中 EN
登录 注册账户

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达，利用大语言模型自动生成交叉领域文献分析简报。

登录 注册账户
01.
PLOS Medicine 2026-05-21

Novel symptoms associated with eclampsia could improve detection and save lives

作者:
Alice Beardmore-Gray↗

by Alice Beardmore-Gray, Andrew Shennan Eclampsia is a life-threatening complication of pre-eclampsia, yet remains difficult to predict. In this Perspective, Alice Beardmore-Gray and Andrew Shennan highlight a recent study that identifies 10 novel prodromal symptoms of eclampsia, with potential to better predict which women are at risk and therefore reduce delays in intervention.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.CL) 2026-06-16

Building Customer Support AI Agents at 100M-User Scale: An Evaluation-Driven Framework

作者:
Aman Gupta↗Kevin Rossell↗Edesio Alcoba\c{c}a↗Jose Chrystian Lima Pacheco↗Carolina Baptista de Lima↗Shao Tang↗Luiz Paulo Rabachini↗Luis Moneda↗Herbert Fei↗Daniel Silva↗Rohan Ramanath↗

The rapid rise in LLM capabilities has made AI agents increasingly viable across a broad range of tasks. Among the most promising applications is building production-ready customer-facing agents, a challenge that demands coordinated excellence in evaluation methodology, context engineering, training, and online measurement. Yet these critical pillars are typically developed in isolation, creating blind spots that only surface after deployment. In this paper, we present a unified framework that bridges offline development with online impact for customer support AI agents at Nubank, a company with 100M+ users. Our approach integrates several key components: (1) structured context engineering tailored to customer support agents, (2) systematic human-in-the-loop prompt iteration, (3) rigorous LLM judge evaluation with measured inter-rater agreement and GEPA optimization for consistency, and (4) ideation-to-production validation. A central insight is that evaluation-pipeline quality directly determines iteration velocity. We present results from five production deployments spanning distinct domains: card delivery, debt management, credit-limit support, card management, and product explanation. These deployments deliver consistent customer-satisfaction gains while substantially accelerating iteration. In our card-delivery deployment, large-scale A/B testing yields a 37 percentage-point improvement in AI transactional Net Promoter Score and a 29 percentage-point gain in self-service rate over prior agent variants, alongside a strong correlation between offline simulation metrics and online outcomes, demonstrating that eval-driven development reliably predicts production impact. On most use cases, AI satisfaction reaches within a few percentage points of expert human agents.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CV) 2026-06-15

Pano3D: Unified 3D Reconstruction and Panoptic Segmentation

作者:
Victor Barberteguy↗Ahmet Iscen↗Mathilde Caron↗Alireza Fathi↗G\"ul Varol↗Cordelia Schmid↗

Recent advances in 3D feedforward reconstruction neural networks have achieved remarkable success in dense reconstruction from images without any camera parameters. Yet, equipping these models with robust semantic understanding remains an open problem. Here we introduce an approach that performs 3D reconstruction and 3D panoptic segmentation in a unified framework. We build on existing 3D reconstruction models and augment them with a set-based mask decoder. The approach is jointly trained with a geometric and semantic loss, which are shown to be mutually beneficial. More precisely, the features are initialized from the geometric information and then finetuned to capture jointly geometry and semantics. We demonstrate the generality of our approach by successfully applying our framework both to online and all-to-all attention reconstruction backbones. Our method achieves state-of-the-art performance in 3D panoptic segmentation across ScanNet, ScanNet200, and ScanNet++ datasets. Ablation studies show that such joint training of a unified model equips 3D feedforward reconstruction neural networks with panoptic segmentation and yields mutually beneficial improvements.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.AI) 2026-06-16

Demystifying Variance in Circuit Discovery of LLMs

作者:
Frank Zhengqing Wu↗Francesco Tonin↗Volkan Cevher↗

arXiv:2606.16920v1 Announce Type: cross Abstract: Circuit discovery is a key technique in mechanistic interpretability to pinpoint the model components that are crucial for performing a given task. Although the current state-of-the-art method (EAP-IG) performs well on the metric of (un)faithfulness, it suffers from substantial variability. This includes resampling variance, where the circuit changes when we probe with a new batch of data from the same distribution; rephrasing variance, where the discovered circuit shifts when the prompts are rephrased; and sample-wise variance, where a circuit with low population unfaithfulness exhibits large fluctuations in unfaithfulness across individual samples. This paper studies the roots of these variances. We demonstrate that CEAP, our new circuit discovery method that improves upon EAP-IG with a theoretical guarantee, can substantially lessen resampling variance. We further show that rephrasing variance arises because prompts with different templates tend to activate different circuits in the model. This leads us to argue that it may be challenging to find a comprehensive circuit that explains and controls the model's behavior on a task, which can be expressed in countless templates, suggesting that LLMs may be inherently hard to steer. We show that sparsity, which has been claimed to form more compact and interpretable task circuits, fails to solve this problem. Regarding sample-wise variance, we argue that it is largely benign: extremely poor unfaithfulness scores often stem from how unfaithfulness is defined, rather than from defects in the measured circuits. We show that the magnitude of unfaithfulness is affected by selective contribution scaling, a neural mechanism that accounts for the extremely poor scores sometimes observed.

阅读与讨论 → 访问原文 →
05.
arXiv (quant-ph) 2026-06-16

Detecting basis-dependent hardware errors through spatio-temporal quantum steering

作者:
Hsiang-Wei Huang↗Kuo-Feng Chiu↗Yi-Te Huang↗Jhen-Dong Lin↗Tse-Ming Chen↗Yueh-Nan Chen↗

arXiv:2606.16451v1 Announce Type: new Abstract: Spatio-temporal quantum steering provides a framework for benchmarking the nonclassicality of general quantum state transfer processes. A central diagnostic is the no-signaling-in-time (NSIT) condition, whose violation can indicate basis-dependent hardware errors. However, finite measurement statistics may also yield apparent violations, thereby obscuring the detection of basis-dependent hardware errors. To address this, we construct a statistical hypothesis test under the null hypothesis that NSIT violations arise solely from statistical fluctuations. Combining the statistical properties of NSIT violation under the null hypothesis with Chebyshev's inequality, we obtain a distribution-free upper bound on the $p$-value without parametric assumptions. We apply this method to two examples. For a single-qubit state-transfer experiment on a superconducting processor, we observe several instances that the NSIT violation is observed and the null hypothesis is simultaneously rejected by a small $p$-value, providing statistical evidence of basis-dependent hardware errors. For a seven-qubit Hayden-Preskill teleportation protocol on IonQ devices, the null hypothesis is also rejected even when the average fidelity exceeds the classical threshold, while the associated nonclassicality measure vanishes. Our results highlight the necessity of statistical hypothesis testing for detecting basis-dependent errors in near-term quantum devices.

阅读与讨论 → 访问原文 →
06.
arXiv (CS.CL) 2026-06-16

Rhythm of the Deep: A Computational-Linguistic Test of Duality of Patterning in Sperm Whale Codas

作者:
Mudit Sinha↗Sanika Chavan↗

Human language has often been described as combining structure at two levels: lower-level units combine into larger units, which then combine into larger sequences. We test for this design feature, duality of patterning, in sperm whale codas using 1,483 codas from the Dominica Sperm Whale Project. Because acoustic similarity can imitate symbolic structure, we treat the problem as computational-linguistic structure discovery from continuous audio rather than as a direct claim about language or meaning. We use a consensus of frozen audio encoders, held-out structural tests, per-statistic nulls, and acoustic-null recoverability gates. The evidence supports a narrow two-tier architecture. At the lower tier, clicks compose into codas not by a stable ordered rule, but by which clicks are present together with their inter-click rhythm. At the upper tier, coda tokens show bout-level sequential dependence, with an NSB second-order transfer-entropy lift of 0.132 bits (p = 0.002). Under tempo scaling, encoder-derived click identity is strongly rate-bound, while coda identity remains substantially more stable, yielding a measurable abstraction gradient across the click-to-coda step. Rhythm-only baselines recover substantial lower-tier structure but fail to reproduce the upper-tier sequential-dependence signal. We do not claim language, semantics, perception, or human-like phonemes. Instead, we report representation-level evidence for a duality-of-patterning-like architecture whose lower tier is rhythmic rather than segmental, and provide a portable null-controlled framework for testing combinatorial structure in induced acoustic token systems.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.AI) 2026-06-16

The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning

作者:
Haolong Qian↗Xianliang Yang↗Yinuo ma↗Lirong Che↗Feng Lu↗Ye Guo↗Lei Song↗Jiang Bian↗Chun Yuan↗

arXiv:2606.16152v1 Announce Type: new Abstract: Knowledge distillation from powerful reasoning models is widely used to improve Small Language Models (SLMs) on mathematical reasoning, often assuming that traces with higher reward model scores provide more useful supervision. We identify a counterintuitive Quality-Utility Paradox in mathematical reasoning distillation. Data refined or synthesized by a stronger Oracle obtains higher perceived quality according to reward models, yet consistently underperforms traces generated by the SLM itself and selected through rejection sampling across Qwen2.5, LLaMA-3, and DeepSeek families. Our analysis shows that Oracle refinement couples logical repair with distributional drift away from the SLM's native reasoning distribution. This drift increases the learner's adaptation cost and can outweigh the benefit of improved reasoning logic. To test this mechanism, we introduce Style-Aligned Refinement, which preserves the native trajectory of the SLM while retaining logical repair from the Oracle. This intervention lowers adaptation cost and restores downstream utility. These findings suggest that effective mathematical reasoning distillation should jointly optimize perceived solution quality and learner-data compatibility, rather than relying solely on reward-model scores. The datasets and code are available at https://github.com/Dracoqhl/Quality-Utility-Paradox.

阅读与讨论 → 访问原文 →
08.
medRxiv (Medicine) 2026-06-11

Long-term exposure to PM2.5 components and lipid profiles in WTC Health Program general responders

作者:
Krasnov↗knobel↗Hsiao-Hsien Hsu↗Teitelbaum↗Mclaughlin↗Just↗A. C↗Kloog↗Yitshak Sade↗

Fine particulate matter (PM2.5) was found to be associated with elevated blood lipids, but fewer studies have examined the associations with specific constituents of PM2.5. We studied the associations between exposure to annual PM2.5 and its 14 constituents, and repeated blood lipid measurements among general responders enrolled in the World Trade Center Health Program between 2003 and 2019 (n = 44,876). We used generalized additive mixed effect models to investigate the single-pollutant associations with repeated measures of blood total cholesterol (TC), high and low-density lipoprotein (HDL-C and LDL-C) levels. We then used linear generalized weighted quantile sum regression with a random intercept for participant ID to account for the clustering of repeated measures and evaluate the combined associations with the component mixture. A decile increase in the mixture of 14 PM2.5 chemical components was associated with 0.375 mg/dL increase in TC levels (95% confidence Interval (CI): 0.174-0.577) and 0.302 mg/dL increase in LDL-C (95% CI: 0.063, 0.540). Lead, organic carbon, and iron were major drivers of both associations. Component-specific models also show higher TC and LDL levels associated with interquartile range increases in organic carbon (0.472, 95% CI [0.027, 0.918] and 0.648 95% CI [0.136, 1.160]) and iron exposure (1.081, 95% CI [0.630, 1.532] and 0.748, 95% CI [0.318, 1.178]). In conclusion, we found PM2.5 exposure to be associated with elevated lipid levels. The associations differed by PM2.5 composition, highlighting organic carbon, lead, and iron and major drivers. These findings are highly significant for a population exposed to extreme air pollution event and susceptible to lipid alterations that might trigger cardiovascular events.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.CL) 2026-06-16

A Survey on Agentic Security: Applications, Threats and Defenses

作者:
Asif Shahriar↗Md Nafiu Rahman↗Sadif Ahmed↗Farig Sadeque↗Md Rizwan Parvez↗

LLM-based agents are now used throughout cybersecurity. While these agents facilitate powerful and autonomous security applications, their autonomy opens up new attack surfaces, and the security community is actively building defenses to secure them. Yet the literature on this subject has grown quickly and unevenly. Existing surveys treat applications, threats, and defenses in isolation, leaving no unified account of how an agent's capabilities, vulnerabilities, and countermeasures interconnect. In this work we present the first holistic survey of the agentic security landscape, structuring the field around the fundamental pillars of Applications, Threats and Defenses. We provide a comprehensive taxonomy of over 260 papers, explaining how agents are used in downstream cybersecurity applications, inherent threats to agentic systems, and countermeasures designed to protect them. In addition, we provide detailed pillar-specific and cross-cutting analyses that show the security-lifecycle coverage of agentic applications, comparison between red-teaming and blue-teaming agents, and the adversarial use of red-teaming applications. On the threat side, we analyze the entry points and agent-loop stages that attacks target, their specificity to the agentic setting, and the threat models they assume. On the defense side, we analyze the prevailing defense strategies, their cost and security trade-offs, and where in the agent lifecycle they are deployed. We further map which defenses cover which attack classes and chart trends in agent architecture, backbone model usage, data modality coverage, and the growth of attack and defense research over time. Taken together, these findings indicate that agentic systems are structurally fragile by default and that securing them will require defenses that span the full agent lifecycle rather than single-layer fixes.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.CV) 2026-06-18

Do as I Do: Dexterous Manipulation Data from Everyday Human Videos

作者:
Bhawna Paliwal↗Haritheja Etukuru↗William Liang↗Pieter Abbeel↗Nur Muhammad Mahi Shafiullah↗Jitendra Malik↗

How can we scalably generate data for robotic manipulation, especially on human-like platforms such as dexterous multi-fingered hands? Learning from human videos has recently emerged as a likely answer to this question. However, difficulties in estimating hand-object interaction and crossing the human-to-robot embodiment gap have hindered the adoption of abundant monocular RGB-only human videos as the primary source of robot manipulation data. In this work, we present DO AS I DO, an algorithm to reconstruct and retarget monocular RGB human videos to multi-fingered dexterous robotic hands. DO AS I DO reconstructs hand-object interactions from various egocentric and exocentric in-the-wild video sources. The algorithm then retargets these hand-object interaction estimates into a sequence of actions executable in the real world, yielding robot-complete manipulation data from disparate human videos. Overall, DO AS I DO outperforms previous state of the art in estimating hand-object interactions and extracting dexterous manipulation trajectories from RGB videos, as we show in experiments on datasets with ground truths and on a dataset of video clips collected online. Our experiments enable us to propose an efficacy playbook for practitioners collecting human data for manipulation.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.AI) 2026-06-12

Bag of Dims: Training-Free Mechanistic Interpretability via Dimension-Level Sign Patterns

作者:
Varun Reddy Nalagatla↗

arXiv:2606.12629v1 Announce Type: cross Abstract: We show that the standard basis of transformer hidden states already provides a training-free, architecture-general feature basis. Individual dimensions encode semantic content via their signs and confidence via their magnitudes, functioning as independent binary registers. We validate this Bag of Dims framework across three model families (Qwen 3.5-4B, Gemma 3-4B, Mistral 7B) through four progressive experiments. Sign patterns alone carry predictive content: replacing all magnitudes with unity achieves 72-93% top-5 next-token accuracy through the LM head, and pure Hamming scoring without any decoder reaches 80-90% top-4096. These sign patterns organize into semantic features: using a single-token type cache (one forward pass per vocabulary token, no context), we discover 175 categories via per-dimension sign consistency (mean AUC 0.80) from 50 anchors with zero training. A trained probe adds only +0.018 AUC and converges to axis-aligned weights, confirming negligible cross-dimension structure. This structure extends to attention: all 175 categories remain discoverable in K and V projections. On the write side, static FFN weight inspection links 20% of features to individual writer neurons (>0.70 agreement; random controls: 0%), with top-200 neuron coalitions achieving >0.70 agreement on 99.9% of prototypes via majority vote. Fully unsupervised discovery (random seeds, no labels) scales to 1500 features at 100% yield and 99% sparsity across all three models, with pairwise MI of 0.0014 bits confirming low inter-dimension coupling. These results establish that the standard basis already suffices for feature reading throughout the transformer compute pathway, requiring no training, no optimization, and no GPU-days beyond a single forward pass per vocabulary token.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.CV) 2026-06-17

GeoDisaster: Benchmarking Orchestrated Agents for Operational Disaster Geo-Intelligence

作者:
Maram Hasan↗Aman Verma↗Savitra Roy↗Hariseetharam Gunduboina↗Daksh Jain↗Muhammad Haris Khan↗Subhasis Chaudhuri↗Biplab Banerjee↗

Remote-sensing vision-language models (RS-VLMs) have advanced Earth-observation analysis toward visual interpretation and instruction-following, yet fall short of operational geo-intelligence, which demands tool-grounded spatial reasoning and structured, evidence-backed decisions. We introduce GeoDisaster, an operational geospatial disaster reasoning benchmark with 2,921 verified instances across 43 question types and five task families: deforestation monitoring, multi-hazard analysis, building-damage assessment, flood-safe routing, and Sentinel-1 SAR flood monitoring. Instances integrate heterogeneous EO/GIS evidence-optical and SAR imagery, raster masks, vector geometries, road networks, and exposure layers-spanning hazard detection, damage assessment, exposure estimation, and diagnostic report generation. Ground-truth answers are grounded in executable geospatial workflows and deterministic consistency checks, removing the need for language-model annotation. We further propose an orchestrated multi-agent framework with 18 disaster-oriented tools, where role-specialized agents coordinate through explicit execution contracts, aligned via Role-Contract Expectation Alignment (RCEA): failure-aware supervised fine-tuning combined with contract-grounded reinforcement learning over dense step-level signals. Experiments show that GeoDisaster challenges existing RS-VLMs and agentic systems, while RCEA improves tool use, evidence grounding, state consistency, and decision generation.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.AI) 2026-06-18

Controllable Quantum Memory Capacity in Quantum Reservoir Networks with Tunable partial-SWAPs

作者:
Erik L. Connerty↗Ethan N. Evans↗

arXiv:2605.12713v3 Announce Type: replace-cross Abstract: In the field of quantum reservoir computing (QRC), many different computational models and architectures have been proposed. From these models, we identify feedback-based models – which use a feedback mechanism to re-embed classical measurements from the QRC – and recurrent models – which use a multi-register approach with memory and readout qubits – as the two major competing architectures that have been discussed and validated on hardware. In this paper, we advance upon the recurrent architectures, which employ a two register approach to endow the QRC with a fading memory. While these approaches have been validated on hardware and have demonstrated great real-world performance on noisy-intermediate-scale-quantum (NISQ) quantum processing units (QPUs), the exact mechanism through which the memory capacity arises is not completely understood or fully controllable. With this, we augment the recurrent approaches and present a hardware-realizable mechanism, which we call a tunable partial-SWAP, that allows for the direct control of the rate of memory dissipation from a QRN implemented on a gate-based QPU. The theory behind this mechanism is discussed in terms of a controlled amplitude-damping channel and validation experiments using a randomized short-term memory capacity (STMC) recall benchmark and the NARMA-5 dataset are conducted using simulation and IBM QPUs, respectively.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.CV) 2026-06-19

The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation

作者:
Nicolas Dufour↗Alexei A. Efros↗Patrick P\'erez↗

The Frechet Inception Distance (FID) is the de facto arbiter of image generation, yet most papers report just a single number from a single trained model using a single sampling seed. How reproducible is that number if we retrain the model, or merely resample from it? In this paper, we treat FID as a random variable on a two-axis panel of training and generation seeds, and measure its variance directly on several hundred SiT networks trained on class-conditional ImageNet 256x256. We report surprising findings: (a) Retraining the model using the same recipe with a different seed moves FID 3.2x more (in Inception feature space) than redrawing samples from a fixed network. (b) That gap is driven by three factors: random initialisation, data ordering, and the per-step Gaussian noise of the flow-matching loss. (c) Increasing compute or model size barely tightens the spread, holding the FID coefficient of variation (CoV) inside a 1-2% band. (d) Per-cell classifier-free-guidance tuning halves the spread but reshuffles which seeds work best, and a lucky training seed reaches the same FID with up to 2x less compute than an unlucky one. Based on these findings, we recommend a new FID evaluation protocol: evaluate under per-cell optimal guidance, treat any FID gap below the empirically measured ~1.3% CoV as inconclusive, and report an error bar over several training seeds rather than a single FID number.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.AI) 2026-06-11

Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data

作者:
Masoume Gholizade↗Fabrizio Ruffini↗Pietro Ducange↗Francesco Marcelloni↗

arXiv:2606.11272v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative and privacy-preserving model training across distributed clients, but most existing FL systems implicitly assume data stationarity. In real-world settings-such as healthcare, industrial IoT (IIOT), cybersecurity, and smart cities-data streams are inherently non-stationary, leading classical FL methods to suffer from performance degradation, instability, and catastrophic forgetting. Continual Learning (CL) addresses learning under evolving data distributions but has been largely studied in centralized settings, overlooking key constraints of federated systems, including privacy, limited communication, and client heterogeneity. Federated Continual Learning (FCL) emerges at the intersection of FL and CL, aiming to support lifelong, adaptive, and privacy-aware learning over distributed and non-stationary data. This survey provides a comprehensive and systematic overview of FCL. We first present a formal definition of the FCL problem and clarify its distinctive characteristics. We then analyze the limitations of classical FL under non-stationary conditions, highlighting how CL principles support long-term adaptation. To organize the rapidly growing literature, we propose a multi-dimensional taxonomy of FCL approaches. Furthermore, we review representative application domains and data modalities, summarize commonly used evaluation metrics, and discuss experimental perspectives for assessing long-term performance and forgetting. Finally, we highlight key open challenges, including handling extreme heterogeneity under temporal drift, designing scalable and privacy-preserving memory mechanisms, and establishing standardized benchmarks. This survey aims to serve as a reference and a roadmap for advancing FCL toward robust and deployable real-world systems.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.AI) 2026-06-15

FlexMS: A Unified Public Benchmark for Molecule Tandem Mass Spectrum Prediction

作者:
Yunhua Zhong↗Yixuan Tang↗Yifan Li↗Pan Liu↗Zhiwen Yang↗Jie Yang↗Jun Xia↗

arXiv:2602.22822v3 Announce Type: replace Abstract: Tandem mass spectrometry (MS/MS) is central to small molecule identification, but current deep learning systems for spectrum prediction still remain difficult to evaluate and deploy in practice. While novel architectures constantly claim state-of-the-art performance, inconsistent metadata conditioning and entangled preprocessing pipelines hinder fair architectural comparisons. Besides, existing evaluations are often restricted to curated datasets, failing to capture the heterogeneity and cross-domain shifts of real-world metabolomics. Furthermore, current benchmarks lack difficulty-aware diagnostics and leave blind to how models behave under specific compute or data constraints. To address this, we present FlexMS, a modular public-data benchmark framework that standardizes MS/MS prediction across public resources while keeping molecular encoders, metadata conditioning, predictor heads, and downstream retrieval under one protocol. FlexMS establishes a fair evaluation playground which significantly lowers the barrier for integrating new predictive tools. Rather than solely optimizing for average scores, FlexMS augments aggregate accuracy with difficulty-aware diagnostics, providing actionable guidance on model selection across different compute constraints, data scales, and downstream retrieval objectives. Ultimately, FlexMS provides the community with a reproducible standard to identify which algorithmic conclusions are stable and which operating points are most viable in practice.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.LG) 2026-06-17

Robust Local Polynomial Regression with Similarity Kernels

作者:
Yaniv Shulman↗

arXiv:2501.10729v3 Announce Type: replace-cross Abstract: Local Polynomial Regression (LPR) is a widely used nonparametric method for modeling complex relationships due to its flexibility and simplicity. It estimates a regression function by fitting low-degree polynomials to localized subsets of the data, weighted by proximity. However, traditional LPR is sensitive to outliers and high-leverage points, which can significantly affect estimation accuracy. This paper revisits the kernel function used to compute regression weights and proposes a novel framework that incorporates both predictor and response variables in the weighting mechanism. The focus of this work is a conditional density kernel that robustly estimates weights by mitigating the influence of outliers through localized density estimation. The proposed method is implemented in Python and is publicly available at https://github.com/yaniv-shulman/rsklpr. The population analysis quantifies the bias induced by density-based robust weighting, and the reported experiments show lower empirical bias than iterative robust LOWESS while remaining competitive with standard LOWESS. This advancement provides a promising extension to traditional LPR, opening new possibilities for robust regression applications.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.CL) 2026-06-16

Evaluating LLM Personalization via Semantic Constraint Verification

作者:
Xuran Li↗Guanqin Zhang↗Imran Razzak↗Hakim Hacid↗Eleanna Kafeza↗Hao Xue↗Flora D. Salim↗

Current evaluation paradigms for Large Language Model (LLM) personalization rely heavily on brittle surface-matching metrics or computationally expensive LLM-as-a-judge protocols, both of which lack interpretability. To address these limitations, we introduce Natural Language Inference Constraint Verification (NLICV), a scalable, semantically invariant framework that maps sentence meanings to truth-condition sets to verify personalization constraints via a Natural Language Inference (NLI) model. Moving beyond binary scoring, NLICV categorizes LLM behaviors into four distinct modes: personalization, generalization, sycophancy, and failure. Extensive experiments demonstrate that NLICV aligns closely with human annotations while drastically reducing the latency and token costs associated with LLM judges (up to 2100 inference speedup). Finally, through an ablation-based procedure, NLICV pinpoints the exact sentences driving the constraint verification, yielding faithful, understandable evidence for its evaluations.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.LG) 2026-06-19

Do Vision-Language Models Understand 3D Scenes or Just Catalogue Objects?

作者:
Animesh Maheshwari↗Divyansh Sahu↗Nishit Verma↗

arXiv:2605.20448v2 Announce Type: replace-cross Abstract: Vision-language models reliably name objects in a scene, but do they represent the 3D layout those objects inhabit? We introduce a 3,034-sample human-curated benchmark targeting three components of spatial understanding: depth-ordered occlusion (probed via three independent counterfactual operationalisations), optical-geometry inference over visible reflections, and volumetric rearrangement planning. Six frontier and open-weight VLMs, scored by trained annotators on 18,204 responses with no LLM-as-judge, reveal a sharp dissociation: models that plan rearrangements over visible layouts at 53–97% accuracy and rarely violate collision constraints fall to 6–45% on occlusion and below 7% on reflections. An embodied-reasoning model reproduces the same profile. White-box analysis on Qwen3-VL-8B-Thinking localises the failure to the visual-token merger: spatial information recoverable throughout the vision encoder becomes inaccessible after token compression and only stabilises again when clean post-merger activations are patched into the language decoder.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.CV) 2026-06-17

BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLM

作者:
Haiquan Wen↗Tianxiao Li↗Zhenglin Huang↗Yiwei He↗Guangliang Cheng↗

The rapid advancement of generative AI has substantially improved image and video synthesis, amplifying the risk of multimodal visual misinformation. Recent MLLMs have shown promise for transparent AI-generated content detection through reasoning and explanation, yet existing approaches largely treat image and video forensics as isolated tasks, leaving cross-modal synergies underexplored. To address this, we present BusterX++, a unified MLLM for joint image and video detection with interpretable reasoning. We also introduce GenBuster-Bench++, a meticulously curated, difficulty-aligned benchmark containing balanced image and video samples spanning recent generation models and diverse real-world scenarios. Using this controlled setting, we revisit the widely adopted $SFT \rightarrow RL$ post-training paradigm. Notably, our findings demonstrate that a single-stage, pure RL strategy driven strictly by sparse outcome rewards consistently matches or surpasses a strong SFT+RL baseline across both unified and single-modality settings. Our key insight reveals that SFT imposes lower policy entropy, which restricts the policy search space and dampens exploratory freedom. In contrast, single-stage pure RL maintains higher policy entropy throughout training, effectively unlocking the spontaneous emergence of cross-modal capability transfer between image and video forensics. Extensive experiments demonstrate that BusterX++ achieves state-of-the-art performance, highlighting the powerful potential of RL for unified cross-modal visual reasoning.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.CL) 2026-06-11

Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases

作者:
Zhao Tan↗Yiji Zhao↗Shiyu Wang↗Chang Xu↗Yuxuan Liang↗Xiping Liu↗Shirui Pan↗Ming Jin↗

Natural Language Querying for Time Series Databases (NLQ4TSDB) aims to assist non-expert users retrieve meaningful events, intervals, and summaries from massive temporal records. However, existing Text-to-SQL methods are not designed for continuous morphological intents such as shapes or anomalies, while time series models struggle to handle ultra-long histories. To address these challenges, we propose Sonar-TS, a neuro-symbolic framework that tackles NLQ4TSDB via a Search-Then-Verify pipeline. Analogous to active sonar, it utilizes a feature index to ping candidate windows via SQL, followed by generated Python programs to lock on and verify candidates against raw signals. To enable effective evaluation, we introduce NLQTSBench, the first large-scale benchmark designed for NLQ over TSDB-scale histories. Our experiments highlight the unique challenges within this domain and demonstrate that Sonar-TS effectively navigates complex temporal queries where traditional methods fail. This work presents the first systematic study of NLQ4TSDB, offering a general framework and evaluation standard to facilitate future research.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.CL) 2026-06-15

LoSoNA: A Benchmark for Local Social Norm Adaptation in Group Conversations

作者:
Mateusz Winiarek↗Maksymilian Bilski↗Mateusz Jacniacki↗

Online group chats are social spaces with local conversational norms that are rarely stated explicitly. The ability and willingness of LLM-based agents to recognize and adapt to these norms remains mostly unexplored. We introduce LoSoNA, a benchmark for local social norm adaptation in multi-party chat. Each scenario gives a subject model a curated group-chat transcript in which non-subject participants demonstrate a hidden local norm, followed by a final elicitor turn that forces a response revealing whether the subject has inferred that norm. We evaluate eight frontier and open-weight models under four prompting conditions that vary how explicitly the model is told to treat the prior conversation as evidence for how it should answer. Naive prompting remains limited for most models; explicit norm-aware prompting helps unevenly, with Gemini 3.1 Pro reaching $84.2\%$ and Claude Fable 5 reaching $81.6\%$, while several other models show small gains or regressions. LoSoNA contributes to recent calls for evaluating LLM social capabilities by testing whether models can infer local conversational norms from precedent and use them in a one-turn group-chat response.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.CL) 2026-06-19

Detecting Hallucinations for Large Language Model-based Knowledge Graph Reasoning

作者:
Xinyan Zhu↗Yaoqi Liu↗Yue Gao↗Huadong Ma↗Cheng Yang↗Chuan Shi↗

Knowledge graph (KG) reasoning infers new knowledge from existing facts and is widely applied in question answering, recommendation, and decision support. With the rapid development of large language models (LLMs), LLM-based KG reasoning frameworks have become increasingly popular by leveraging retrieved KG information. However, hallucinations in LLMs remain a critical issue. Even when relevant KG knowledge is incorporated, models may still generate incorrect outputs, leading to misinformation and unreliable decisions. Existing hallucination detection methods either focus on LLM internal states or verify consistency with retrieved contexts, but both overlook the structural information in KGs, resulting in suboptimal performance. To address this gap, we propose LUCID, the first halLUcination deteCtIon method for LLM-based knowleDge graph reasoning frameworks. LUCID jointly leverages LLM attention scores, KG semantics, and structural information. Specifically, it extracts node and edge features from attention scores and semantic similarities, and integrates them with KG structure using a graph neural network. We also construct manually annotated benchmark datasets for evaluation. Experiments on nine datasets show that LUCID achieves state of the art performance compared to 15 baselines.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.CL) 2026-06-11

Cross-Layer Discrete Concept Discovery for Interpreting Language Models

作者:
Ankur Garg↗Xuemin Yu↗Hassan Sajjad↗Samira Ebrahimi Kahou↗

Interpreting language models remains challenging due to the existence of residual stream, which linearly mixes and duplicates features across adjacent layers, causing single-layer analyses to miss this cross-layer structure. Cross-layer sparse autoencoders (SAEs) address layer mixing but operate in continuous space, where concepts split across many neurons without clear boundaries. We introduce Cross-Layer Vector Quantized-Variational Autoencoder (CLVQ-VAE), a novel framework which maps representations from a lower layer to a higher layer through a discrete vector-quantization bottleneck, collapsing duplicated residual-stream features into compact, interpretable concept vectors. Our approach combines top-k temperature-based sampling with exponential moving average (EMA) codebook updates, providing controlled exploration of the discrete latent space while maintaining codebook diversity. Across both encoder- and decoder-based models on ERASER-Movie, Jigsaw, and AGNews, CLVQ-VAE outperforms clustering, single-layer vector quantized-variational autoencoder (VQ-VAE), and sparse autoencoder (SAE) baselines across three evaluation axes: removing identified concepts drops model accuracy by up to 93%, LLM judges rank our concepts first in 66.7% of comparisons, and human annotators recover model predictions from our visualizations with 78% accuracy versus 54% for clustering.

阅读与讨论 → 访问原文 →