跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1085新增论文
+884其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 06:59各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 08:51 — 2026-11-19 08:51(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:2026-11-19 06:59最近发现新增版本:2026-11-19 06:59库内论文最新更新时间:2026-11-18 08:00

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

26,871 已收录论文22,375 AI 相关8,156 有修订112 HF 社区发现

论文修订列表

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 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v2arXiv:2606.14536

可证明安全且可扩展的强化学习

Provably Safe, Yet Scalable Reinforcement Learning

Kai S. Yun, Zeyang Li, Navid Azizan

AI 速读 基于摘要

提出两阶段框架 PS2-RL,用学习到的备份策略在线隐式构造控制不变集,从而在保持可证明安全性的同时提升可扩展性。

cs.LG · cs.RO · eess.SY

查看原文摘要

Safe reinforcement learning (RL) aims to learn policies that optimize rewards while satisfying constraints. Predominant approaches rely on soft-constrained policy optimization, which has achieved empirical success but does not provide formal safety guarantees for the learned policy. In contrast, methods with strict guarantees typically rely on explicit certificate functions, whose construction requires the direct synthesis and verification of control-invariant sets, a process that scales poorly with state dimension and often yields overly conservative behavior. In this paper, we present the Provably Safe, yet Scalable RL (PS2-RL) framework, a novel two-phase architecture for learning provably safe policies in a scalable manner, designed to overcome the key bottlenecks of prior methods. Rather than explicitly computing invariant sets, PS2-RL leverages a learned backup policy to forward-integrate the system dynamics, generating an implicit control-invariant set online. In the first phase, the backup policy is trained with the safe-arrival value function to achieve rapid, safe recovery to the certified base set for invariant-set construction. In the second phase, an RL policy is trained end-to-end through a differentiable projection layer that strictly enforces the safety guarantees induced by the learned backup policy. By maximizing the volume of the implicit control-invariant set in the first phase, the resulting PS2 policy from the second phase is performant and scalable, while maintaining provable safety. Crucially, PS2-RL imposes no restrictions on the underlying RL algorithm and can be plugged into any existing training pipeline. We establish theoretical guarantees for the proposed framework and evaluate it on robotic control tasks with state dimensions up to 10, a regime in which prior provably safe RL methods struggle or become impractical.

版本更新 · v2arXiv:2611.01466

Resolve, Clear, or Defer: Training-Free Active Prototype Triage for Ecological Detection Pipelines

Anirudh Potlapally, Brijesh Nanda Brunda Yogananda, Jianyang Gu, Maanav Jajodia, Luke Meyers, Wei-Lun Chao, Hari Subramoni

原文摘要

Ecological monitoring increasingly relies on camera traps and aerial surveys that generate large image collections. High-recall animal detectors can localize candidate animals at scale. However, they also produce many detections that still require expert review, including false positives, ambiguous cases, and animals difficult to identify at the species level. Since exhaustive review requires substantial effort, we propose training-free active prototype triage, where reviewed detections become reusable evidence to (1) Resolve supported foreground classes, (2) Clear likely background false positives, or (3) Defer insufficiently supported cases for expert review. Across camera-trap and aerial datasets, foreground recognition and false-positive rejection benefit from different pretrained representations: BioCLIP2 provides foreground evidence while DINOv3 provides background evidence, reducing erroneous foreground clearing while improving automatic foreground recovery. Deferring unsupported cases avoids the higher error rates caused by forced decisions. Compared with confidence-thresholded multiclass k-NN and uncertainty-sampling logistic regression, prototype triage improves foreground recovery while maintaining competitive or lower review burden. Acquisition goes beyond class discovery: even after classes are represented, prototype choice determines how reliably evidence propagates through the remaining detections. Our results suggest that once animal localization reaches high recall, the challenge shifts from finding animals to deciding which examples to review, how to reuse them, and when evidence does not support an automatic decision.

cs.CV

版本更新 · v2arXiv:2610.42002

GeoFlip 预览:视频生成中几何敏感物理的基准评测

GeoFlip Preview: Benchmarking Geometry-Sensitive Physics in Video Generation

Yuqi Li, Junming Liu, Bowen Hu, Ruize Niu, Huiran Duan, Ming-Hsuan Yang, Yingli Tian, Hao Wu

AI 速读 基于摘要

GeoFlip 是一个通过受控几何干预构造配对场景、检验图生视频模型能否把首帧几何差异转化为正确物理演化的基准。

cs.CV

查看原文摘要

Video generation models synthesize realistic motion, but can they respond correctly to changes in initial geometry? We introduce GeoFlip, a video generation benchmark centered on physical outcome flips induced by geometry. With shared physical settings and textual prompts held fixed, GeoFlip applies controlled interventions to support extent, object placement, and mechanism configuration, constructing paired scenes with contrasting reference events, such as remaining stable versus falling or tipping. These pairs test whether models translate geometric differences in the first frame into correct physical evolution. The benchmark comprises 482 scene pairs and 964 reference videos across six physical categories, with reference outcomes established through procedural scene construction, physics simulation, and numerical validation and verification of physical events. We evaluate 16 models for image to video generation along three dimensions: event correctness, structural integrity, and similarity to reference videos. We examine evaluation consistency with independent vision language judges. On the 442 conditions shared by all models, the highest event correctness averaged across tasks is 27.98%, revealing substantial limitations in physical generation conditioned on geometry. Model strengths vary across physical mechanisms, and the three evaluation dimensions capture distinct capabilities. Typical failures include ignoring geometric changes, generating incorrect object motion, bending rigid objects, and introducing additional components. Rank correlations between judges reach 0.906 for event correctness and 0.929 for structural integrity. By combining controlled geometric interventions, verifiable physical references, and multidimensional evaluation, GeoFlip assesses progress from visual realism toward physical consistency conditioned on geometry.

版本更新 · v2arXiv:2611.05244

表达性集群机器人中的现实差距与感知差距

Reality and Perceptual Gaps in Expressive Swarm Robotics

Ali Imran, Abdalwhab Bakheet Mohammed Abdalwhab, Rafael Gomes Braga, Hélène Duval, Audrey Rochette, Vivek Shankar Varadharajan, Yann Bouteiller, Jean Mazerolle 等 10 位作者

AI 速读 基于摘要

同一套去中心化协调代码在三类机器人集群上现场演出时,作者报告硬件实现会显著改变可见运动,且观众的意义归因与情绪反应并不一致。

cs.RO

查看原文摘要

Moving robot swarms from simulation into the physical world can be difficult because small discrepancies in hardware, timing and communication can cascade across interacting robots and alter group behaviour. This challenge is known as the reality gap. When swarms operate in human environments, a second challenge emerges: a perceptual gap between what the swarm physically does and what human onlookers actually perceive. This study examines the same decentralised coordination code deployed across three robotic swarms-tabletop, aerial and human-scale mobile manipulators-during live artistic performances. We find that while the underlying algorithms executed reliably on all three platforms, physical embodiment drastically altered visible motion-distorting execution timescales by more than a factor of three and reshaping trajectory geometry. More importantly, audience surveys revealed that human interpretation does not mirror technical success: how observers attribute meaning (perceived purpose) and how they react emotionally (comfort versus threat) depend heavily on physical form. Meaning attribution and emotional responses did not vary together. Our results demonstrate that successfully transferring swarm software to physical hardware is insufficient for real-world deployment. Addressing the reality gap does not guarantee that the resulting collective motion will be readily interpreted by human observers. Swarms destined for human environments must be engineered not only for decentralised stability but also for the expressive physical dynamics through which humans interpret collective motion.

版本更新 · v2arXiv:2605.13740

利用语言模型先验从观测中学习POMDP世界模型

Learning POMDP World Models from Observations with Language-Model Priors

Valentin Six, Frederik Panse, Mathis Fajeau, Lancelot Da Costa, Mridul Sharma, Alfonso Amayuelas, Tim Z. Xiao, David Hyland 等 10 位作者

AI 速读 基于摘要

提出Pinductor,用大语言模型从少量观测-动作轨迹中提出并迭代精炼POMDP候选模型,以信念似然为目标,从而减少环境交互。

cs.LG

查看原文摘要

Whether navigating a building, operating a robot, or playing a game, an agent that acts effectively in an environment must first learn an internal model of how that environment works. Partially-observable Markov decision processes (POMDPs) provide a flexible modeling class for such internal world models, but learning them from observation-action trajectories alone is challenging and typically requires extensive environment interaction. We ask whether language-model priors can reduce costly interaction by leveraging prior knowledge, and introduce Pinductor (POMDP-inductor): an LLM proposes candidate POMDP models from a few observation-action trajectories and iteratively refines them to optimize a belief-based likelihood score. Despite relying on strictly less information, Pinductor achieves comparable performance and sample efficiency to LLM-based POMDP learning methods with privileged access to hidden states. Moreover, it is up to 330 times more sample-efficient than standard POMDP baselines such as DreamerV3, at comparable computational cost. Further results show that performance scales with LLM capability and degrades gracefully as semantic information about the environment is withheld. Together, these results position language-model priors as a practical tool for sample-efficient world-model learning under partial observability, and a step toward generalist agents in real-world environments. Code: https://github.com/atomresearch/pinductor.

版本更新 · v2arXiv:2611.05266

在智能体强化学习中稳定化同策略定向引导

Stabilizing On-Policy Targeted Guidance in Agentic Reinforcement Learning

Kevin Frans, Alexander M Rush, Sergey Levine, Pieter Abbeel, Ashvin Nair

AI 速读 基于摘要

作者提出并分析“定向引导”框架,通过同策略自蒸馏从逐轮文本反馈中学习,并在智能体多轮软件工程环境中探索如何稳定训练且不损害基线RL性能。

cs.LG

查看原文摘要

Naive on-policy RL is often bottlenecked by the capabilities of the base model --- insufficient coverage can result in an inability to learn from certain rewards. At the same time, rewards in modern post-training systems often come from rich textual sources, e.g. judge models with a rubric of criteria. Can we utilize such structures to provide a rich directional signal that enables improving on otherwise difficult to optimize rewards? In this work, we examine a framework we refer to as targeted guidance that learns from per-turn textual feedback via an on-policy self-distillation objective. Our focus is not only on directly improving hard-to-optimize behaviors, but on how to do so throughout the training process without degrading baseline RL performance. Over a range of settings across an agentic multi-turn software engineering environment, we find success by combining targeted self-distillation with a per-criteria RL reward, and by limiting feedback to turns where the policy specifically fails. We further examine the design choices that lead to stable entropy and reduce oscillatory behavior throughout training.

版本更新 · v2arXiv:2609.02459

CivBench:面向《文明VI》中工具中介智能体的长时程基准

CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI

Austin Tudor David Andrews, Liam Wilkinson, Jamie Heagerty, Harry Coppock, Jakob Nicolaus Foerster, Rui Ponte Costa

AI 速读 基于摘要

作者提出开源基准 CivBench,通过 MCP 在《文明VI》中评测语言模型智能体的长时程、工具中介行为,并提出 PMR 与 RAG@10 两个接口级指标。

cs.AI

查看原文摘要

We present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context Protocol (MCP). A single episode can span over 300 turns and produces thousands of tool calls over a large action space, requiring sustained planning, state monitoring, and execution under partial observability. The environment exposes 76 MCP tools and a deterministic narration layer that retrieves and formats game state as structured text. We use CivBench to characterise agent behaviour across four model families in 23 admissible runs. The sample is a pilot, not a model ranking: aggregate outcomes do not reliably discriminate models at this scale. Instead, we introduce two interface-level metrics that the environment makes measurable: Proactive Monitoring Rate (PMR), capturing whether agents actively query latent strategic state, and RAG@10, capturing whether commitments stated in structured planning reflections are executed within ten subsequent turns. Across runs we observe two consistent patterns under a shared playbook protocol. Agents under-monitor strategically relevant state that is available but requires explicit querying: despite playbook guidance to query victory progress every 20 turns, agents do so only every 30-75 turns, and in 8 of 20 detectable defeats they failed to query within the 20-turn warning window before game end. Agents also frequently fail to execute near-term commitments stated in their own planning reflections (RAG@10 between 48.2% and 65.8% across models). Both patterns arise despite tool access and explicit guidance, and we interpret them as deviations under instruction rather than absences of capability. We release the environment, scenarios, logs, metrics, and analysis pipeline at https://github.com/lmwilki/civ6-mcp.

版本更新 · v2arXiv:2510.05849

ESS-Flow:源空间中将免训练引导作为贝叶斯推断

ESS-Flow: Training-free guidance as Bayesian inference in source space

Adhithyan Kalaivanan, Zheng Zhao, Jens Sjölund, Fredrik Lindsten

AI 速读 基于摘要

ESS-Flow 利用流模型源分布的高斯先验,在源空间用椭圆切片采样做无梯度贝叶斯推断,实现预训练流模型的条件生成。

cs.LG · stat.ML

查看原文摘要

Guiding pretrained flow-based generative models for conditional generation or to produce samples with desired target properties enables solving diverse tasks without retraining on paired data. We present ESS-Flow, a gradient-free method that leverages the Gaussian prior of the source distribution in flow-based models to perform Bayesian inference directly in the source space using elliptical slice sampling. ESS-Flow only requires forward passes through the generative model and observation process, making it applicable even when gradients are unavailable, such as with non-differentiable simulation-based observations or quantization in the generation process. We demonstrate its effectiveness on scientific applications including generating materials with target properties, protein backbone structures with improved designability, and synthesizable, drug-like molecules.

版本更新 · v3arXiv:2606.27571

Kimball 数据仓库架构:评估一致性数据(Conformed Data)相对于 Inmon 模型的挑战

Kimball's Data Warehouse Architecture: Evaluating the Challenges of Conformed Data against the Inmon Model

Júlio Rocha, Salviano Soares, António Valente

AI 速读 基于摘要

该文围绕 Kimball 以一致性维度为核心的数据总线架构与 Inmon 的 hub-and-spoke 架构展开比较,重点讨论一致性数据面临的挑战。

cs.DB

查看原文摘要

In recent decades, driven by rapid data growth, organisations have faced the need to restructure their storage frameworks to efficiently handle queries requested by employees through available enterprise applications. Investigating this need involves examining the classic approaches of William H. Inmon, widely known as the father of Data Warehousing, and Ralph Kimball. Although both shared the same core concerns, Kimball later suggested an alternative architecture focused primarily on user needs. According to Ariyachandra and Watson, Inmon's "hub-and-spoke" architecture and Kimball's data bus framework featuring conformed dimensions stand out among alternative approaches. A comparison across these architectures highlights four key aspects: Information Quality, System Quality, Individual Impacts, and Organisational Impacts. Although Kimball and Inmon proposed contrasting solutions, they did not view each other as rivals. For instance, in one of the editions of the book "The Data Warehouse Toolkit", published by Kimball in 1996, the back cover features a note by Inmon stating that it is "one of the definitive books of our industry. If you take time to read only one professional book, make it this book.

版本更新 · v3arXiv:2610.20277

TANGO: RNA Topology and Geometry Co-Design

Tianmeng Hu, Biao Luo, Ke Li

原文摘要

Designing RNA sequences that satisfy target tertiary-structure objectives is an important problem in RNA engineering, with broad applications in synthetic biology and therapeutics. Existing 3D RNA design methods have made substantial progress, but they largely treat the target fold as a geometry-only objective. This is incomplete for RNA, whose functional folds are specified not only by tertiary geometry but also by secondary base-pairing topology. We therefore formulate RNA inverse design as a topology-and-geometry co-design problem and propose TANGO, a multi-objective multi-agent reinforcement learning framework for this task. TANGO adopts a staged curriculum: it first learns a topology-aware policy from secondary-structure targets, then transfers this policy to tertiary-structure targets to train a general co-design model, and finally applies frontier-guided fine-tuning to refine target-specific trade-offs among secondary-structure fidelity, tertiary-structure fidelity, and sequence diversity. Experiments show that TANGO generates diverse and novel designs, improving tertiary- and secondary-structure performance by 18.3% and 52.7%, respectively, over the strongest baseline.

cs.LG · cs.MA

版本更新 · v2arXiv:2605.16789

轨迹感知缓存加速整流流模型

Accelerating Rectified Flow Models via Trajectory-Aware Caching

Xiao Liu, Kai Liu, Naiyang Guan, Hongliang Lu, Zhixin Wang, Zhikai Chen, Renjing Pei, Yulun Zhang

AI 速读 基于摘要

TACache 提出免训练的“先跳步后补偿”缓存框架,通过沿整流流轨迹分解速度加速度来减少误差,从而加速扩散与整流流模型的采样。

cs.CV

查看原文摘要

Diffusion and rectified flow (RF) models generate high-fidelity images and videos, but their iterative velocity-field evaluations are computationally expensive. Existing caching methods accelerate sampling by skipping timesteps, yet their coarse approximations introduce accumulated errors over long skip intervals and degrade quality under aggressive acceleration. We propose TACache (Trajectory-Aware Cache), a training-free acceleration framework following a skip-then-compensate paradigm. TACache performs an orthogonal decomposition of discrete velocity acceleration along the RF trajectory into a parallel component and an orthogonal residual, isolating the magnitude and directional sources of per-step approximation error. The framework operates in two stages: offline, cumulative variation thresholds on the magnitude and direction indicators yield the skip schedule and bound how far each skip interval may extend; online, at each skipped step the offline statistics are combined with the sample's historical orthogonal direction to reconstruct the skipped velocity without additional model evaluations. Main comparisons on BAGEL, FLUX.1-dev, and Wan2.1-1.3B show that TACache achieves up to $4.11\times$ speedup on text-to-image generation and $2.11\times$ speedup on text-to-video generation, with consistent improvements over prior cache-based methods on most quality metrics. Our code is available at https://github.com/XiaoLiu1237/TACache.

版本更新 · v2arXiv:2611.05048

图相似性与最优传输

Graph Similarity Meets Optimal Transport

Jens Breitung, Timo Gervens, Martin Grohe

AI 速读 基于摘要

该论文研究用最优传输松弛双射对齐来定义图距离时,最优传输版本与双射版本之间的整性间隙,并给出若干距离的上下界与计算复杂性结果。

cs.DM

查看原文摘要

A natural way to compare two graphs is to align their vertex sets by a bijection and to measure the difference of the aligned adjacency matrices in a matrix norm. Depending on the norm, this yields, for example, the edit distance, the cut distance, the spectral distance, and the local edit distance. To make these distances applicable to graphs of different order, one can consider blowups of the graphs or, equivalently, relax bijections to fractional alignments, that is, optimal transport plans between the uniform distributions on the vertex sets, in the spirit of Gromov-Wasserstein distances. We investigate how much the optimal transport versions can differ from their bijective counterparts, that is, we quantify their integrality gaps. For the edit distance, we improve the best known upper bound on the integrality gap from 3 to 2 and the lower bound from 6/5 to 4/3. For the cut distance, we approach Lovász's conjecture that $δ_\square \le 2δ_\square^{\rm OT}$ from both sides. We improve the previously best known upper bound $δ_\square \le 32 \cdot (δ_\square^{\rm OT})^{1/67}$ (Borgs, Chayes, Lovász, Sós and Vesztergombi, Adv. Math. 2008) to $δ_\square \le C_\varepsilon \cdot (δ_\square^{\rm OT})^{1-\varepsilon}$ for every $\varepsilon > 0$, and we construct graphs $G,H$ with $δ_\square(G,H) = 2δ_\square^{\rm OT}(G,H)$, establishing a factor-2 lower bound that matches Lovász's conjecture. For the local edit and spectral distances, we obtain upper bounds of order $\sqrt{t\ln(1/t)}$ and $\sqrt{t}$, respectively, where $t$ is the corresponding optimal transport distance, and we show that, unlike for the edit and cut distances, no linear upper bounds are possible. Finally, we show that computing the optimal transport distances is NP-hard, and we give hardness of approximation results for the cut, spectral, and local edit distances.

版本更新 · v2arXiv:2603.16482

Cue-guided dual-path reconstruction with adaptive multi-scale response refinement for low-light image enhancement

Yicui Shi, Yuhan Chen, Xiangfei Huang, Zhenguo Wang, Wenxuan Yu, Ying Fang, Jie Li, Guofa Li

原文摘要

Low-light image enhancement (LLIE) supports optical sensing and scene observation when limited photon capture and sensor noise degrade image quality. However, existing methods can introduce colour deviations or blur local details in the enhanced images. To address this challenge, we propose CueDR-Net, a dual-path network that combines brightness adjustment with local content reconstruction through bidirectional cue interaction and adaptive multi-scale refinement. Specifically, a fixed extractor derives luminance variation, colour, and texture cue maps from the input image. These maps are encoded in a cue stream that exchanges features with the image stream through bidirectional attention. The exchanged features support two paths for brightness adjustment and local content reconstruction. The brightness adjustment path predicts pixel wise adjustment maps that control iterative intensity changes in the input image. In parallel, the residual path uses the exchanged features to predict an additive correction for local content reconstruction. To capture weak structures across scales, Adaptive Multi-Scale Response Refinement Convolution (AMRRConv) refines the features used for both predictions. It fuses learnable local transition responses with multi-scale features from factorized three-plane filtering using pixel wise weights. The adjusted image is added to the correction before being mapped to the enhanced image. Evaluations on LOLv1, LSRW-HUAWEI, and LSRW-NIKON demonstrate competitive enhancement performance, supported by ablation studies. AMRRConv also achieves competitive low-light detection performance with a small neck parameter count when integrated into YOLOv11.

cs.CV · cs.AI

版本更新 · v2arXiv:2511.17481

基于数字孪生条件视频扩散的反事实世界模型

Counterfactual World Models via Digital Twin-conditioned Video Diffusion

Yiqing Shen, Aiza Maksutova, Chenjia Li, Mathias Unberath

AI 速读 基于摘要

提出 CWMDT 框架,用数字孪生结构化表示场景并借助大语言模型推理干预传播,从而把标准视频扩散模型改造为可回答反事实查询的世界模型。

cs.CV

查看原文摘要

World models learn to predict the temporal evolution of visual observations given a control signal, potentially enabling agents to reason about environments through forward simulation. Because of the focus on forward simulation, current world models generate predictions based on factual observations. For many emerging applications, such as comprehensive evaluations of physical AI behavior under varying conditions, the ability of world models to answer counterfactual queries -- such as "what would happen if this object was removed?" -- is of increasing importance. We formalize counterfactual world models that additionally take interventions as explicit inputs, predicting temporal sequences under hypothetical modifications to observed scene properties. Traditional world models operate directly on entangled pixel-space representations where object properties and relationships cannot be selectively modified. This modeling choice prevents targeted interventions on specific scene properties. We introduce CWMDT, a framework to overcome those limitations, turning standard video diffusion models into effective counterfactual world models. First, CWMDT constructs digital twins of observed scenes to explicitly encode objects and their relationships, represented as structured text. Second, CWMDT applies large language models to reason over these representations and predict how a counterfactual intervention propagates through time to alter the observed scene. Third, CWMDT conditions a video diffusion model with the modified representation to generate counterfactual visual sequences. Evaluations on two benchmarks show that the CWMDT approach achieves state-of-the-art performance, suggesting that alternative representations of videos, such as the digital twins considered here, offer powerful control signals for video forward simulation-based world models.

版本更新 · v2arXiv:2606.07841

面向变分推断的默认优化器大规模经验调参与比较

Large-scale empirical tuning and comparison of default optimizers for variational inference

Trevor Campbell, Jonathan H. Huggins, Kyurae Kim, Charles C. Margossian

AI 速读 基于摘要

作者在1092个贝叶斯推断优化问题上大规模评测56种随机梯度优化算法,发现没有单一方法占优,但选5种算法组合即可接近最佳观测性能。

stat.CO · cs.LG · stat.ML

查看原文摘要

Black-box variational inference (BBVI) is a methodology for posterior approximation that relies on stochastic optimization. In practice, the stochastic optimizers underpinning BBVI generally require extensive problem-specific tuning, which undermines its promise as a truly "black box" inference algorithm. However, over the past decade, many new adaptive stochastic optimization algorithms have been developed that reduce or remove entirely the need for tuning. In this work, we investigate this new collection of adaptive methods in the context of BBVI, with the goal of establishing the current state of the art in tuning-free optimization-based inference. In particular, we present a large-scale empirical evaluation of 56 stochastic gradient-based optimization algorithms applied to 1092 Bayesian inference optimization problems, involving over 550,000 individual optimization runs and 15 core-years of compute. The optimization algorithms we evaluate are chosen to represent a wide spectrum of recent approaches and the benchmark problems are chosen to span a range of difficulty, with posterior target dimension 1-10^4, condition number 1-10^8, and a range of variational families. Our results show that no single method dominates, but running a selection of 5 algorithms suffices to reliably get close to the best-possible observed performance. We thus provide a strong baseline for applications where expert tuning is not possible and for comparison when developing new stochastic optimization algorithms.

版本更新 · v5arXiv:2502.06774

ENFORCE:基于自适应深度神经投影的非线性约束学习

ENFORCE: Nonlinear Constrained Learning with Adaptive-depth Neural Projection

Giacomo Lastrucci, Artur M. Schweidtmann

AI 速读 基于摘要

提出 ENFORCE 架构,通过自适应投影模块 AdaNP 在预测中施加非线性等式与不等式约束,并在基准任务上报告满足给定容差 ε 的约束。

cs.LG

查看原文摘要

Ensuring neural networks adhere to domain-specific constraints is crucial for addressing safety and trustworthiness while also enhancing inference accuracy. Despite the nonlinear nature of most real-world tasks, the majority of existing methods are limited to affine (equality) or convex (inequality) constraints. We introduce ENFORCE, a neural network architecture that uses an adaptive projection module (AdaNP) to enforce nonlinear equality and inequality constraints in the predictions up to a specified tolerance $\varepsilon$, and exactly in the affine-in-$y$ case. For affine constraint sets, we prove that the associated projection mapping is non-expansive (1-Lipschitz), ensuring stable gradient propagation. For nonlinear constraints, we establish local convergence analysis under standard regularity conditions. We evaluate ENFORCE on multiple tasks, including function fitting, real-world engineering case studies, and learning optimization problems. For the latter, we introduce a class of scalable optimization problems as a benchmark for nonlinear constrained learning. In the benchmarks, the predictions of our architecture satisfy nonlinear equality and inequality constraints up to a prescribed tolerance $\varepsilon$, while maintaining scalability with tractable computational complexity at training and inference time.

版本更新 · v6arXiv:2508.04281

Safeguarding Deliberation in Digital Democracy

Jairo Gudiño-Rosero, Juan Ignacio Zambrano, Umberto Grandi, César A. Hidalgo

原文摘要

Large Language Models (LLMs) are gaining traction in digital democracy experiments as a method to aggregate preferences through deliberation and express the resulting common ground as consensus statements. Yet, participants can exploit critical vulnerabilities in such LLM-based systems. Here, we examine the vulnerability and robustness of consensus-generating LLMs to prompt-injection attacks, which consist of introducing strategically designed texts to amplify particular viewpoints, erase certain opinions, or divert consensus toward unrelated or irrelevant topics. Using data collected in a 2023 experiment conducted in the UK, we construct attack-free and adversarial variants of prompts containing public policy questions and opinion texts. We classify the valences of opinions and consensus statements and estimate the extent to which attacks shift LLM-generated consensus statements. Overall, we find that default LLMs exhibit widespread vulnerability to these attacks, particularly (i) when the topics under discussion concern taxation, redistribution, or green-transition policies; (ii) when attacks employ false authority or instruction-like rhetorical strategies; and (iii) when attacks favor parties whose positions are least represented in the attack-free consensus statements, turning attacks into a lever to pull the consensus towards these parties' positions. Against these non-adaptive attacks, a pipeline that detects and removes injections reduces directional failures to near zero, while majority-rule reinforcement learning anchors the consensus to participants' actual positions. Although attackers may adapt to stronger defenses, these findings advance our understanding of both the vulnerabilities and the potential defenses of consensus-generating LLMs in digital democracy applications.

cs.CY · cs.CR

版本更新 · v2arXiv:2609.32991

数据应该教什么?跨越电路、存储与使用的瓶颈迁移

What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use

Yixiao Chen, Ke Cheng, Yue Liu, Jun Zhang, Jie Jiang

AI 速读 基于摘要

作者提出一种“电路视角”的数据诊断原则,将语言模型训练中的瓶颈分为计算形成、内容可用与路径选择三类,并报告相应数据干预在350M模型实验中的效果。

cs.LG

查看原文摘要

What should data teach a language model at a particular point in training? A circuit view reveals three distinct bottlenecks: forming a computation, making its required content available, and selecting among available routes. A shared diagnosis-to-data principle connects them: localize the missing operation, preserve its causal relation, vary shortcut-bearing context, and re-audit the residual. Formation-sensitive selection and prerequisite ordering accelerate a binding-matching-transport path; a brief early prefix from the same training multiset retains a validation advantage through 100B tokens. Availability counterfactuals then distinguish writing content from invoking available memory, while paired supervision and context-opportunity ranking improve matched route decisions and long-context answer likelihood. A continuous 350M-model experiment connects the three interventions on the same facts: early circuit training improves subsequent learning, and the complete sequence outperforms stage-replacement controls on facts withheld from Use teaching. Independent query surfaces and opposed-source decisions expose conditional arbitration as the remaining frontier. Together, these results show why a change in the limiting operation calls for a change in supervision, not merely a new ranking of difficult examples.

版本更新 · v2arXiv:2609.20260

Counterexamples and Sufficient Conditions: Comments on "Optimally-Transported Generalized Method of Moments"

Masahiro Kato

原文摘要

We comment on the optimally-transported generalized method of moments (OTGMM) of Schennach and Starck (2026) and give counterexamples to Theorems 2-6. In the small-error analysis, the assumptions do not ensure consistency or asymptotic normality (Theorems 2-3). In the large-error analysis, Theorem 4 states the equivalence between the OTGMM estimator and the GMM estimator with modified moments, and Theorems 5-6 assert consistency and asymptotic normality. Through counterexamples, we show that the equivalence in Theorem 4 fails and a component of the Lagrange multiplier has different limits under the two estimators (Theorems 5-6). We also point out that, under misspecification, the population value selected by OTGMM depends on the metric. We give sufficient conditions and establish results following the original motivation for OTGMM. Our corrections to Theorems 4-6 change their assumptions or interpretation more substantially than those to Theorems 2 and 3. Furthermore, we correct Assumption 16 and the test's null distribution.

econ.EM · cs.LG · math.ST · stat.ME · stat.ML

版本更新 · v2arXiv:2607.13455

反向以进阶:从反向简单任务中进行遥操作成本有效的高难度策略学习

Reverse to Advance: Teleoperation-Cost Effective Hard Policy Learning from Reversed Easy Tasks

Qiyuan Qiao, Ge Yuan, Can Wang, Dong Xu

AI 速读 基于摘要

提出一种通过时间反转简单任务来自动生成并精炼监督数据、从而低成本学习高难度操作策略的框架。

cs.RO

查看原文摘要

High-quality teleoperation datasets are costly to collect, particularly for hard tasks. We observe that many tasks exhibit directional asymmetry: completing the forward hard task is difficult, whereas reversing it by relaxing or disrupting the environment is comparatively easy. This suggests that reversed easy-task trajectories can serve as a scalable supervision signal for the hard task, reducing the cost of manual demonstration collection. However, reversed data can be noisy, and directly training on it may yield suboptimal policies. To enable largely automated acquisition and effective use of reversed data, we propose a teleoperation-cost effective framework for hard policy learning via temporal reversal of easy tasks, consisting of three key components: a closed-loop data collection pipeline that alternates between hard-task and easy-task policies to autonomously reset the environment and generate diverse trajectories; a hierarchical data refinement pipeline that temporally inverts easy-task rollouts and filters low-quality motion using kinematic priors and a critic-guided advantage filter; and an iterative policy learning method that trains the hard-task policy using both initial reversed easy-task demonstrations and the filtered reversed data in a continuous online learning loop. By combining automated collection, hierarchical refinement, and iterative learning, our method enables scalable, reliable training of complex, high-precision manipulation tasks. Across two simulated benchmarks and real-robot experiments, we demonstrate that our method improves hard-task success rates with higher data efficiency and more stable training compared to reversal-based and reinforcement-learning baselines, without requiring extensive hard-task teleoperation.

版本更新 · v2arXiv:2607.26630

有向图上的次二次割查询可达性

Reachability with Subquadratic Cut Queries on Directed Graphs

Ben Bals, Matei Tinca, Yasamin Nazari

AI 速读 基于摘要

在有向图的割查询模型中,作者给出了DAG上单源可达性的确定性算法(O(n√(n log n))次查询),以及一般有向图上单源可达性、强连通分量和最小s-t割的确定性算法(O(n^{9/5} log n)次查询)。

cs.DS

查看原文摘要

In the cut-query model, we have access to a (directed) graph via an oracle and we can query the size of the (directed) cut of a given subset of the vertices. One of the most elementary tasks in this model is to decide if there is a path between two fixed vertices $s$ and $t$. While many results are known for undirected graphs, much less is understood for directed graphs in the cut-query model. Even for the basic task of $s$-$t$ reachability, the best known randomized algorithm is to reconstruct the entire graph with a technique by Grebinski and Kucherov using $O(n^2 / \log n)$ queries. On directed acyclic graphs (DAGs), we obtain a deterministic single-source reachability algorithm using $O(n \sqrt{n \log n})$ queries. The result is based on a topological sort algorithm and can also be adapted to compute single-source shortest paths in DAGs. On general directed graphs, we obtain deterministic algorithms for single-source reachability, strongly connected components and minimum $s$-$t$ cut using $O(n^{9/5}\log n)$ queries. The algorithm is simple and relies on two natural greedy subroutines and a modified version of Dinic's algorithm.

版本更新 · v2arXiv:2608.25623

利用认知能力画像评估AI对工作场所任务的适用性

Using profiles of cognitive capability to assess AI suitability for workplace tasks

Jonathan Prunty, Marko Tešić, Patrick Quinn, José Hernández-Orallo, Lucy Cheke

AI 速读 基于摘要

提出一套基于共同认知能力维度的画像流程,将AI系统能力与工作任务需求对齐,用于判断哪些任务适合自动化、保留给人类或人机协作。

cs.AI · cs.CY · cs.HC

查看原文摘要

Organisations deploying AI face a scoping problem: which tasks can be automated, which should remain with humans, and which are best shared between the two. Aggregate benchmark scores provide little insight into where systems will succeed or fail in practice, while human judgements of model capabilities quickly become outdated. We introduce a pipeline that profiles agents and tasks using a shared set of core cognitive capabilities. Cognitive capability profiling infers an agent's capabilities from performance on a benchmark battery annotated for the cognitive demands of each item. Task requirements weighting elicits from domain experts the relative importance of these same capabilities for their work. As both use a common set of cognitive dimensions, they can be updated independently as models and roles change, and combined to estimate AI suitability at the level of a domain, organisation, role, or individual duty. We validate capability recovery on synthetic agents, profile six AI systems, and elicit task requirements from 410 employees across six occupational domains. AI systems differed more across cognitive dimensions than across model families, while workplace activities converged on a shared cognitive core. The resulting scores provide a comparative scoping tool for identifying promising candidates for piloting and areas where current systems are unlikely to be well suited. We discuss extending the framework to profile human workers alongside AI systems, moving from AI suitability towards human-machine task allocation.

版本更新 · v2arXiv:2610.21323

AdaLoop:以视觉编码器进行思考

AdaLoop: Thinking with the Vision Encoder

Xinran Nicole Han, Yiyang Lu, Katelyn Gan, Todd Zickler

AI 速读 基于摘要

AdaLoop 提出一种按问题条件进行视觉循环计算的框架,让冻结的预训练视觉编码器在多次迭代中复用其变换,以适配不同问题所需的视觉处理深度。

cs.CV

查看原文摘要

Most vision-language models (VLMs) treat the vision encoder as a static feature extractor: it encodes an image once, independently of the question, and leaves subsequent reasoning to the language model. Yet different questions may require different visual operations and processing depths. We present AdaLoop, a framework for question-conditioned visual recurrence in VLMs. AdaLoop adapts visual computation to the question and reuses the encoder's transformations across multiple iterations, with the pretrained vision weights frozen. We also introduce VisRO, a procedural dataset and generation pipeline for training and evaluating vision-centric reasoning. On six VisRO tasks, AdaLoop outperforms standard fine-tuning and question-conditioned single-pass baselines with matched training data and optimizer updates. These gains hold across three VLM families on both in-distribution and out-of-distribution examples. Our findings suggest that pretrained vision encoders can contribute to reasoning through task-directed, iterative visual computation.

版本更新 · v3arXiv:2606.13843

Rethinking the UI of GenUI: A Tale of Two Designs

Xiang 'Anthony' Chen, Savvas Dimitrios Petridis, Ruofei Du, Yang Li

原文摘要

Generative user interface (GenUI) tools use large models to create UI mockups from high-level descriptions; a recurring interaction paradigm starts with an unstructured prompt, followed by depth-first generation of a polished, high-fidelity prototype. To examine how it supports early-stage, 0-to-1 design exploration, we contrast this paradigm with structured input, breadth-first workflow, and low-fidelity generation. In our study, 24 industry professionals in early-stage product and UX design used a commercial GenUI system and our research prototype as study-era instances of each paradigm for a comparative evaluation. Findings show that 1) structured input surfaces key facets but raises entry barriers; 2) breadth-first workflow reveals more possibilities, but previewing multi-screen UX ideas remains hard; and 3) despite low fidelity's value, participants rated high fidelity as better suited to their design stage and to communicating ideas. Our findings contribute a model-agnostic, design-level account of how GenUI users specify intent, traverse alternatives, and interpret fidelity.

cs.HC

版本更新 · v2arXiv:2611.01656

AIDA: An AI Outage Registry with Evidence from On-Chain MEV

Wenbin Wu

原文摘要

Generative AI coding tools have lowered the cost of writing trading software, but no systematic dataset records when these services fail. We introduce the AI Incident and Disruption Archive (AIDA), a multi-vendor registry of 5,868 deduplicated outage incidents across 30 providers from 2025 to 2026, with foundation-model incidents verified against primary status-page or postmortem URLs. Pairing AIDA with 5,041,034 verified maximal extractable value (MEV) transactions by 8,516 Ethereum addresses, their contract creations, and a 22-month Base Layer-2 panel of 1,099,593,191 swaps and 29,120 private executors, we establish two findings. First, entry into MEV expanded where code and public state suffice, as active arbitrage addresses quadrupled from late 2024 to late 2026 and liquidators grew by a third, while sandwich attackers, who need private order flow and builder access, declined. Execution nonetheless remained concentrated, with the top fifty addresses executing two thirds of verified trades. Second, AI outages stall new trading code while deployed bots keep trading. On Ethereum, addresses releasing a private executor fall to 0.67 on the day of an eight-hour disruption (0.68 for executor creations during OpenAI outage hours) and to 0.66 at lag two before rebounding on day three; on Base, operator top-level creations fall to 0.76 during OpenAI hours and executor-deploying operators to 0.88 at lag two. Non-trading creations, automated factory clones, and live arbitrage and sandwich execution across both chains remain unchanged. Cheaper code thus lowers the barrier to building MEV contracts, while private order flow, latency and capital still determine who wins execution.

q-fin.TR · cs.CE

版本更新 · v2arXiv:2607.14940

Causal Inference for Sequential Settings under Interference and Latent Confounding

Phevos Paschalidis, Constantinos Daskalakis, Devavrat Shah

原文摘要

We study causal inference under outcome interference for sequential, observational settings. Specifically, we consider settings where the binary outcomes over N units are Markovian across T time steps. At each time step, the outcomes of N units have dependencies captured through an Ising model; each outcome is also impacted through an external field capturing the effects of its treatment as well as latent confounders. Similar to panel data literature, these latent confounders are modeled to have a low-rank factor structure. Our data is a single sample from this high-dimensional distribution. To estimate causal quantities of interest, we provide a computationally efficient method based on Maximum Pseudo-Likelihood Estimation (MPLE) for learning the model parameters. Under mild assumptions, we establish non-asymptotic consistency for parameter estimation and show this translates to faithful estimation of causal quantities of interest after sampling from the learned model. We demonstrate the efficacy of the method through synthetic experiments as well as a real-world case-study investigating causal effects of vaccine rates on COVID-19 death rates within US counties nationwide.

cs.LG · math.PR

版本更新 · v2arXiv:2606.14373

Machine-learned particle flow as a foundation model for collider physics

Farouk Mokhtar, Joosep Pata, Michael Kagan, Javier Duarte

原文摘要

The workflow from particle collision to physics analysis passes through a series of reconstruction steps that are traditionally modular and disconnected, with no shared representation linking low-level detector data to high-level analysis tasks. We show that casting event reconstruction as a machine learning problem naturally produces such a shared representation. We repurpose a machine learning model trained for particle-flow reconstruction (MLPF) to perform three distinct analysis tasks: jet flavor identification, jet energy regression, and missing momentum regression. By appending the per-particle latent representations learned during reconstruction as additional input features, we substantially improve over baselines that use conventional particle-level features alone. We further demonstrate that a single linear layer trained using only the latent representations achieves competitive performance against state-of-the-art baseline architectures, and outperforms the baseline for missing momentum regression with approximately 35 times fewer parameters. These results demonstrate that the latent representations learned during reconstruction encode essential physics information needed for downstream analysis, establishing MLPF as a foundation model and offering a concrete step toward an end-to-end pipeline from detector data to physics analysis.

hep-ex · cs.LG · hep-ph · physics.data-an · physics.ins-det

版本更新 · v2arXiv:2609.32602

AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion

Gal Wertheizer, Rom Himelstein, Tomer Peretz, Avi Mendelson

原文摘要

Adversarial attacks optimized on a single open-weight LLM can transfer to and jailbreak architecturally different models, allowing an attacker with white-box access to one model to compromise independently deployed systems. This creates a shared vulnerability across models, yet existing defenses are not designed for this cross-model threat. We find that cross-model transfer aligns with shared internal representation geometry, making it a natural defense target. AnchorRep targets this geometry directly with a lightweight LoRA adapter that pushes the defended model's internal representations of harmful prompts away from those of a frozen anchor model on the same prompts. Training uses a small set of harmful prompts and no adversarial examples. Across five models and four architectural families, AnchorRep reduces cross-model attack success rate to <=1.1% on 2,000 transferred attacks (0% on two), including the largest drop on Mistral (36% -> 1.1%). Existing defenses can reduce transfer, but only at high cost either inducing up to 77% degenerate benign output or increasing over-refusal by up to 18%. Because such degenerate benign outputs are not captured by standard refusal-based metrics, we introduce the Benign Garble Rate to quantify them. Our results suggest that cross-model robustness can be achieved by shaping representation geometry, without requiring attack-specific training

cs.LG · cs.AI

版本更新 · v4arXiv:2503.15846

A Closer Look at Dynamic Scene Graph Generation In the Era of Multimodal Large Language Models

Xuanming Cui, Jaiminkumar Ashokbhai Bhoi, Chionh Wei Peng, Adriel Kuek, Ser Nam Lim

原文摘要

Dynamic Scene Graph Generation (DSGG) aims to capture objects and their evolving relations in videos. Despite recent progress, the practicality and quality of generated scene graphs remain limited compared to the rapid advances in Multimodal Large Language Models (MLLMs). In this work, we revisit DSGG from two fundamental perspectives: task setup and model design. From the task setup perspective, we identify two key limitations of the current recall-oriented evaluation protocol: (i) a severe precision-recall trade-off, and (ii) uninformative and redundant relation generation. To better assess practical usefulness, we introduce five additional metrics that provide a more comprehensive evaluation of the quality of generated dynamic scene graphs. From the model design perspective, we explore directly using MLLMs for scene graph generation and establish a strong MLLM-based DSGG baseline through three design changes. First, we replace the conventional bottom-up pipeline with a top-down reason-then-locate strategy. Second, we reformulate frame-wise dynamic graphs as Temporal Relation Set (TRS) prediction, improving both efficiency and performance. Third, we introduce Importance-Aware Finetuning (IAF) to encourage more relevant and diverse relation generation. Extensive experiments on Action Genome, VidVRD, and PVSG show that our approach consistently achieves state-of-the-art performance.

cs.CV

版本更新 · v3arXiv:2610.20527

JetStream: Generating Verified Query Accelerators for Existing Database Systems

Akhilesh Balasingam, Amadou Ngom, Geoffrey X. Yu, Tim Kraska

原文摘要

Recent work has shown that LLMs can synthesize highly instance-optimized database systems for fixed workloads, but to date these systems only replace the DBMS's native storage and assume static data: users must migrate their data, often give up ad-hoc queries, lose acceleration once the data changes, and lack formal correctness guarantees. We present JetStream, which instead generates query-specific accelerators that extend an existing DBMS. Given a set of parameterized query templates, a staged agentic workflow synthesizes accelerators that run directly over the DBMS's native tables and may maintain custom auxiliary state, while the host DBMS remains responsible for storage, transactions, recovery, and all the other queries. A fixed, engine-neutral substrate keeps auxiliary state transactionally consistent under writes, while generated backend adapters handle engine-specific hooks. JetStream generates two kinds of accelerators: tested accelerators, which may use any optimization and are validated by differential testing, and verified accelerators, which trade some performance for a machine-checked proof that every answer satisfies a trusted specification derived from the SQL. On TPC-H at SF=20, JetStream achieves a $584\times$ geomean read speedup over DuckDB ($89\times$ verified) and retains $139\times$ ($46\times$ verified) under a continuous update stream of 10,000 modified rows per second.

cs.DB