探索全球前沿学术脉络

01.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.14832

PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions

作者:

Chenxin Li↗Zhengyao Fang↗Zhengyang Tang↗Pengyuan Lyu↗Xingran Zhou↗Xin Lai↗Fei Tang↗Liang Wu↗Yiduo Guo↗Weinong Wang↗Junyi Li↗Yi Zhang↗…

Phone agents are increasingly expected to complete real mobile workflows rather than merely predict the next screen action. However, much of the current mobile-agent literature still evaluates agents primarily as GUI controllers that observe a screen, emit taps and swipes, and are scored by target app state. Real phone-use tasks are broader: they require deciding when to use app GUIs, device-side commands, or structured tools, while leaving evidence that the intended side effect actually occurred. We introduce PhoneHarness, a mixed-action benchmark and execution harness for studying phone-use agents on verifiable mobile workflows. PhoneHarness runs a device-side agent loop over GUI, CLI, and host-side tool actions, combining deterministic action routing with bounded GUI delegation and auditable execution traces. Its benchmark, PhoneHarness Bench, evaluates whether agents complete tasks with observable side effects, not only whether they produce plausible final answers. On the annotated evaluation split, PhoneHarness reaches a 75.0% pass rate, outperforming the strongest non-PhoneHarness settings by 12.9 percentage points. PhoneHarness and PhoneHarness Bench therefore play distinct but mutually dependent roles: the harness makes mixed phone workflows executable, while the benchmark measures whether agents can use that harness reliably and safely. Our findings suggest that reliable phone automation depends on action-surface routing and verifiable execution, not only visual GUI control.

阅读与讨论 → 访问原文 →

02.

medRxiv (Medicine) 2026-06-15 DOI: HASH:dfaacf92e7c80e9ee1c4b62852689ed8

Repurposing cardiovascular disease risk models to predict incident and co-occurring cardiovascular, cardiometabolic and neurocognitive outcomes.

作者:

Quill↗Chaturvedi↗van Vugt↗Hingorani↗A. D↗Schmidt↗A. F↗

Background: Cardiovascular disease (CVD), cardiometabolic and neurocognitive conditions share risk factors and frequently co-occur. We evaluated whether four established CVD risk prediction models (QRISK3, PCE, SCORE2, SCORE2-OP) can be repurposed to predict 10-year risk of these conditions and their co-occurrence with CVD. Methods: The models were recalibrated using 20% of the UK Biobank (UKB) and evaluated in the remaining 80%. We performed external validation using data from Clinical Practice Research Datalink (CPRD) Aurum, assessing model discrimination (c-statistics) and calibration (intercept and slope). We used permuted feature importance to determine the influence of each individual predictor in the models. Results: Depending on the model, the c-statistics for incident CVD ranged from 0.71 to 0.74 in the UKB test set (16,137 events). Discrimination was equal to or higher than CVD when evaluated against non-traditional CVD outcomes: 0.74 to 0.77 for heart failure (3,471 events), 0.72 to 0.73 for atrial fibrillation (9,213 events), 0.73 to 0.75 for peripheral arterial disease (1,927 events) and 0.80 to 0.82 for abdominal aortic aneurysm (595 events). For the multimorbidity endpoints, model discrimination ranged from 0.74 for the composite of CVD and T2DM (SCORE2-OP) to 0.83 for the composite of CVD and dementia or Parkinson's disease (QRISK3). When considering the onset of any cardiovascular, cardiometabolic, or neurocognitive outcome discrimination ranged from 0.71 to 0.72. The repurposed models slightly underestimated the predicted risk in the CPRD compared to the UKB: average difference in calibration intercept was at most -0.64. After age and sex, smoking status and systolic blood pressure contributed most to model predictions. Conclusions: Repurposed CVD models can be used to identify 10-year risk of many CVD-related conditions and their multimorbidity. These may be used to support risk-based approaches to prevention and screening. The repurposed models have been made available at: https://repurposed-cvd-risk-models.shinyapps.io/cvd_cmd_dementia_app/ Keywords: Risk prediction; cardiovascular disease; cardiometabolic disease; dementia; disease prevention.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2601.05746

DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation

作者:

Zhenghao Li↗Zhi Zheng↗Wei Chen↗Jielun Zhao↗Yong Chen↗Tong Xu↗Enhong Chen↗

arXiv:2601.05746v2 Announce Type: replace Abstract: Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving. Researchers have further investigated Multi-Agent Debate (MAD) frameworks, which enhance the reasoning and collaboration capabilities of MAS through information exchange and debate among multiple agents. However, existing approaches often rely on unguided initialization, causing agents to adopt identical reasoning paths that lead to the same errors. As a result, effective debate among agents is hindered, and the final outcome frequently degenerates into simple majority voting. To solve the above problem, we introduce Dynamic Multi-Agent Debate (DynaDebate), which enhances the effectiveness of multi-agent debate through three key mechanisms: (1) Dynamic Path Generation and Allocation, which employs a dedicated Path Generation Agent to generate diverse and logical solution paths with adaptive redundancy; (2) Process-Centric Debate, which shifts the focus from surface-level outcome voting to rigorous step-by-step logic critique to ensure process correctness; (3) A Trigger-Based Verification Agent, which is activated upon disagreement and uses external tools to objectively resolve deadlocks. Experiments show that DynaDebate achieves superior or highly competitive performance across the majority of benchmarks\footnote{The code is at https://github.com/nwpuLee2021/brianstorm.}.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18797

Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports

作者:

Qingyu Lu↗Ruochen Li↗Liang Ding↗Yufei Xia↗Youxiang Zhu↗Dacheng Tao↗

Reliable evaluation of generated radiology reports requires strict clinical accuracy, as omitted critical findings or mischaracterized radiographic observations can directly affect patient care. Existing metrics obscure this requirement by reducing report quality to a medically ungrounded scalar. Although Large Language Models (LLMs) possess rich medical knowledge, they likewise struggle to draw a reliable boundary between clinically significant errors and harmless variation. We study this boundary using ReEvalMed benchmark as testbed and evaluate metric-level clinical significance from detecting true clinical errors ("Discrimination") and tolerating insignificant variations ("Robustness"). Across 8 LLM evaluators under one-pass and two-pass settings, we identify a widespread discrimination bias: models effectively detect errors but also over-penalize harmless rephrasings. To mitigate this, we synthesize 4k report pairs and train lightweight interpretable metrics on Qwen3-8B and MedGemma-4B. Our trained metric sharpens the clinical significance boundary, surpassing 32B-scale medical LLMs and remaining competitive with proprietary models. Crucially, the more costly two-pass setting fails to consistently improve overall performance and mainly trades discrimination for robustness. These findings suggest one-pass trained metrics as the practical choice for cost-sensitive deployment, with two-pass inference reserved for settings where D-R balance is critical. We will release the dataset and metric.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2603.09344

Robust Regularized Policy Iteration under Transition Uncertainty

作者:

Hongqiang Lin↗Zhenghui Fu↗Weihao Tang↗Pengfei Wang↗Yiding Sun↗Qixian Huang↗Dongxu Zhang↗

arXiv:2603.09344v3 Announce Type: replace Abstract: Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift. The learned policy may visit out-of-distribution state-action pairs where value estimates and learned dynamics are unreliable. To address policy-induced extrapolation and transition uncertainty in a unified framework, we formulate offline RL as robust policy optimization, treating the transition kernel as a decision variable within an uncertainty set and optimizing the policy against the worst-case dynamics. We propose Robust Regularized Policy Iteration (RRPI), which replaces the intractable max-min bilevel objective with a tractable KL-regularized surrogate and derives an efficient policy iteration procedure based on a robust regularized Bellman operator. We provide theoretical guarantees by showing that the proposed operator is a $\gamma$-contraction and that iteratively updating the surrogate yields monotonic improvement of the original robust objective with convergence. Experiments on D4RL benchmarks demonstrate that RRPI achieves strong average performance, outperforming recent baselines including percentile-based methods on the majority of environments while remaining competitive on the rest. Moreover, RRPI exhibits robust performance by aligning lower $Q$-values with high epistemic uncertainty, which prevents the policy from executing unreliable out-of-distribution actions.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2605.05481

Approximate Next Policy Sampling: Replacing Conservative Target Policy Updates in Deep RL

作者:

Dillon Sandhu↗Ronald Parr↗

arXiv:2605.05481v2 Announce Type: replace Abstract: We revisit a classic "chicken-and-egg" problem in reinforcement learning: to safely improve a policy, the value function must be accurate on the state-visitation distribution of the updated policy. That distribution over states is unknown and cannot be sampled for the purposes of training the value function. Conservative updates solve this problem, but at the cost of shrinking the policy update. This paper explores an alternative solution, Approximate Next Policy Sampling (ANPS), which addresses the problem by modifying the training distribution rather than constraining the policy update. ANPS is satisfied if the distribution of the training data approximates that of the next policy. To demonstrate the feasibility and efficacy of ANPS, we introduce Stable Value Approximate Policy Iteration (SV-API). SV-API modifies the standard approximate policy iteration loop to hold the target policy fixed while an iteratively updated behavioral policy gathers relevant experience. It only commits to a new policy once a convergence criterion has been met. If certain stability criteria are met, the update is guaranteed to be safe; otherwise, it remains no less safe than standard approximate policy iteration. Applying SV-API to PPO yields Stable Value PPO (SV-PPO), which matches or improves performance on high-dimensional discrete (Atari) and continuous control benchmarks while executing substantially larger target policy updates. These results demonstrate the viability of ANPS as a new solution to this classic challenge in RL.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17973

Fine-tuning LLMs for Passive Depression Severity Estimation from AI Mental Health Dialogue

作者:

Olivier Tieleman↗Ziyi Zhu↗Ting Su↗Samuel J. Bell↗Thomas D. Hull↗Caitlin A. Stamatis↗

Depression is the leading cause of disability worldwide, and early detection of symptom change is essential for timely intervention. Validated instruments such as the Patient Health Questionnaire-9 (PHQ-9) support symptom monitoring at scale, but real-world completion rates are low, introducing response bias and systematic missingness. Passive approaches that infer severity from routinely generated data could close this gap. We address this by predicting PHQ-9 total scores directly from transcripts of conversations between users and an AI mental health application, requiring only conversation text and no additional clinical data. We fine-tune a Qwen3.5-27B backbone with a regression head, augment 3,111 ground-truth labels with pseudolabels generated by a reasoning model (Claude Opus) and iteratively trained intermediate models, for a combined dataset of 6,283 users. On a held-out test set of 842 users, our best model achieves MAE = 2.6, RMSE = 4.0, Pearson r = 0.80, and AUC = 0.91 at the PHQ-9 >= 10 clinical threshold. We also find AUC > 0.87 at every severity threshold from PHQ-9 >= 3 to PHQ-9 >= 24, demonstrating that the model captures depression severity across the full clinical spectrum. This work opens the door to passive, continuous symptom monitoring in AI mental health platforms, without requiring users to complete self-report measures.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2603.07920

RLPR: Radar-to-LiDAR Place Recognition via Two-Stage Asymmetric Cross-Modal Alignment for Autonomous Driving

作者:

Zhangshuo Qi↗Jingyi Xu↗Luqi Cheng↗Shichen Wen↗Guangming Xiong↗

All-weather autonomy is critical for autonomous driving, which necessitates reliable localization across diverse scenarios. While LiDAR place recognition is widely deployed for this task, its performance degrades in adverse weather. Conversely, radar-based methods, though weather-resilient, are hindered by the general unavailability of radar maps. To bridge this gap, radar-to-LiDAR place recognition, which localizes radar scans within existing LiDAR maps, has garnered increasing interest. However, extracting discriminative and generalizable features shared between modalities remains challenging, compounded by the scarcity of large-scale paired training data and the signal heterogeneity across radar types. In this work, we propose RLPR, a robust radar-to-LiDAR place recognition framework compatible with single-chip, scanning, and 4D radars. We first design a dual-stream network to extract structural features that abstract away from sensor-specific signal properties (e.g., Doppler or RCS). Subsequently, motivated by our task-specific asymmetry observation between radar and LiDAR, we introduce a two-stage asymmetric cross-modal alignment (TACMA) strategy, which leverages the pre-trained radar branch as a discriminative anchor to guide the alignment process. Experiments on four datasets demonstrate that RLPR achieves state-of-the-art recognition accuracy with strong zero-shot generalization capabilities.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.17464

CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models

作者:

Jeffrey G. Wang↗Jason Wang↗Marvin Li↗Seth Neel↗

arXiv:2606.17464v1 Announce Type: new Abstract: Membership inference attacks (MIAs) are a canonical way to assess a machine learning model's privacy properties. Although several attempts have been made to evaluate MIAs on language models, the extant literature has suffered numerous difficulties in constructing clean evaluations to test new techniques. In particular, subtle distribution shifts between member and non-member sets can undermine the statistical validity of MIAs; recent work has underscored this by showing that "blind" methods with no access to the underlying model can perform far better than published methods on the same benchmarks. This paper constructs a benchmark for principled evaluation of MIAs against LLMs, by leveraging the insight that training data before and after a fixed point during training are drawn from the same distribution. Therefore, all open-source models with intermediate checkpoints and public training data can be converted into MIA testbeds. We apply our framework to a half-dozen published attacks on the Pythia and OLMo family of models, from 70M to 7B parameters. To facilitate further privacy research, we open-source a modular library for designing and implementing attacks in this setting: https://github.com/safr-ai-lab/pandora_llm.

阅读与讨论 → 访问原文 →

10.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2506.06010

Magnetic control of an exciton-polariton condensate in a van der Waals magnet

作者:

Heng Zhang↗Niloufar Nilforoushan↗Christian Weidgans↗Tobias Inzenhofer↗Marlene Liebich↗Josef Riepl↗Julian Hirschmann↗Imke Gronwald↗Kseniia Mosina↗Zden\v{e}k Sofer↗Ritaj Tyagi↗Jan Wilhelm↗…

arXiv:2506.06010v3 Announce Type: replace-cross Abstract: Quasiparticle condensates are among the most spectacular solid-state manifestations of quantum physics. Coupling macroscopic real-space wavefunctions to additional degrees of freedom, such as the electron spin, would add valuable control knobs for quantum applications. While creating spin-carrying superconducting condensates has attracted enormous attention, man-made condensates of light-matter hybrids known as exciton-polaritons have lacked an analogous spin-based perspective. Here we open a new door by demonstrating magnetically tunable exciton-polariton condensation in the van der Waals magnet CrSBr. Under photoexcitation, CrSBr microwires embedded in an optical cavity show the hallmarks of polariton condensation: a dramatic increase of the emission intensity from an excited laterally confined polariton state by multiple orders of magnitude, spectral narrowing of the emission line, and a continuous shift of the peak energy. Interferometry evidences an increase in spatial and temporal coherence. Owing to the strong coupling between the spin order and excitonic correlation, the energy of the condensate can be tuned by up to 10.5 meV by an external magnetic field of only 2 Tesla. Our results establish CrSBr microcavities as a powerful platform for exploring magnetic control of polariton condensates and mark a significant step toward spin-controlled coherent quantum light sources.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18530

Evaluating Prompting-Based Defenses Against Domain-Camouflaged Injection Attacks

作者:

Aaditya Pai↗

Domain-camouflaged injection attacks embed malicious instructions in retrieved content using domain-appropriate vocabulary, evading standard detectors that rely on syntactic injection markers. When detection fails, practitioners need to know which defense architectures reduce attack success. We evaluate five prompting-based defenses (spotlighting, paraphrasing, prompt sandwiching, and two combinations) against domain-camouflaged injection across three model families (Claude Haiku, Llama 3.1 8B, Gemini 2.0 Flash) and three deployment domains (financial, legal, general) using 3,510 trials. Paraphrasing retrieved content before agent processing is the most consistently effective defense in this benchmark, reducing camouflage attack success rate by 55-84\% depending on model, and achieves lower attack success rates than our Llama Guard 4 configuration on every model tested. Defense effectiveness is strongly model-dependent: spotlighting halves attack success on Claude Haiku but provides no benefit on Llama 3.1 8B. Financial domain deployments face the highest residual risk at 26-33\% baseline attack success rate, with no prompting-based defense fully eliminating the threat on weaker models. These results provide the first systematic evaluation of prompting-based defenses specifically against camouflage-class injection attacks and establish benchmark-based recommendations for practitioners. All tasks use synthetically constructed professional documents; whether these benchmark rankings generalize to real enterprise documents remains an open question.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14353

Can Deep Neural Networks Improve Compression of Very Large Scientific Data?

作者:

Muhannad Alhumaidi↗Guozhong Li↗Spiros Skiadopoulos↗Panos Kalnis↗

arXiv:2606.14353v1 Announce Type: new Abstract: Error-bounded lossy compression is a fundamental technique for managing the rapidly growing volumes of scientific data produced by modern simulations and observational instruments. Most state-of-the-art-compressors follow a prediction-residual paradigm, where compression effectiveness depends on the quality of the predictor: more accurate predictions generate smaller residuals that are easier to compress. This observation raises a question: can modern machine learning models serve as superior predictors for scientific data compression? Answering this question directly is challenging because developing compression-specific ML predictors requires substantial resources. Instead, we leverage the climate domain where highly accurate pretrained weather forecasting foundation models already exist, making them an ideal testbed. We present a framework that integrates spatial and temporal deep learning models into a conventional error-bounded compression pipeline. The framework supports auto-regressive forecasting models and avoids error accumulation. Using ERA5 climate data as a representative large-scale scientific dataset, we evaluate three distinct ML predictors: a VAEformer-based codec (CRA5), a graph neural network forecaster (GraphCast), and a vision-transformer forecaster (Aurora), against the state-of-the-art compressor SZ3.1 under identical quantization and entropy-coding backends. Our evaluation over approximately 1.7 TB of data reveals a surprising result: although ML predictors generate more accurate predictions and can improve reconstruction quality by up to 91% while achieving up to 9.6x higher compression ratios for highly predictable variables, they do not improve overall dataset-level compression ratio. We show that prediction accuracy alone is insufficient: the spatial structure of the resulting residuals plays a decisive role in entropy coding efficiency.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18588

Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication

作者:

Wenqi Jia↗Zhewen Hu↗Ying Huang↗Yu Gong↗Stavros Kalafatis↗Yuke Wang↗Wei Niu↗Chengming Zhang↗Ang Li↗Sheng Di↗Yuede Ji↗Bo Fang↗…

3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated regions, causing global inconsistency, or rely on global Gaussian-level exchanges, which lead to substantial growth in inter-GPU communication and quickly dominate iteration time. We propose Splaxel, a communication-efficient distributed 3DGS training framework based on pixel-level local rendering and global composition. Instead of synchronizing Gaussians, each GPU renders its local subset and exchanges only partial pixel values, maintaining mathematical consistency while keeping communication cost stable as the scene size increases. Splaxel further reduces pixel-level redundancy through geometric and transmittance visibility prediction and improves GPU utilization via conflict-free camera-view consolidation. Evaluated on large-scale datasets with up to 120M Gaussians, Splaxel achieves up to 7.6$\times$ speedup over the state-of-the-art distributed 3DGS framework while preserving high reconstruction quality.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2509.18428

Latent Action Pretraining Through World Modeling

作者:

Bahey Tharwat↗Yara Nasser↗Ali Abouzeid↗Ian Reid↗

Vision-Language-Action (VLA) models have gained popularity for learning robotic manipulation tasks that follow language instructions. State-of-the-art VLAs, such as OpenVLA and $\pi_{0}$, were trained on large-scale, manually labeled action datasets collected through teleoperation. More recent approaches, including LAPA and villa-X, introduce latent action representations that enable unsupervised pretraining on unlabeled datasets by modeling abstract visual changes between frames. Although these methods have shown strong results, their large model sizes make deployment in real-world settings challenging. In this work, we propose LAWM, a model-agnostic framework to pretrain imitation learning models in a self-supervised way, by learning latent action representations from unlabeled video data through world modeling. These videos can be sourced from robot recordings or videos of humans performing actions with everyday objects. Our framework is able to transfer learned knowledge across tasks, environments, and embodiments. It outperforms models pretrained with ground-truth robot actions and other similar pretraining methods on the LIBERO benchmark and real-world setup, while being efficient and practical for real-world settings.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.13870

Mirage Probes: How Vision Models Fake Visual Understanding

作者:

Daniel Ben-Levi↗Judah Goldfeder↗Weiliang Zhao↗Raz Lapid↗Amit LeVi↗Allen G. Roush↗Ravid Shwartz-Ziv↗Hod Lipson↗

Vision-language models (VLMs) can answer image-based questions confidently, and often correctly, even when no image is provided. This mirage behavior inflates benchmark scores without reflecting visual grounding. Prior work treats this as a single failure mode. We argue it is two. Using Mirage Probes, a contrastive probing framework that pairs paraphrased question variants with matched mirage and non-mirage labels on the same image, we show that mirage behavior is linearly decodable from internal activations across residual stream, MLP, post-attention, and attention-head sites in two open-source VLMs. We demonstrate that a Naive Bayes text baseline cannot recover this signal, ruling out surface lexical confounds. Cross-benchmark separability patterns, together with a novel Prior Harnessing Index (PHI) measuring how much a model can answer from text alone, expose two distinct regimes: textual biases, where the model answers from language priors without engaging visual representations, and spurious images, where it constructs false visual content in latent space and answers as if grounded. The distinction has direct mitigation consequences: text-distribution cleaning can address the first regime but cannot reach the second, since spurious-image mirages live in the model's visual representations rather than its text. Faithful visual grounding will require interventions at the representational level.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2602.00593

Pix2Fact: When Vision Is Not Enough – Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes

作者:

Yifan Jiang↗Cong Zhang↗Bofei Zhang↗Qiaofeng Zheng↗Yifan Yang↗Bingzhang Wang↗Yew-Soon Ong↗

Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and external knowledge, a synergy overlooked by existing benchmarks that evaluate these abilities in isolation. To fill this void, we introduce Pix2Fact, a visual question-answering benchmark designed to assess expert-level visual perception and knowledge search. Pix2Fact comprises 1,000 high-resolution (4K+) images spanning eight scenarios. Its questions and answers are meticulously crafted by PhD-holding annotators from top global universities across diverse disciplines. Each question requires detailed visual grounding and the integration of external knowledge. Evaluating ten state-of-the-art VLMs, including proprietary models such as Gemini-3.1-Pro and GPT-5.4, we find that Pix2Fact poses a formidable challenge: the most advanced model (Gemini-3.1-Pro) achieves only 51.7% average accuracy, even with access to visual ground truth and search tools. Our analysis attributes this low accuracy to three factors, frequent visual grounding errors even with visual ground truth, shallow search harnessing, and VLM's inability to retrieve long-tail, unstructured local information. This striking gap exposes the limitations of current models in assisting humans with real-world scenarios that demand overwhelming visual comprehension. We believe Pix2Fact will serve as a critical benchmark to drive the next generation of language-vision agents that seamlessly integrate fine-grained perception with robust knowledge search.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2312.06173

Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion

作者:

Anke Tang↗Xianglin Luo↗Li Shen↗Yong Luo↗Liang Ding↗Han Hu↗Bo Du↗Dacheng Tao↗

arXiv:2312.06173v2 Announce Type: replace Abstract: Merging models fine-tuned from a common, extensively pre-trained large model but specialized for different tasks has been demonstrated as a cheap and scalable strategy to construct a multi-task model that performs well across diverse tasks. Recent research, exemplified by task arithmetic, highlights that this multi-task model can be derived through arithmetic operations on task vectors. Nevertheless, current merging techniques frequently resolve potential conflicts among parameters from task-specific models by evaluating individual attributes, such as the parameters' magnitude or sign, overlooking their collective impact on the overall functionality of the model. In this work, we propose the CONtinuous relaxation of disCRETE (Concrete) subspace learning method to identify a common low-dimensional subspace and utilize its shared information to track the interference problem without sacrificing much performance. Specifically, we model the problem as a bi-level optimization problem and introduce a meta-learning framework to find the Concrete subspace mask through gradient-based techniques. At the upper level, we focus on learning a shared Concrete mask to identify the subspace, while at the inner level, model merging is performed to maximize the performance of the merged model. We conduct extensive experiments on both vision domain and language domain, and the results demonstrate the effectiveness of our method. The code is available at https://github.com/tanganke/subspace_fusion

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11262

PermDoRA – Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry

作者:

Gowtham Sivaramakrishnan↗Sarvesha Kumar Kombaiah Seetha↗Kishan Gupta Balaji↗Santhosh Baradwaj Vaduvur Ranganathan↗

arXiv:2606.11262v1 Announce Type: cross Abstract: Access control in large language models (LLMs) requires modular mechanisms to enable domain-specific behavior without retraining or cross-domain interference. A common hypothesis is that interference during adapter composition arises from overlap in linear parameter updates, suggesting that enforcing orthogonality or directional independence should improve multi-domain performance. We test this hypothesis using DoRA-RBAC, a hierarchical adapter composition framework based on weight-decomposed low-rank adaptation. We compare conventional Euclidean merging with a geometry-aware Riemannian-inspired merging strategy that approximates the Frechet mean via normalized directional averaging across multiple QA benchmarks (GPQA, PubMedQA, SimpleQA, WMDP) on LLaMA-3.1-8B and Mistral-7B. Our results show that while single-domain performance matches LoRA, geometry-aware merging provides no consistent advantage over standard averaging in multi-domain settings.Diagnostic analysis further reveals that angular alignment and orthogonality of adapter updates are weak predictors of composition performance. These findings suggest that adapter interference is not governed primarily by parameter-space geometry, but is instead consistent with interactions in shared nonlinear representations.

阅读与讨论 → 访问原文 →

19.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2505.23893

A complexity theory for non-local quantum computation

作者:

Andreas Bluhm↗Simon H\"ofer↗Alex May↗Mikka Stasiuk↗Philip Verduyn Lunel↗Henry Yuen↗

arXiv:2505.23893v2 Announce Type: replace Abstract: Non-local quantum computation (NLQC) replaces a local interaction between two systems with a single round of communication and shared entanglement. Despite many partial results, it is known that a characterization of entanglement cost in at least certain NLQC tasks would imply significant breakthroughs in complexity theory. Here, we avoid these obstructions and take an indirect approach to understanding resource requirements in NLQC, which mimics the approach used by complexity theorists: we study the relative hardness of different NLQC tasks by identifying resource efficient reductions between them. Most significantly, we prove that $f$-measure and $f$-route, the two best studied NLQC tasks, are in fact equivalent under $O(1)$ overhead reductions. This result simplifies many existing proofs in the literature and extends several new properties to $f$-measure. For instance, we obtain sub-exponential upper bounds on $f$-measure for all functions, and efficient protocols for functions in the complexity class $\mathsf{Mod}_k\mathsf{L}$. Beyond this, we study a number of other examples of NLQC tasks and their relationships.

阅读与讨论 → 访问原文 →

20.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2512.15199

Sharing quantum indistinguishability with multiple parties

作者:

Lemieux Wang↗Hanwool Lee↗Joonwoo Bae↗Kieran Flatt↗

arXiv:2512.15199v3 Announce Type: replace Abstract: Quantum indistinguishability of non-orthogonal quantum states is a valuable resource in quantum information applications such as cryptography and randomness generation. In this article, we present a sequential state-discrimination scheme that enables multiple parties to share quantum uncertainty, in terms of the max relative entropy, generated by a single party. Our scheme is based upon maximum-confidence measurements and takes advantages of weak measurements to allow a number of parties to perform state discrimination on a single quantum system. We review known sequential state discrimination and show how our scheme would work through a number of examples where ensembles may or may not contain symmetries. Our results will have a role to play in understanding the ultimate limits of sequential information extraction and guide the development of quantum resource sharing in sequential settings.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16019

Scaling Human and G2P Supervision for Robust Phonetic Transcription

作者:

Alexander Metzger↗Aruna Srivastava↗Ruslan Mukhamedvaleev↗

Expert phonetic annotation is costly, especially for non-standard dialects and atypical speech. A common alternative is using Grapheme-to-Phoneme (G2P) models to auto-generate phonetic labels from text transcripts at scale. We study how automatic phonetic transcription performance scales with human and G2P supervision in English. Using a curated 80-hour benchmark spanning native, non-native and post-stroke speech, we identify a supervision quality threshold: G2P supervision helps only when fewer than 20-30 hours of human annotation are available. Beyond this threshold, it provides no significant benefit and can reduce cross-dialect robustness. What is effective after this threshold is ASR pretraining which we use to achieve a 2.3x reduction in weighted phone feature error rate over prior systems, with strong gains on non-native and aphasic speech. These results suggest that quantity-driven G2P scaling may yield diminishing returns for robust generalization.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19469

Measuring Curriculum Alignment across Topical Coverage, Competency, and Cognitive Depth: A Longitudinal Framework Applied to CS2013 and CS2023

作者:

Sherzod Turaev↗Mary John↗Saja Aldabet↗Mamoun Awad↗Nazar Zaki↗Khaled Shuaib↗

arXiv:2606.19469v1 Announce Type: new Abstract: Undergraduate computer science is governed by international curricular guidelines revised about once a decade, yet programs lack a reliable, reproducible way to measure how completely they cover the current guidelines and how that coverage shifts when the guidelines are restructured. We address this with a human-in-the-loop pipeline that measures a program's coverage of an external body of knowledge, applied longitudinally to one accredited BSc in Computer Science against Computer Science Curricula 2013 (CS2013) and 2023 (CS2023). The pipeline represents the program and each guideline as structured corpora, generates candidate course-to-knowledge-unit matches by semantic retrieval, and confirms them through human judgment under an explicit coverage definition. Of seven benchmarked retrievers, a reciprocal-rank-fusion ensemble was strongest, and a reputed long-context model underperformed a small sentence model, so retriever choice must be measured. Both maps were validated by an independent second rater (Cohen's kappa 0.64 for CS2023, 0.69 for CS2013). The program covers 49.7% of CS2023 and 50.9% of CS2013 knowledge units, near-constant across a decade. Extending the same retrieve-then-confirm design to competency articulation and cognitive depth shows that the program articulates the competency for ~88% of covered units under each guideline, yet delivers it at the recommended depth for 76% of present units under CS2023 against 95% under CS2013, a gap reflecting the newer guideline's raised expectations, not the program. The longitudinal comparison separates persistent structural gaps (parallel and distributed computing, foundations of programming languages, systems fundamentals), uncovered against both guidelines and ABET, from differences that reflect the standard's evolution. The instrument is reusable and available from the authors on request.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12300

Natural-Language Temporal Grounding in Hour-Long Videos is a Search Problem: A Benchmark and Empirical Decomposition

作者:

Sukmin Seo↗Geewook Kim↗

Temporal grounding–returning the interval $[t_s, t_e]$ for a natural-language query over a video–is the language interface to long-form video, yet has been studied on short videos; the dynamics of hour-scale natural-language grounding remain underexplored. We take the position that at hour-scale, the binding constraint is search, not recognition: Video-LLMs are bottlenecked not by localizing a nearby event, but–given a natural-language query–by searching for the relevant region of a long video. To test this, we release ExtremeWhenBench, the first open hour-scale grounding benchmark (2,273 queries over 194 videos, mean 75.7 min, max 9 hr) with an open-form query distribution. Every open Video-LLM collapses while a frame-level retrieval baseline outperforms them; a failure taxonomy attributes 85% of failures to search; and a retrieve-then-ground hybrid recovers 6.7x over the monolithic Video-LLM–mirroring retrieve-then-read in open-domain QA.

阅读与讨论 → 访问原文 →

24.

Nature Medicine 2026-06-12 DOI: HASH:e981593fd442d72ab99c9aaa75fc2792

General-purpose large language models outperform specialized clinical AI tools on medical benchmarks

作者:

Krithik Vishwanath↗

Specialized clinical artificial intelligence (AI) tools are entering medical practice despite scarce independent evaluation. We quantitatively evaluate two clinical AI tools, OpenEvidence and UpToDate Expert AI, built on large language models (LLMs) against three frontier LLMs: GPT-5.2, Gemini 3.1 Pro and Claude Opus 4.6. Our evaluation has three stages: (1) 500 MedQA questions testing medical knowledge, (2) 500 HealthBench items measuring alignment with clinicians and (3) the real clinical queries (RCQ) benchmark, built from 100 de-identified queries from physicians to a general-purpose language model in a live clinical environment. For the RCQ benchmark, 12 US clinicians performed randomized, blinded review of model outputs, producing 1,800 model–question annotations. Frontier LLMs outperformed clinical AI tools in all three evaluations. Clinical AI tools performed comparably to auto-enabled Google Search AI Overview on the RCQ. These findings highlight the need for independent, real-world evaluation of AI tools before they enter clinical settings. In an independent evaluation, frontier large language models outperformed specialized clinical artificial intelligence tools on medical knowledge, clinician alignment and real-world clinical queries.

阅读与讨论 → 访问原文 →

25.

bioRxiv (Bioinfo) 2026-06-08 DOI: HASH:6c972fd4df6324edd4d6c7223e4c7bf9

HydraMPP: A lightweight library for distributed massive parallel processing in Python - threading at scale.

作者:

Figueroa↗J. L↗White↗R. A↗

We now exist in the era of massive datasets from genomics, large language models, and all the known knowledge of humanity right at our fingertips. Much of this data is becoming more accessible; however, processing such data remains an ongoing issue across systems including high performance computing (HPC) infrastructures. Massively parallel computing (MPP) has solved this using a divide and conquer approach by splitting workloads across independent nodes (i.e., central processing units (CPU) allowing for higher scaling of data). The main engine for this in python is Ray; however, it has many issues including a large code space, security issues, debugging opacity, and memory management issues. Here, we present HydraMPP, a lightweight, ease of use and utilization, with high auditability, and with SLURM ergonomics.

阅读与讨论 → 访问原文 →