-1.8% of tour length) for the two solvers that degrade under the shift, and almost nothing for the one that does not. Across two heterogeneity mechanisms, three solvers, two confirmation collections and budgets of 25 to 200 samples per instance, the gain is predicted by the spread of difficulty within a workload, not its average. Allocating on a power-law curve fitted to twenty charged probe samples per instance recovers 88-93% of the uncharged optimum; successive halving does worse. A 2-opt local search, however, removes most of the gap at negligible cost, after which reallocation adds a few hundredths of a percent of tour length.

cs.LG · cs.AI · math.OC

新论文 · v1arXiv:2611.24619

GateWatch: Low-Overhead LLM Monitoring with Boolean Circuits

Firas Spanioli, Yaniv David

原文摘要

As large language models (LLMs) and LLM-based agents are increasingly deployed, monitoring their behavior becomes important for detecting unsafe or unintended actions. Activation probes offer an efficient approach, but existing methods face trade-offs between accuracy, interpretability, and computational overhead. Probes on raw activations lack interpretable inputs, whereas sparse autoencoder (SAE) probes use interpretable features but often rely on additive classifiers and large SAE encoders, limiting interpretability and increasing memory overhead. We introduce GateWatch, a compact, interpretable classifier that expresses its entire decision rule as an explicit Boolean logic over a small number of binarized SAE features. We explore three approaches to constructing these circuits under a specified gate budget. For efficient deployment, GateWatchServe computes only selected SAE features, enables streaming of their binary values across layers during inference, and evaluates multiple GateWatch classifiers in parallel using compact lookup tables. Across 24 tasks on Gemma-2-9B, GateWatch achieves 80.49% mean test accuracy using only 3.8 SAE features and 3.5 logic gates per probe on average, just 1.17 percentage points below full 16K-feature SAE probes, while matching or outperforming them on 10 tasks and reducing probe memory by 99.98%. Inside vLLM, 1,000 concurrent multi-layer, multi-token GateWatch classifiers retain 97-98% of baseline throughput and 99.8% of KV-cache capacity.

cs.AI · cs.LG

版本更新 · v2arXiv:2610.01269

IQS-BO: In-Context Query Selection for Bayesian Optimisation

Luca Geminiani, Nadja Klein

原文摘要

Bayesian Optimisation (BO) is a powerful framework for optimising expensive black-box functions, but typically requires refitting a surrogate and maximising an acquisition function at every evaluation. In-context approaches based on Prior-data Fitted Networks (PFNs) amortise part of this cost by pre-training transformers on functions drawn from synthetic priors. PFNS4BO amortises the surrogate but still relies on a numerically maximised acquisition function, while FIBO performs BO fully in-context by sampling optimiser locations from a learned density, which fixes the decision rule and admits no surrogate. Learned acquisition functions score a finite candidate set with a network, but, lacking a label for the query, learn the score by reinforcement learning. We propose IQS-BO, a PFN that learns the query decision by supervised learning on synthetic priors. In a single forward pass, IQS-BO predicts the probability that each candidate is the best in the set, and we show that training minimises its expected KL divergence to the posterior probability of this event. The model can be pre-trained without a surrogate for fully in-context BO, or take the predictions of a fixed probabilistic surrogate as additional input, amortising only the decision step. Our method proposes queries at a fraction of the cost of acquisition-based methods, while matching or outperforming BO with Gaussian processes (GPs) and available in-context methods in sequential and batch optimisation, in low and high dimensions. Finally, we propose a mixture prior for pre-training PFNs which combines samples from GPs with functions exhibiting warped inputs, narrow optima, or plateaus that are poorly modelled by stationary GP kernels. We show that pre-training on this prior can improve performance and help the network generalise to a broader range of optimisation problems.

cs.LG · stat.ML

新论文 · v1arXiv:2611.24325

Structure-Preserving Neural Approximation of Convex, Semiconvex, and Quasiconvex Functions

Yeachan Park, Yeoneung Kim

原文摘要

Input convex neural networks provide a natural way to enforce convexity globally through architectural constraints. We study how this structure-preserving approximation framework extends to semiconvex, quasiconvex, and convex transformable functions. For $C^{1,1}$ convex functions on compact convex domains, we establish the sharp $W^{1,p}$ minimax rate $m^{-1/d}$ under max-affine approximation with $m$ affine pieces, and show that every max-affine function admits an exact bounded-width ICNN representation with complexity linear in $m$. The same $W^{1,p}$ approximation rate extends to semiconvex functions through quadratic lifting and to convex transformable functions through monotone composition. For general Lipschitz quasiconvex functions, we develop a quantitative finite-probe approximation theory based on monotone responses to affine projections and obtain a structure-preserving IqCNN with an $L^\infty$ approximation guarantee. We further show that these approximation results extend to ReLU-transferable smooth activations, including Softplus and ELU. Numerical experiments on PDE-based approximation problems compare the proposed architectures with parameter-matched MLPs and validation-tuned shape penalties, demonstrating global structural validity without penalty tuning while maintaining competitive approximation accuracy. Overall, the results identify recoverable convex latent structure as the key mechanism enabling gradient-level structure-preserving approximation beyond convexity.

cs.LG · math.OC

版本更新 · v4arXiv:2602.11776

MUSE: Multi-Tenant Model Serving With Seamless Model Updates

Cláudio Correia, Alberto E. A. Ferreira, Lucas Martins, Miguel P. Bento, Sofia Guerreiro, Ricardo Ribeiro Pereira, Ana Sofia Gomes, Jacopo Bono 等 10 位作者

原文摘要

In binary classification systems, decision thresholds translate model scores into actions. Choosing suitable thresholds relies on the specific distribution of the underlying model scores but also on the specific business decisions of each client using that model. However, retraining models inevitably shifts score distributions, invalidating existing thresholds. In multi-tenant Score-as-a-Service environments, where decision boundaries reside in client-managed infrastructure, this creates a severe bottleneck: recalibration requires coordinating threshold updates across hundreds of clients, consuming excessive human hours and leading to model stagnation. We introduce MUSE, a model serving framework that enables seamless model updates by decoupling model scores from client decision boundaries. Designed for multi-tenancy, MUSE optimizes infrastructure re-use by sharing models via dynamic intent-based routing, combined with a two-level score transformation that maps model outputs to a stable, reference distribution. Deployed at scale by Feedzai, MUSE processes over 4 thousand events per second, and over 55 billion events in the last 12 months, across several dozens of tenants, while maintaining high-availability and low-latency guarantees. By reducing model lead time from weeks to minutes, MUSE promotes model resilience against shifting attacks, saving millions of dollars in fraud losses and operational costs.

cs.LG · cs.DC

新论文 · v1arXiv:2611.24166

SoU-RHS: Bayesian Structured Sparsity for Compact Architecture Recovery in CNNs

Rafael Mouallem Rosa, Julyan Arbel

原文摘要

Highly parameterized convolutional neural networks often achieve strong predictive performance, but their memory, computation, and deployment costs motivate the search for methods that recover compact architectures from large reference models. We propose SoU-RHS, a Bayesian structured-sparsity procedure that augments Regularized Horseshoe Shrinkage (RHS) with the so-called Sources of Uncertainty Sparse Global-Local mechanism (SoU-SGL). The resulting model sharpens the separation between active and inactive filters, providing an effective mechanism for architecture recovery. A key property of SoU-RHS is stability: across different overparameterized starting widths and under a reasonable range of pruning thresholds, it recovers compact architectures with similar total size and layer-wise allocation. This supports the interpretation that the procedure is identifying a compact structure adapted to the data, rather than merely compressing each initial model separately. Across standard image-classification benchmarks, SoU-RHS recovers substantially smaller architectures than deterministic structured-sparsity baselines, while maintaining competitive accuracy, achieving lower negative log-likelihood in every evaluated configuration and generally lower expected calibration error.

cs.LG · stat.ML

新论文 · v1arXiv:2611.24113

AG-BFGS: Foundations for Accelerated Geometry Learning

Regina Carla Sousa, Denis Vargas, Elizabeth Wanner, Joshua Knowles

原文摘要

We introduce an accelerated geometry-learning framework for BFGS that incorporates momentum into the learning of Hessian inverse approximations. We prove that the resulting accelerated updates satisfy explicit stability conditions and preserve positive definiteness within admissible parameter regions. Numerical experiments demonstrate consistent improvements over the corresponding non-accelerated schemes while maintaining numerical stability. These results provide the first rigorous theoretical foundation for accelerated quasi-Newton learning and bridge the gap between empirical observations and mathematical guarantees for accelerated second-order methods.

math.OC · cs.LG · cs.NE · math.NA

版本更新 · v2arXiv:2611.23076

Pareto-Informed Smart "Predict, then Optimize" for Multi-Objective Combinatorial Problems

Aabhash Dhakal, Tim Lachner

原文摘要

Many real-world planning applications, from logistics, routing to resource allocation, give rise to optimization problems that need to balance multiple, conflicting objectives. While machine learning is often used to predict the unknown parameters or costs of these problems, standard models trained on prediction accuracy can lead to suboptimal plans. Decision-Focused Learning (DFL) addresses this by integrating the downstream optimization task into the training objective. However, existing DFL methods for multi-objective problems rely on simple scalarization, which fails to capture the rich trade-offs of the Pareto Frontier. To address this gap, we propose a Pareto-aware extension to single-objective Smart "Predict, then Optimize" (SPO+) for multi-objective combinatorial optimization problems. Our loss function leverages the true Pareto Frontier, forming a target decision that aligns with a sampled preference vector, and minimizes regret against this target. Experiments on multi-objective shortest path and multi-objective knapsack problems show that our approach outperforms traditional two-stage Mean Squared Error (MSE) baselines. It also surpasses scalarization-based SPO+ approaches.

cs.LG

新论文 · v1arXiv:2611.24028

Algorithmic Market Making Can Lead to Rough Volatility Through the Order Book

Sai Niranjan Ramachandran

原文摘要

Existing work suggests that markets can show volatility with paths rougher than those of Brownian motion. In theory this can happen when the order flow is close to instability with memory that decays as a power law. However, it is not fully clear how such order flow could arise from the predominantly algorithmic market making that characterizes order book dynamics. We show one such consistent mechanism. We treat each market maker as a desk that uses a first-order gradient rule to move the distances of its orders from the mid price toward target distances provided by an unknown oracle. We assume that distinct desks do not act synchronously in time but act whenever new information relevant to their respective oracles arrives, which each desk samples over its own characteristic lookback horizon. Across all desks the rule therefore takes the form of stochastic gradient descent (SGD) with information-driven (mini-batch) noise. In the continuum limit this update rule makes the volume of the order book follow a conservative stochastic partial differential equation (the Dean--Kawasaki equation) whose fluctuations drive the order flow. The distinct horizons of the desks further induce a persistent memory in the order flow that decays as a power law. Standard scaling arguments then lead to rough volatility. We confirm the key predictions of the model on simulated agents and on six months of Binance data with about 790 million orders. In liquid markets governed mainly by market makers, such as the perpetual futures of Binance, the order books are consistent with how our desks change the book.

cs.LG · q-fin.MF · q-fin.TR