paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

arXiv

Deep Generative Model for Human Mobility Behavior

Ye Hong, Yatao Zhang, Konrad Schindler, Martin Raubal

Understanding and modeling human mobility is central to challenges in transport planning, sustainable urban design, and public health. Despite decades of effort, simulating individual mobility remains challenging because of its complex, context-dependent, and exploratory nature. Here, building on the activity-based view of daily mobility, we propose MobilityGen, a diffusion-based generative framework for simulating multi-attribute activity-travel sequences over days to weeks at large spatial scales. By linking behavioral attributes with environmental context, MobilityGen reproduces key patterns such as scaling laws for location visits, activity time allocation, and the coupled evolution of travel mode and destination choices. It reflects spatio-temporal variability and generates diverse and plausible mobility patterns consistent with the built environment. Beyond standard validation, MobilityGen enables analyses that have been difficult with earlier models, including how access to urban space varies across travel modes and how co-presence dynamics shape social exposure and segregation. Together, these results support an integrated, data-driven basis for fine-grained studies of human mobility behavior and its societal implications.

arXiv

Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents

Zhiping Zhang, Yi Evie Zhang, Freda Shi, Tianshi Li

LLM agents require personal information for personalization in order to effectively act on users' behalf, but this raises privacy concerns that can discourage data sharing, limiting both the autonomy levels at which agents can operate and the effectiveness of personalization. Yet the expanded design space of agent autonomy also presents opportunities to shape these effects, which remain underexplored. We conducted a $3\times3$ between-subjects experiment ($N=450$) to study how agent autonomy level influences personalization's effects on users' privacy concerns, trust, and willingness to use, as well as the underlying psychological processes. We find that risk-contingent autonomy, where the agent delegates control back to users upon detecting potential privacy leakage, improves users' perceived control. This in turn attenuates personalization's adverse effects: privacy concerns rise less and trust declines less. Our results suggest that designing $\textbf{agent's autonomy}$ that supports $\textbf{human autonomy}$ (both perceived control and oversight effectiveness) helps users benefit from personalization without being deterred by growing privacy concerns. This positions aligning decision authority between users and agents ($\textbf{autonomy alignment}$) as an important opportunity and challenge for trustworthy human-agent interaction.

arXiv

Probabilistic Circuits for Knowledge Graph Completion with Reduced Rule Sets

Jaikrishna Manojkumar Patil, Nathaniel Lee, Al Mehdi Saadat Chowdhury, YooJung Choi, Paulo Shakarian

Rule-based methods for knowledge graph completion provide explainable results, but often require tens of thousands of rules to achieve competitive performance. Although individual predictions may use only a few rules, reasoning over an entire dataset requires these massive rule sets, hampering system-level understanding. We address this by learning a probability distribution over sets of rules that work together using probabilistic circuits. Our approach achieves a 70-96% reduction in the number of rules needed to reach peak baseline performance. Using an equivalent minimal number of rules, we outperform the baseline by up to 31$\times$. When comparing our minimal rule sets against baseline's full rule sets, we preserve 91% of peak baseline performance. Empirical validation on 8 benchmark datasets shows that our reduced rule sets exhibit higher utilization---fewer rules are wasted, and each prediction requires fewer rules. We show that our framework is grounded in well-known semantics of Nilsson's probabilistic logic and does not require independence assumptions. We provide exact probabilistic inference as well as an efficient lower bound and evaluate both.

arXiv

Reflex First, Reflect Later: Latency-Aware Embodied LLM Agents for Dynamic Response

Yangqing Zheng, Shunqi Mao, Dingxin Zhang, Weidong Cai

Large language models (LLMs) have substantially improved the planning capabilities of embodied agents, enabling their deployment in dynamic and safety-critical environments. However, these settings expose a critical limitation: inference latency. Delayed LLM responses can weaken real-time responsiveness and misalign agent reasoning with rapidly changing environmental states. This paper systematically studies the impact of inference latency on LLM-based embodied agents in dynamic environments. We introduce an FPS-based Time Conversion Mechanism (TCM) that maps inference time to elapsed simulation time, allowing computational delays to directly affect environmental evolution and agent outcomes. We instantiate this protocol in HAZARD and introduce Response Latency (RL) and Latency-to-Action Ratio (LAR) to evaluate agent responsiveness. Building on this framework, we propose the Rapid-Reflex Async-Reflect Agent (RRARA), which integrates rapid reflexive actions with asynchronous LLM reflection to mitigate latency-induced errors. We further introduce an LLM-based PrePlanner that generates cached object-centric subgoals, reducing repeated LLM calls while retaining the model's high-level reasoning capability. Experiments show that accounting for inference latency substantially changes embodied-agent performance and that RRARA achieves a stronger balance between decision quality and responsiveness.

arXiv

Contamination Means Overestimation? A Fine-Grained Empirical Study in Code Intelligence

Zhen Yang, Hongyi Lin, Yifan He, Junqi Wang, Zeyu Sun, Shuo Liu, Jie Xu, Pengpeng Wang, Zhongxing Yu, Qingyuan Liang

In recent years, code intelligence has gained increasing importance in the field of automated software engineering. Meanwhile, the widespread adoption of Pretrained Language Models (PLMs) and Large Language Models (LLMs) has raised concerns regarding data contamination and its potential impact on model performance evaluation. Previous studies mainly focused on sample-level contamination, ignoring partial contamination scenarios that are pervasive in code intelligence. This paper fills this gap and presents a systematic empirical study to investigate the fine-grained data contamination on mainstream code tasks. Our study involves diverse representative PLMs: RoBERTa and GPT-2, and LLMs: LLaMA and StarCoder, covering three major tasks: code translation, code generation, and code summarization, across two Programming Languages (PLs): Java and Python. We categorize contamination scenarios into four types according to the code intelligence practice, namely input-only, output-only, unpaired, and paired contamination settings, and construct corresponding experimental and control groups for exploration. Experimental results show that, under the pre-training, fine-tuning, and inference paradigm adopted by PLMs, even deliberately injecting paired contamination does not lead to significant performance overestimation. But direct inference or small-scale fine-tuning uncovers the contamination effects. In contrast, LLMs with pre-training and inference paradigm are significantly affected by the paired contamination. Apart from the above, other contamination scenarios have no impact on both PLMs and LLMs. Our findings challenge the conventional belief that contamination inevitably leads to performance overestimation, providing new insights into the evaluation and deployment of code intelligence models.

arXiv

ACEvo: Adversarial Co-Evolution of Problem Distributions and Solvers for Combinatorial Optimization

Ruibo Duan, Yuxin Liu, Haoran Ye, Xinyao Dong, zhiqiang xu, Chenglin Fan

Large language models (LLMs) are increasingly used to synthesize heuristic programs, yet most existing pipelines optimize solvers against fixed benchmark distributions. This static setup can obscure solver weaknesses and limit understanding of how LLM-designed algorithms adapt under distribution shift. We present Adversarial Co-Evolution (ACEvo), a closed-loop framework in which LLMs iteratively co-evolve two types of executable programs: heuristic solvers and problem generators. The generator proposes increasingly challenging instances, while the solver is refined to improve performance on the evolving distribution, forming an automated adversarial curriculum for program design and evaluation. We instantiate ACEvo on routing problems, including TSP, OP, and CVRP. Across these domains, the framework produces instance distributions that consistently induce larger optimality gaps than standard benchmarks and yields solver programs that outperform those obtained from static-training baselines under distribution shift. Beyond final performance, ACEvo provides a testbed for studying LLM-based algorithm design under evolving distributions, including how reflective mutation, adversarial feedback, and co-adaptation shape the evolution of both generators and solvers. These results suggest that closed-loop co-evolution is a promising paradigm for using language models not only to generate algorithms, but also to construct adaptive evaluation environments.

arXiv

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning

Hongyi James Cai, Junlin Wang, Xiaoyin Chen, Bhuwan Dhingra

Recent advancements in large language models (LLMs) suggest that reinforcement learning (RL) effectively internalizes search strategies, yielding significant improvements on challenging reasoning tasks through extended chains of thought. While backtracking is widely viewed as the core mechanism enabling this improvement, its precise dynamics and how SFT and RL interact to optimize for it, remain poorly understood. In this work, we argue that backtracking, the ability to explicitly revisit and revise earlier reasoning steps, is a key operator that enables the transition from linear generation to non-linear tree search for LLMs, unlocking strong performance on combinatorially complex tasks. We motivate this claim by first studying the interplay between supervised fine-tuning (SFT) warm-up and RL across eight reasoning tasks: Countdown, Sudoku, Arc 1D, Advanced Geometry, Color Cube Rotation, List Functions, Zebra Puzzles, and Self Reference. We find that a regular SFT warm-up using self-sampled CoT sequences provides a modest boost to subsequent RL compared to training without any SFT warm-up; however, such gains saturate as tasks become more difficult. Motivated by this failure mode, we introduce a backtracking-centric training recipe. By synthetically varying the number of explicit backtracking steps in the SFT warm-up, we show that (i) longer CoTs containing backtracks stabilize and amplify RL, and (ii) the optimal backtrack depth scales with task difficulty: zero for Arc 1D, one for Countdown, and five or more for Sudoku. Our findings establish that principled backtracking is essential for improving the model's reasoning capability.

arXiv

Transformer-Based Neural Quantum Digital Twins for Many-Body Spectral Reconstruction and Adaptive Quantum-Annealing Schedule Design

Jianlong Lu, Hanqiu Peng, Hongrui Zhang, Ying Chen

We introduce Transformer-based Neural Quantum Digital Twins (Tx-NQDTs) to reconstruct the low-energy spectral evolution of many-body quantum systems along quantum-annealing paths, including ground- and first-excited-state energies, spectral gaps, and transition matrix elements, at efficient computational cost. Tx-NQDTs employ a graph-informed Transformer neural network trained to estimate the spectral information needed for annealing-schedule design. We integrate these estimates with an adaptive schedule-construction procedure guided by first-order adiabatic perturbation theory (FOAPT), which is used as a closed-system spectral diagnostic to allocate annealing time near predicted spectral bottlenecks. Experiments on a D-Wave quantum annealer ($N=10,15,20$ logical variables, with schedules represented by up to 12 control points) show that Tx-NQDT-informed schedules can improve empirical ground-state success probabilities relative to the default $20\,μ\mathrm{s}$ linear schedule under the tested hardware conditions. The proposed schedules achieve success probabilities $2.2$--$11.7$ percentage points higher across the reported easy and hard subsets and outperform the default baseline in 44 of 60 cases. The results demonstrate the feasibility of using learned logical spectral information to automatically generate adaptive quantum-annealing schedules for practical hardware experiments.

arXiv

LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?

Kexian Tang, Junyao Gao, Yanhong Zeng, Haodong Duan, Yanan SUN, Zhening Xing, Wenran Liu, Kai Chen, Kaifeng Lyu

Many real-world applications of spatial intelligence, such as robotic control, autonomous driving, and automated assembly, require spatial reasoning across multiple sequential steps. However, the extent to which current Multimodal Large Language Models (MLLMs) possess this capability remains largely unexplored. Inspired by LEGO construction, a recreational activity that critically relies on multi-step spatial reasoning, we introduce LEGO-Puzzles: a benchmark designed to systematically evaluate the spatial reasoning capabilities of MLLMs from basic spatial understanding to multi-step planning. LEGO-Puzzles contains two task sets. The Elementary set covers 11 visual question-answering (VQA) tasks with 1,100 carefully curated samples to test elementary spatial reasoning skills that are cruical for LEGO assembly. The Planning set directly requires the model to generate a step-by-step plan for assembling a target LEGO structure, where the tasks are organized into subsets with different planning horizons ranging up to 8. Our evaluation of 29 state-of-the-art MLLMs shows that even the strongest models struggle with elementary reasoning tasks in LEGO construction, falling at least 20% behind human performance. The planning accuracy also quickly drops to 0% as the number of planning steps increases, whereas our human participants solve all the tasks perfectly. Switching the output format from multiple choice to image generation degrades model performance even further, leading to zero accuracy even for planning 3 steps. Overall, LEGO-Puzzles reveals critical limitations in current MLLMs' spatial reasoning capabilities and highlights the need for substantial advances.

arXiv

On-Policy Self-Distillation without Any Supervision

Yijiang Li, Bingyang Wang, Yijun Liang, Yunjie Tian, Di Fu, Nuno Vasconcelos

On-policy (Self-)Distillation (OPD / OPSD) has shown strong potential for post-training large language models (LLMs). However, existing methods still rely heavily on external supervision, including ground-truth signals, environmental feedback, or guidance from larger models, and therefore fall short of genuine "self"-distillation. In this study, we show that on-policy self-distillation can be achieved using only a model's own generations via internal consistency. We propose unsupervised on-policy self-distillation (U-OPSD). U-OPSD first samples multiple rollouts and constructs a pseudo solution by majority vote under a self-consistency threshold. It then conditions the model's distribution on the pseudo-solution and distills itself on the disagreeing completions, allowing the model to correct itself precisely where it is confidently wrong. Across diverse benchmarks, base models, and training settings, U-OPSD consistently improves over the base models and matches or surpasses supervised methods with ground truth (GT) such as OPSD and GRPO. On five mathematical reasoning benchmarks, i.e., AIME24, AIME25, HMMT25, MATH500, and AMC23, U-OPSD improves over the base model by 8.5% and 10.7% on Qwen3 non-thinking mode at 4B and 8B scales, and outperforms OPSD by 3.2% and 2.3% on average, respectively. In thinking mode, U-OPSD stays on par with OPSD, ahead by 0.9% at 4B and level at 8B and surpassing GRPO by 0.7% and 1.1%, respectively. Code is available at [https://github.com/williamium3000/u-opsd](https://github.com/williamium3000/u-opsd).

arXiv

Evolutionary Curriculum Learning Improves Biological Sequence Modeling

Richard Zhu, Kento Nishi

Variational autoencoders (VAEs) trained on multiple sequence alignments (MSAs) have emerged as powerful generative models for biological sequences, with applications ranging from disease variant prediction to functional RNA design. However, standard biological VAE training treats all sequences as exchangeable, ignoring the rich evolutionary structure that organizes homologous sequences from evolutionarily close to highly divergent. We propose Evolutionary Curriculum Learning (ECL), a training strategy that exploits this structure by progressively exposing the model to sequences of increasing evolutionary distance from sampled anchors, following a power-law expansion schedule. Applied to two architecturally distinct VAE models and two biological domains--protein variant effect prediction with EVE and RNA family sequence generation with RfamGen--ECL improves downstream task performance across five random seeds per configuration. Mean ClinVar classification AUROC rises from 0.981 to 0.989 for p53; for PTEN, ECL attains 1.000 in every seed whereas the baseline is unstable (mean 0.905, falling as low as 0.54). For RNA, ECL raises mean covariance-model bit scores on all three families tested and exceeds its seed-matched baseline in 12 of 15 training runs, though with only three families the effect cannot be established as significant at the family level. Ablation experiments show that progressively expanding the sampled sequences by evolutionary distance outperforms fixed-size neighborhood sampling in addition to uniform random sampling. Evolutionary distance is therefore a useful inductive bias for ordering the training curriculum in biological sequence modeling.

arXiv

A Convex Hull Cheapest Insertion Heuristic for the Non-Euclidean TSP

Mithun Goutham, Ethan David Rosati, Hollis Schuler, Meghna Menon, Sarah Garrow, Stephanie Stockar

Autonomous robots frequently encounter routing problems that involve non-Euclidean cost considerations due to obstacles, traffic, or a cost function that is not simply the straight-line distance between locations to be visited. Often, the resulting Non-Euclidean Traveling Salesperson Problem (NETSP) must be solved onboard with limited computational resources, posing a significant challenge due to its NP-hard combinatorial nature. To address this, the Adapted Convex Hull Cheapest Insertion (ACHCI) algorithm is proposed. ACHCI is a lightweight heuristic designed for resource-constrained onboard tour computation, with small form factor robots as its target application. ACHCI combines a multidimensional scaling approach with a convex hull initialized tour construction procedure to generalize the well-known Euclidean CHCI heuristic to non-Euclidean problems. Computational experiments on diverse modified TSPLIB scenarios demonstrate that ACHCI outperforms other lightweight heuristics like Nearest Neighbor and Nearest Insertion in 88\% and 99\% of the cases, as well as population-based metaheuristics such as Genetic Algorithms and Ant Colony Optimization in 87\% and 95\% of test cases respectively. The adoption of ACHCI for resource-limited onboard routing is expected to enhance the operational efficiency of autonomous agents by reducing travel distance, energy consumption, charging-related downtime, task completion duration and operating costs.

arXiv

Attack Ensembles Expose a Safety-Utility Trade-off in Black-Box Guard Defenses Against Encoded VLM Jailbreaks

Haoyu Zhang, Zhuoxi Wang, Shibo Zheng, Yi Feng, Xiao Luo, Zijian Xiao, Haowen Xu, Xiangchen Guan, Mohammad Zandsalimy, Shanu Sushmita

Safety classifiers ("guards") are the dominant black-box defense for vision-language models, yet a guard judges an input's surface form, not its meaning: a harmful request re-encoded as set theory, formal logic, a classical language, code, or text rendered inside an image slips past a guard that would block it in plain language - the decode gap. The standard fix is a preprocessor that recovers image content and decodes the encoding before the guard. We build one and evaluate it against an ensemble of eleven published encoding attacks, counting a behavior as broken if any attack succeeds. That metric separates two mechanisms such defenses conflate. Restoring a view the guard never had improves it on both axes at once: it blocks far more attacks, and, measured on a category-balanced benign set, it blocks fewer benign requests, because restating a request normalizes the borderline phrasing a classifier over-flags. It still does not make the system safer: against an attacker free to choose among eleven encodings, closing one channel relocates the success rather than removing it, and no ensemble contrast survives multiple-comparison correction. What does lower ensemble attack success is re-screening the recovered pre-decode surface, and that step is where the entire benign cost falls. The safety-utility trade-off is therefore not a property of recovery; it is localized to one step. Across the full guard x target x condition factorial, no configuration reaches an ensemble attack-success rate at or below 40% while holding benign over-refusal under 70%. The per-attack averages usually reported understate the attacker roughly fourfold, which is why this frontier is easy to miss. Composing across defense families is the one lever that moved the safety axis, beating every configuration we measured, and still landing far outside any deployable refusal budget.

arXiv

From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models

Seunggeun Kim, Jaeyeon Kim, Taekyun Lee, Yuyuan Chen, Yilun Du, Sham Kakade, Sitan Chen

Many discrete reasoning tasks, such as code generation, are inherently non-causal: programmers move between high-level structure and local details, a process we call any-order inference. For autoregressive language models, which lack a native any-order interface, non-causal abilities such as infilling and next-edit prediction require hand-designed mechanisms. Can we instead design models that natively support any-order inference? Masked diffusion models have recently emerged as compelling candidates, as their any-order training objective naturally offers an any-order prediction interface. This interface, however, does not automatically yield any-order inference. We demonstrate that this interface-inference gap stems from positional uncertainty: fixed-canvas, token-level models may know what semantic component should appear without knowing where to place it. In light of this, we propose two complementary approaches: (1) Insertion-based masked diffusion, building on FlexMDM (Kim et al, 2025), relaxes fixed-position commitments via insertions, enabling generation across non-contiguous regions. (2) Latent-space masked diffusion shifts prediction to coarser semantic segments, enabling search over latent generation orders. Empirically, we train a 7B FlexMDM for Python coding and a 125M LatentMDM for GSM8K and show that both approaches induce distinct any-order inference behaviors and improve downstream performance. We release our codebase at https://github.com/SeunggeunKimkr/genuine-any-order.

arXiv

When benchmark inferences do not compose: Projectibility in AI evaluation

Brett Reynolds

An AI benchmark result rarely reaches a consequential claim in one step. Evaluators generalize it to further cases, interpret it as evidence of capability, extrapolate it to new tasks, transport it to another system or site, and combine it with assumptions about human review and downstream consequences. Validity-centred approaches require evidence for each claim. This paper makes explicit and operationalizes a problem those approaches leave to the analyst: warranted links don't automatically make a warranted chain. The target of one study may not be the source of the next; system, population, outcome, or conditions may change at the interface; and shared data or model lineage may make apparently independent support dependent. Projectibility concerns whether a bounded extension from observed to unobserved cases is warranted. Goodman supplies the problem of rival extensions; argument-based validity supplies an architecture for testing them. The contribution is an interface audit for distributed AI evidence: typed source and target descriptions, and a procedure separating endpoints that never meet from endpoints that meet while warrant fails to cross. A legal-research case shows how benchmark evidence and a deployment study can each be sound while remaining parallel. A known-truth demonstration shows why aggregate stability can erase distinctions a later projection requires. The resulting projectibility audit diagnoses unsupported joins in benchmark-to-use arguments.

arXiv

Unified Static-Dynamic Pruning for Efficient LLM Inference

Jinhyeok Kim, Yejoon Lee, Jaeyoung Do

The increasing deployment of large language models (LLMs) has magnified the computational and memory bottlenecks of autoregressive decoding, where low compute intensity and bandwidth-bound kernels dominate inference cost. Weight pruning offers a promising remedy, but existing methods remain confined to either static pruning (SP), which permanently removes redundant weights but lacks adaptivity, or dynamic pruning (DP), which adapts to input sparsity but introduces runtime irregularity. This paper presents SPDP, a unified sparse-inference framework that integrates unstructured SP with input-adaptive DP for efficient LLM inference on GPUs. SPDP co-designs a new Tiled-Column-wise Bitmap Compressed (Tiled-CBC) format and two complementary GPU kernels: (1) a CUDA-core spMspV kernel featuring Hybrid Activation-aware Dynamic Shared-Memory Bitmap Decoding (HAD-SMBD) for fine-grained, runtime activation skipping, and (2) a Tensor-Core SpMM kernel optimized for prefill computation. This joint format-kernel design harmonizes static and dynamic sparsity, maintaining bandwidth-efficient memory access and high compute intensity under both phases of LLM inference. Comprehensive evaluations on inference-optimized GPUs demonstrate that SPDP achieves 1.24x-1.37x average speedup (up to 2.51x) over state-of-the-art sparse frameworks such as SpInfer, while matching perplexity with up to 25% higher sparsity. SPDP advances the inference efficiency-quality Pareto frontier, showing that unified static-dynamic pruning can deliver substantial throughput and performance-per-watt improvements in large-scale LLM serving.

arXiv

Multilevel Graph Wavelet Compressed Sensing with Scale-Aware Neural Recovery

Amirhossein Nouranizadeh, Sarang Rajendra Patil, Alan John Varghese, Varsha Narayanan, Amit Chakraborty, Mengjia Xu

Scientific machine learning methods such as neural operators and physics-informed neural networks have advanced engineering applications and inverse problems, but their training typically requires large volumes of simulated data. This makes data preparation and model training expensive. We propose Graph Wavelet Compressed Sensing (GWCS), a learning-based framework for offline compression of graph signals by representing them as sparse, interpretable wavelet-domain representations using the spectral graph wavelet transform. The framework combines a nonparametric multilevel importance sampler, which retains high-energy wavelet coefficients within each scale for a given compression ratio, with a scale-aware graph neural network that reconstructs the signal from the sparse coefficients. We evaluate the proposed framework on synthetic approximately band-limited graph signals over random graphs and four PDE simulation datasets over meshes, which include Turbulent Radiative Layer, Viscoelastic Instability, Kolmogorov Flow, and Dynamic Stall. We compare against graph signal sampling methods and graph autoencoder baselines. Results demonstrate that the framework achieves high reconstruction fidelity and substantial data compression compared to existing benchmarks.

arXiv

Riemannian Deep Learning: Modules, Networks, and Geometries

Ziheng Chen

Deep neural networks on manifold-valued representations have attracted growing interest, but many basic components remain tied to specific manifolds, rely on Euclidean approximations, or require costly and numerically fragile geometric operations. This thesis develops a unified framework for Riemannian deep learning from three complementary perspectives: reusable neural modules, manifold-specific network architectures, and the design of underlying geometries. It generalizes batch normalization from Euclidean spaces and individual manifolds to broad classes of Lie groups and gyrogroups, and extends multinomial logistic regression from Euclidean space to SPD manifolds and then to general Riemannian manifolds. It further develops neural networks for several important geometric representations, including an unconstrained model of hyperbolic space, Busemann-based hyperbolic learning, and full-rank correlation matrices. Finally, it introduces adaptive and computationally efficient Riemannian metrics on SPD manifolds, including learnable Log-Euclidean geometries and fast, stable Cholesky-based geometries. The proposed methods are supported by theoretical analysis and validated through numerical experiments and applications in vision, signal processing, graph learning, and genomics.

arXiv

Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems

Alexander Apartsin, Yehudit Aperstein

A cyber-physical system (CPS) can enter a faulty state that is individually normal on every sensor and reconstructs accurately, yet is improbable under normal joint operation. This exposes the central weakness of reconstruction-based detection: reconstruction measures whether a state can be reproduced (reachability), not whether normal operation is likely to occupy it (probability). We model CPS normal behavior as a union of many imbalanced operating regimes, ten assumptions we call Massive, Implicit, Imbalanced Multimodality (MIIM). Our detector, LatAD, jointly learns a latent and a Gaussian-mixture clustering of these regimes (VaDE) and scores anomalies by density rather than reconstruction. Because a CPS is an assembly of coupled subsystems, we factorize that density over correlation-community subsystems and combine per-community surprises by a cohesion-weighted, sparsity-adaptive statistic, concentrating a local fault a global density dilutes. Evaluated with raw point-wise metrics and a difficulty split isolating the stealthy faults a per-channel threshold misses, LatAD attains the best AUROC on three real CPS benchmarks (WADI 0.862, HAI 0.949, SWaT 0.993) and leads the difficult subset of all three, notably on HAI (0.849; a significant +0.09 over the next-best baseline, 95% CI [0.046, 0.160]); the reconstruction-based USAD and TranAD fall to 0.30-0.48 on these reconstructable-but-improbable faults.

arXiv

Safe Bayesian Optimization with Counterfactual Policies

Katherine Avery, Bruno Castro da Silva, David Jensen

In many decision-making settings, new interventions are acceptable only if they do not reduce outcomes below some established threshold. For example, in clinical medicine, new treatments are often acceptable only if they do not worsen outcomes relative to an established standard of care. Safe Bayesian optimization maximizes an objective subject to safety constraints. In the setting that we consider here, safety is defined relative to a known baseline policy whose outcomes are counterfactual and therefore unobserved. Thus, the counterfactual outcomes of the baseline policy must be estimated and those (uncertain) estimates must be used to safely optimize the objective. We address this estimation problem by using conformal prediction to construct valid uncertainty intervals for counterfactual baseline outcomes, and we show how these intervals can be integrated into safe Bayesian optimization to ensure that constraint violations occur at or below a user-specified rate. We also show how to adapt these conformal estimates to different kinds of covariate shift. We provide a safety proof, experimental evidence, and a sensitivity analysis.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →