探索全球前沿学术脉络

01.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19380

AgentArmor: A Framework, Evaluation, \& Mitigation of Coding Agent Failures

作者:

Kenneth Ge↗Andre Assis↗

arXiv:2606.19380v1 Announce Type: cross Abstract: Software engineering and deployment are increasingly being delegated to AI coding agents. The scale of their adoption is surfacing rare, but highly destructive, failure modes. In this paper, we study these failure modes as stemming from three distinct mechanisms: underspecification, where default model behavior is unsafe; capability errors, where the safe action is available but the model does not adhere to it due to bias or capability limitations; and agent harness errors, where the model fails to execute the safe action through the harness. We evaluate these across 8 different evaluations, each inspired by real-life deployment failures, totaling 20 coding environments and 59 synthetic transcript templates. Based on this evaluation, we propose AgentArmor, an agent harness modification, to mitigate these errors. By adding an extended system prompt, a separate command classifier, a ``3 strikes'' policy, deterministic guardrails, and tools for the agent to edit its own context, we show that AgentArmor is safer across a statistically significant number of samples. Thus, we suggest concrete mitigations for current coding agents and a design philosophy for future agent harness features.

阅读与讨论 → 访问原文 →

02.

bioRxiv (Bioinfo) 2026-06-10 DOI: HASH:c5debf1d5f38c84fb834fa3582c12eb3

SPARQ-MI leverages end-to-end spatial single-cell analysis of the tumor microenvironment

作者:

Kiwitz↗Turiello↗Effern↗Toma↗Landsberg↗Hoelzel↗Thurley↗

Detailed spatial analysis of the tumor micro-environment (TME) through multiplexed fluorescence imaging requires quantitative image-processing and data-analysis methods. While data-preprocessing down to segmentation of individual cells is captured by available methods, statistical analysis of single-cell features is compromised by the uneven noise distribution especially in complex tissues such as the TME, as well as by labor-intensive manual cell-type annotation and region segmentation. Here, we present SPARQ-MI (Spatial Phenotyping, Architecture Reconstruction and Quantification from Multiplexed Imaging) for streamlined spatial single-cell analysis, along with a tissue microarray PhenoCycler data-set with 37 fluorescent channels from melanoma patients under immunotherapy. We demonstrate that SPARQ-MI enables robust reconstruction of the cellular and spatial composition in this and other tissue types. Our analysis reveals associations of the cell-state and spatial location of CD8 T cells with response to immunotherapy. Overall, SPARQ-MI allows for quantitative analysis of complex fluorescence histology samples under minimal user input, and accounting for spatially uneven coverage of antibody signals, setting the stage for quantitative analysis of clinical samples.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2606.24759

UniDrive: A Unified Vision-Language and Grounding Framework for Interpretable Risk Understanding in Autonomous Driving

作者:

Xiaowei Gao↗Pengxiang Li↗Yitai Cheng↗Ruihan Xu↗James Haworth↗Stephen Law↗Yun Ye↗

arXiv:2606.24759v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have shown strong potential for autonomous driving scene understanding, yet existing methods still face a fundamental trade-off between temporal reasoning and spatial precision. Models that rely on single-frame or low-resolution inputs often miss small, distant, or partially occluded hazards, while language-centric driving models frequently provide limited grounded evidence for their explanations. To address this gap, we propose UniDrive, a unified visual-language and grounding framework for interpretable risk understanding in autonomous driving. UniDrive combines a temporal reasoning branch that models scene dynamics from multi-frame visual input with a high-resolution perception branch that preserves fine-grained spatial details from the latest frame. The two branches are integrated through a gated cross-attention fusion module, enabling dynamic context to be aligned with precise spatial evidence. Based on the fused representation, UniDrive jointly generates natural-language risk descriptions and grounded bounding-box outputs for risk objects. Experiments on the DRAMA-Reasoning benchmark show that UniDrive outperforms representative image-based and video-based baselines in both captioning and risk-object grounding. In particular, UniDrive achieves the best overall performance on the validation split and demonstrates clear advantages in small-object localization, zero-shot generalization to NuScenes and BDD100K, and human-rated interpretability and trustworthiness. These results suggest that explicitly combining temporal semantics and high-resolution perception provides a stronger foundation for interpretable and safety-oriented autonomous driving systems. The code is available at https://github.com/pixeli99/unidrive-dev.

阅读与讨论 → 访问原文 →

04.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2606.14698

Resolving the Edge of a Quantum Pyramid

作者:

Alvan Arulandu↗

arXiv:2606.14698v1 Announce Type: new Abstract: Standing on the shoulders of giants, we resolve the quantum pyramids conjecture, confirming the globally information-optimal measurement for an ensemble of equiangular equiprobable pure states, as conjectured by Englert and \v{R}eháček (arXiv:0905.0510). We do so by proving the remaining entropy inequalities of Holevo and Utkin (arXiv:2506.06700), which certify optimality for obtuse and flat pyramids. For obtuse pyramids, our key contribution is a rigorous proof that local minimizers of the corresponding entropy inequality cannot have three distinct coordinate values. We show that eliminating this family can be reduced to a neat algebraic reciprocal inequality relating branches of the Lambert $W$ function, which may be of independent interest. For flat pyramids, we prove a tight $\ell^p$ inequality for zero-sum vectors that was recently conjectured, proved analytically in dimension $d=3$, and computationally verified for $d\leq 200$ by Holevo and Utkin (arXiv:2603.24017). We prove this bound for all $d\geq 2$ via a technique in symmetric inequalities known as the equal variables method.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18774

RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing

作者:

Guannan Lai↗Haoran Hu↗Han-Jia Ye↗

arXiv:2606.18774v1 Announce Type: new Abstract: We present RouteJudge, an online pairwise preference evaluation framework for LLM routing systems, with a public platform available at https://routejudge.cn. Different from model-level response evaluation, RouteJudge focuses on router-level decision quality. For each user query, multiple routing strategies independently recommend candidate models under the same model pool and budget constraints. The selected model responses are then presented to users through anonymous pairwise comparisons, and the resulting user preferences are attributed back to the routing strategies behind the compared responses. Each evaluation record stores the query, routing decisions, model responses, preference labels, cost, latency, and task metadata, enabling preference-aware, cost-aware, and task-conditioned analysis of LLM routers. To support the continuous expansion of routing methods in RouteJudge, we further release ORBIT (Optimal Routing and Budgeted Inference Toolbox), a modular and extensible toolbox that standardizes the end-to-end workflow of LLM routing. ORBIT provides unified interfaces for benchmark loading, query representation, router implementation, budget-aware evaluation, and method comparison, allowing researchers to develop and evaluate routing algorithms under consistent protocols. It also serves as the submission and integration layer for RouteJudge: researchers can implement routing methods within ORBIT, validate them on existing routing benchmarks, and submit compatible routers for online preference-based evaluation. The code of ORBIT is available at https://github.com/AIGNLAI/LAMDA-ORBIT.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2207.03116

Equivariant Representation Learning via Class-Pose Decomposition

作者:

Giovanni Luca Marchetti↗Gustaf Tegn\'er↗Anastasiia Varava↗Danica Kragic↗

arXiv:2207.03116v4 Announce Type: replace Abstract: We introduce a general method for learning representations that are equivariant to symmetries of data. Our central idea is to decompose the latent space into an invariant factor and the symmetry group itself. The components semantically correspond to intrinsic data classes and poses respectively. The learner is trained on a loss encouraging equivariance based on supervision from relative symmetry information. The approach is motivated by theoretical results from group theory and guarantees representations that are lossless, interpretable and disentangled. We provide an empirical investigation via experiments involving datasets with a variety of symmetries. Results show that our representations capture the geometry of data and outperform other equivariant representation learning frameworks.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15974

A Large-Scale Multi-Dimensional Empirical Study of LLMs for Conversation Summarization

作者:

Weixiao Zhou↗Gengyao Li↗Xianfu Cheng↗Junnan Zhu↗Feifei Zhai↗Zhoujun Li↗

Despite the significant advancement of LLMs in conversation summarization, their evaluation remains limited by insufficient scenarios, input lengths, and sample sizes. Furthermore, existing benchmarks often omit frontier reasoning systems and efficient small models, or lack fine-grained, multi-dimensional assessments. To bridge these gaps, we propose OmniCSEval, a unified benchmark comprising 1,800 diverse conversations across six real-world scenarios, featuring context lengths ranging from 128 to 32k tokens. For fine-grained evaluation, we employ a bidirectional fact-checking framework that integrates key fact matching to assess completeness and conciseness, alongside summary fact verification to evaluate faithfulness. To ensure reliable assessment, we establish a human-LLM collaborative pipeline for key fact extraction and a multi-LLM consensus verifier for summary fact decomposition. Leveraging this framework, we evaluate 28 LLMs across four distinct categories grouped by reasoning capability and model scale. Our extensive empirical study reveals critical insights regarding the cross-scenario challenges current LLMs continue to face, the impacts of reasoning and scale, and the efficiency and adaptability of reasoning models. We also provide guidance for system selection in real-world deployments.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2603.09276

On Regret Bounds of Thompson Sampling for Bayesian Optimization

作者:

Shion Takeno↗Shogo Iwazaki↗

arXiv:2603.09276v2 Announce Type: replace-cross Abstract: We study a widely used Bayesian optimization method, Gaussian process Thompson sampling (GP-TS), under the assumption that the objective function is a sample path from a GP. Compared with the GP upper confidence bound (GP-UCB) with established high-probability and expected regret bounds, most analyses of GP-TS have been limited to expected regret. Moreover, whether the recent analyses of GP-UCB for the lenient regret and the improved cumulative regret upper bound can be applied to GP-TS remains unclear. To fill these gaps, this paper shows several regret bounds: (i) a regret lower bound for GP-TS, which implies that GP-TS suffers from a polynomial dependence on $1/\delta$ with probability $\delta$, (ii) an upper bound of the second moment of cumulative regret, which directly suggests an improved regret upper bound on $\delta$, (iii) expected lenient regret upper bounds, and (iv) an improved cumulative regret upper bound on the time horizon $T$. Along the way, we provide several useful lemmas, including a relaxation of the necessary condition from recent analysis to obtain improved regret upper bounds on $T$.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16615

SUP-MCRL: Subject-aware Unified Pseudo-feature Coded Multimodal Contrastive Representation Learning for EEG Visual Decoding

作者:

Shengyu Gong↗Weiming Zeng↗Yueyang Li↗Zijian Kang↗Hongjie Yan↗Wai Ting Siok↗Nizhuan Wang↗

Non-invasive brain-computer interfaces suffer severe fidelity degradation in neural visual decoding when generalizing to natural visual experiences. Conventional multimodal contrastive representation learning solely optimizes geometric distance alignment, neglecting semantic consistency and subject selectivity, causing spurious zero-shot alignment. We propose SUP-MCRL, a unified framework integrating three collaborative mechanisms: (1) Semantic-entity Aware Visual Encoder (SAVE), learning spatial attention to extract semantic content without pre-trained saliency models; (2 Unified EEG Enhancer (UEE), employing multi-scale atrous convolutions and inter-band attention for adaptive cross-subject robustness; and (3) Prototype-based Progressive Augmenter (PPA), maintaining an EMA-updated pseudo-feature pool to prevent representation collapse. Zero-shot experiments on THINGS-EEG achieve 66.0%/91.9% (Top-1/Top-5) intra-subject and 24.0%/52.9% LOSO accuracy, surpassing state-of-the-art methods. Code is available at https://github.com/NZWANG/SUP-MCRL.

阅读与讨论 → 访问原文 →

10.

medRxiv (Medicine) 2026-06-12 DOI: HASH:5a9a743a2ac5f8e6bf0ef4d6c10175de

Room-Specialized Mixture-of-Experts for In-Home ADL Recognition with Ambient Sensors

作者:

Addepalli↗V. r↗Rao↗Kiselica↗Kummerfeld↗Abdalnabi↗Lee↗

Monitoring activities of daily living (ADLs) in the home is a promising approach for tracking dementia progression in older adults. While ambient sensor-based ADL systems are well-studied, most existing ADL recognition systems rely on globally trained models that ignore the spatial organization of in-home activities. In real deployments, where training data are sparse and highly home-specific, global transformer models may fail to capture room-dependent behavioral structure. We propose a deterministic Mixture of Experts (MoE) architecture for in-home ADL recognition, in which each expert is a compact transformer specialized to one room of the home (bedroom, kitchen, bathroom, living area). Input segments are routed using a deterministic gating strategy based on room-level motion activity and time-of-day priors for sleep-related behaviors. Unlike learned routing networks, the proposed gate encodes domain knowledge about where ADLs are likely to occur, reducing model complexity under limited per-home training data. By decomposing ADL recognition into room-specific activity spaces, the proposed architecture reduces competition between dominant and low-frequency activities under highly imbalanced residential data. We evaluated the system on data collected via low-cost ambient sensors (motion, light, temperature, humidity) and Raspberry Pi edge devices across five homes, with ground-truth ADL labels provided by participants and caregivers. Across the five homes, the proposed MoE consistently outperformed global transformer, 1D CNN, and Random Forest baselines, achieving macro-F1 scores ranging from 0.60 to 0.88, highlighting the importance of home-specific modeling in real-world deployments. These findings suggest that room-aware expert specialization may provide a practical and interpretable strategy for low-data ADL recognition in real-world residential environments.

阅读与讨论 → 访问原文 →

11.

medRxiv (Medicine) 2026-06-12 DOI: HASH:944153cf2348858c38e1083f871c6045

Design, Implementation, and Evaluation of a Shadowing Program for Medical Students in the Basic Sciences Phase

作者:

Omid↗Changiz↗ghasemi↗Khodadoustan↗Heshmat↗Arefan↗Fazel Harandi↗M. H↗Yousefi↗

Introduction Shadowing, as an educational method based on active observation, can foster a realistic understanding of professional roles and enhance the communication skills of medical students. This study aimed to design, implement, and evaluate a shadowing program for basic sciences medical students. Methods This development study was conducted based on the ADDIE model in five phases. The study population consisted of 799 medical students in semesters 2 to 5. The stages included Analysis (determining needs through literature review and expert panels), Design (specifying learning environments and evaluation methods), Development (preparing guides and educational tools), Implementation (within the Medical Ethics course), and Evaluation (using questionnaires and reflection forms). Findings This study aimed to design and evaluate an educational shadowing program based on the ADDIE model. In the Analysis phase, the profiles of 799 students and learning objectives were determined. In the Design phase, a structured program for four types of shadowing was designed. In the Development phase, all guides and educational tools were prepared. In the Implementation phase, the program was carried out with complete coverage and adherence to ethical considerations. Finally, the program evaluation showed that "Motivation to become a good physician" (3.75-3.95) and "Enhancing empathy" (3.50-3.94) received the highest scores, while "Increasing understanding of the basic science-clinical connection" (2.53-2.89) and "Willingness to attend on holidays" (1.87-2.31) received the lowest scores. Conclusion The findings indicate that implementing the shadowing program is an effective method for strengthening the professional attitudes and academic motivation of medical students. However, the program did not significantly improve students perception of the basic science-clinical connection, indicating a need for curricular refinement. The continuation and extension of this program to other levels and fields of medical sciences are recommended.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.08343

GENERIC-FNO: Embedding Energy Conservation and Entropy Production into Fourier Neural Operators

作者:

Jason Sulskis↗Sathya Ravi↗

arXiv:2606.08343v2 Announce Type: replace Abstract: We introduce GENERIC-FNO, the first neural operator to embed the full GENERIC (metriplectic) structure of nonequilibrium thermodynamics – reversible, energy-conserving dynamics and irreversible, entropy-producing dynamics coupled through the degeneracy conditions – directly in function space. Existing structure-preserving neural operators enforce at most a single conservation law or reversible (Hamiltonian) structure, while thermodynamically consistent learning has been confined to finite-dimensional, graph, or particle systems. GENERIC-FNO closes this gap: it learns the energy and entropy functionals as neural operators and parameterizes the Poisson and friction operators as diagonal Fourier multipliers sandwiched between rank-one projections that enforce the degeneracy conditions exactly, by construction, with no penalty term, update projection, or residual. The degeneracy identities hold to machine precision (residuals ~10^-13) for any initialization, dimension, or resolution, so the continuous-time dynamics conserve the learned energy and produce entropy exactly; the explicit time stepping adds only a small O(dt^2) drift (per-step residual ~10^-6). We further note that the (E,S,L,M) decomposition of a given flow is not unique, and introduce a gauge-invariant dissipation diagnostic separating reversible from dissipative dynamics independently of the learned functionals. Across three operator backbones (1D/2D FNOs and DeepONet) and four PDEs spanning reversible, dissipative, and mixed regimes, GENERIC-FNO preserves its exact structural guarantees zero-shot across a 4x super-resolution range (64 to 256), recovers the ground-truth ordering of physical dissipation, and is competitive with strong unconstrained and energy-penalized baselines, outperforming them on several dissipative and mixed problems at comparable or fewer parameters.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17775

A Neuromorphic Trigger for Efficient Audio Event Detection

作者:

Benjamin Hatton↗Oliver Rhodes↗Luca Peres↗

arXiv:2606.17775v1 Announce Type: cross Abstract: Efficient processing of continuous audio streams remains a key challenge for real-time and resource-constrained systems. This paper introduces a neuromorphic trigger for audio event detection, based on a spiking neural network (SNN) that selectively gates input to downstream models. The proposed trigger acts as a low-cost front-end, identifying salient audio segments and forwarding only these to a more computationally intensive model for tasks such as classification. The trigger is implemented as a lightweight fully connected SNN and evaluated on two representative tasks: Anomalous Sound Detection (ASD) and Sound Event Detection (SED). For ASD, the trigger achieves a one-second segment-based F1 score of 0.97 on a class-agnostic form of the URBAN-SED dataset, demonstrating high reliability in identifying relevant audio regions. For SED, the trigger is combined with the Dang classifier on the DCASE 2017 Challenge Task 2 dataset, showing a potential $42.6\times$ reduction in FLOPs while reducing the lower bound of the event-based error rate from 0.41 to 0.25. These results highlight the potential of neuromorphic triggers as real-time, energy-efficient front-end filters, enabling substantial reductions in computational cost.

阅读与讨论 → 访问原文 →

14.

medRxiv (Medicine) 2026-06-15 DOI: HASH:255b6c09d205b63b32360e63a6715003

Epileptogenicity alters intrahippocampal ripple propagation

作者:

Chen↗Ye↗Staba↗R. J↗wang↗Weiss↗S. A↗

Objective: Tracing the propagation of high-frequency oscillations (HFOs) aids in localizing epileptogenic regions and improving surgical outcomes. We examined how hippocampal epileptogenicity influences the propagation properties of the HFOs it generates. Methods: We analyzed non-REM sleep stereo-EEG from 49 patients (68 hemispheres) with verified hippocampal contacts. Hippocampi were stratified by excitability: 28 seizure onset zone (SOZ), 22 more-irritative non-SOZ (>6 interictal epileptiform discharges [IED]/min), and 18 less-irritative non-SOZ (

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18591

Bridging Creative Intent and Visual Quality: Creator-Driven Recurrent Video Generation with Agentic Feedback Loops

作者:

Denis Savytski↗Aiden Lei↗Heding Liu↗Warren Yang↗Sihan Liang↗Alexander Liu↗Zhe Zhao↗

Generative AI has made content creation increasingly accessible, but many AI-generated videos lack narrative coherence and creative direction, issues that become more substantial at longer durations. Unlike coding, where AI generation benefits from reliable feedback and techniques such as recurrent self-improvement, video generation requires subjective feedback about plot, scenes, and narrative, which naturally motivates approaches that incorporate human creative direction. We introduce CHIEF, a human-AI co-creation video generation framework that places the creator at the center of human-in-the-loop iterative video refinement, and supports them by providing automatic subjective feedback. The creator incorporates their creative direction by driving each iteration, while their revisions are incorporated by a specialized refiner agent. The feedback loop is generated by persona-conditioned multimodal LLMs that watch generated videos and produce subjective critique from the audience perspectives, providing feedback that self-evaluation alone cannot capture. To test the effectiveness of our proposed framework, we work with high school and college students with no prior filmmaking experience to create videos, from short 1-minute videos to a complete short 10-minute film with a complicated plot.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15954

Green SARC: Predictive Cost and Carbon Governance for Agentic AI Systems

作者:

Gaston Besanson↗

arXiv:2606.15954v1 Announce Type: cross Abstract: Agentic AI systems act through tools and sub-agents, yet the controls meant to bound their financial and environmental cost still sit on dashboards evaluated beside or after execution. Green SARC applies the SARC governance-by-architecture framework – four enforcement sites in the agent loop – to FinOps and GreenOps, contributing the theory of what to enforce and how to predict it. We report four policy-independent results. (i) The unconstrained "State Snowball" is $\Theta(n^2)$ in loop depth; on 3,000 real multi-step plans (SWE-rebench) it holds on 100%, with median curvature $\hat{c}_2=216$ exceeding the linear-accretion prediction $p/2=134$ – real plans accrete faster than the model. (ii) On real residuals the Normal-$\sigma$ gate under-covers (92% at nominal 95%); split-conformal calibration holds (95.2%). (iii) A soft Lagrangian penalty tuned to the budget in expectation breaches it on 91.5% of seeds; the architectural gate breaches 0%. (iv) Under binding budgets the gate's over-budget incidence is 0% on synthetic and real (BurstGPT) arrivals. End-to-end token/USD/carbon savings (47–55%) are real but policy-dependent in magnitude – set by a scope-cap knob, not by gate rejections. The library is open-source, dependency-free, and ships a regeneration script for every cited number.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2511.05017

Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings

作者:

Aakriti Agrawal↗Gouthaman KV↗Rohith Aralikatti↗Gauri Jagatap↗Jiaxin Yuan↗Sarvesh Baskar↗Vijay Kamarshi↗Andrea Fanelli↗Furong Huang↗

Hallucinations in Large Vision-Language Models (LVLMs) remain a persistent challenge, often stemming from inadequate integration of visual information during multimodal reasoning. A key cause is the model's over-reliance on textual priors and underutilization of visual cues, leading to outputs that are linguistically fluent but visually inaccurate. For example, given an image of an empty kitchen countertop, an LVLM might hallucinate a "bowl of fruit" or "cup of coffee", relying on language associations rather than visual evidence. Most LVLMs incorporate visual features by appending them to the input stream of a pre-trained LLM and training on large-scale vision-language datasets. Our systematic analysis reveals that this strategy often leads to over-dependence on textual information due to the inherent bias of LLMs towards language-dominant representations. This imbalance skews attention towards the text over visual content, weakening the model's ability to ground outputs in visual inputs. To address this, we propose a simple yet effective visual feature incorporation method that encourages the model to learn visually-informed textual embeddings distinct from those of the base LLM and promotes a more balanced attention distribution. Experimental results across multiple hallucination benchmarks demonstrate that our method significantly reduces hallucinations and fosters more balanced multimodal reasoning. Notably, our approach achieves substantial gains, including +9.33% on MMVP-MLLM, +2.99% on POPE-AOKVQA, up to +3.4% on Merlin, and +3% on the hard-data split of HallusionBench.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15782

Mitigating Visual Hallucinations in Multimodal Systems through Retrieval-Augmented Reliability-Aware Inference

作者:

Pratheswaran Hariharan↗Haiping Xu↗Donghui Yan↗

Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-language understanding and natural-language response generation. However, these systems can still produce overconfident predictions and hallucination-like outputs, particularly when the visual evidence is weak, ambiguous, or semantically inconsistent. Most existing approaches focus on improving multimodal representation alignment or retrieval-augmented generation, while providing limited mechanisms to quantify instance-level prediction reliability or identify incorrect visual outputs. This work proposes a retrieval-augmented reliability-aware inference framework for trustworthy multimodal visual understanding. The proposed framework constructs an external visual evidence database using pretrained visual embeddings and nearest-neighbor retrieval over normalized feature representations. Retrieved evidence is used to estimate prediction trustworthiness through multiple reliability indicators, including similarity strength, class-support agreement, evidence margin, entropy-based uncertainty, and an aggregate reliability score. Based on these signals, a decision gate determines whether the system should accept the prediction, answer with caution, or abstain/fallback when evidence is insufficient. A multimodal response-generation layer then produces a final user-facing response conditioned on the reliability decision. Experiments on ImageNet-100 demonstrate that the proposed reliability-aware framework improves accepted prediction accuracy from 85.84\% to 88.88\% at 89.04\% coverage. The hallucination-like accepted wrong-answer rate is reduced from 14.16\% to 11.12\%. These results show that integrating retrieval evidence, reliability estimation, and selective decision gating can improve calibration and reduce overconfident visual errors without retraining large multimodal models.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13704

Position: AI Must Become Planet-Centered, Not Just Human-Centered

作者:

Maria Perez-Ortiz↗

arXiv:2606.13704v1 Announce Type: cross Abstract: This position paper argues that contemporary AI paradigms are insufficient for supporting complex global goals and introduces Planet-Centered AI (PCAI) as a design philosophy and research agenda that reorients AI toward planetary-scale socio-ecological systems and their long-term trajectories. A planet-centered approach is grounded in systems thinking, treating Earth as an interconnected whole of which humans are part. We diagnose recurring limitations across AI frameworks, many of which remain human-centered, and show why these become especially consequential under current planetary conditions characterized by systemic risk, non-stationarity, and deep uncertainty. We then articulate how PCAI reshapes the AI lifecycle, from problem formulation and model design to evaluation and deployment, by emphasizing alignment with global agendas, developing system-aware AI foundations, trajectory-oriented evaluation, and monitorability. Finally, we advance a falsifiable claim: AI systems optimized without explicit consideration of systemic consequences are more likely to exacerbate systemic instability than to mitigate it.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-24 DOI: arXiv:2606.24259

SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization

作者:

Noor Islam S. Mohammad↗Ulug Bayazit↗

Fine-tuned encoders deployed across heterogeneous NLP tasks face three compounding problems: mismatched inductive biases, class-imbalance corruption of feature statistics, and no mechanism to condition attention on external lexical knowledge. We introduce \surgellm, a unified transformer framework that addresses each with a dedicated lightweight module: a surgical feature gate (learned per-dimension sigmoid over curated lexical indicators and \texttt{[CLS]}; provably degenerates to identity when features are uninformative), task-conditioned prefix tokens (quantized feature values and task identity prepended to every input), and Instance-Weighted Normalization (IWN; removes class-prior bias from gate statistics). We prove an excess-risk bound linking gate benefit to surgical feature alignment. Across four tasks, SST-2, multi-hop retrieval, LLM-prompt attribution, and authorship detection, covering 17,830 examples and eleven model variants over three seeds, the IWN variant achieves macro-F1 0.940 ($+0.036$ over the strongest non-IWN baseline; $+0.130$ on authorship detection). A random-vocabulary control ($-0.028$ avg.\ F1) confirms gains are lexical, not parametric. Code, vocabularies, and a $99.5\%$-recovery auto-extraction recipe are released.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16234

Propagating Structural Guidance: Synthesizing Fluorescein Angiography from Fundus Images and Sparse OCT Scans

作者:

Tengfei Ma↗Ruiqi Wu↗Chenran Zhang↗Ye Geng↗Na Su↗Xiangyuan Duanmu↗Tao Zhou↗Yi Zhou↗Wen Fan↗

Fundus fluorescein angiography (FFA) is critical for assessing retinal vascular abnormalities, but its acquisition is invasive and not always feasible. In contrast, color fundus photography (CFP) is non-invasive and widely accessible, which has motivated studies on CFP-to-FFA synthesis. However, prior works rely solely on CFP surface texture, fundamentally limiting the ability to reconstruct functional vascular information and subtle pathological changes. To address this, we propose a novel framework that synthesizes FFA from CFP with structural guidance provided by optical coherence tomography (OCT). We construct a multi-modal retinal imaging dataset with paired CFP, FFA, and OCT from 3,676 patient eyes–the first tri-modally aligned dataset in retinal imaging. To bridge the spatial gap between OCT and fundus modalities, we propose a Spatially Aligned Cross-Modal Fusion (SACMF) module that projects depth-resolved OCT features onto the fundus plane and injects them into the CFP encoder via adaptive layer normalization. Beyond feature fusion, we further introduce Token-wise Cross-Modality Alignment (TCMA), a token-level contrastive learning strategy that explicitly aligns CFP and FFA representations at corresponding spatial positions. Our method achieves superior synthesis performance compared to state-of-the-art methods. Moreover, extensive experiments demonstrate that the FFA images synthesized by our approach bring greater improvements in downstream disease diagnosis performance than existing methods, highlighting the clinical potential of our approach as a non-invasive decision-support tool in routine workflows. The code is available at https://github.com/while-plus/OCT-guide-FFA-Syn.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15869

Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigation

作者:

Jingyu Li↗Zhe Liu↗Dongnan Hu↗Junjie Wu↗Zipei Ma↗Wenxiao Wu↗Chao Han↗Zhihui Hao↗Zhikang Liu↗Kun Zhan↗Jiankang Deng↗Xiatian Zhu↗…

World action models~(WAMs) have shown great promise for autonomous driving and urban navigation. Built upon Vision-Language-Action models or video generation models, existing approaches suffer key limitations: (1) High inference latency due to future observation prediction at test time, and (2) tightly coupled video and action modeling leading to representational mismatch and degraded generalization. To address both issues, we propose Metis, an end-to-end WAM framework that decouples video generation and action prediction. Specifically, Metis employs a Mixture-of-Transformers architecture with dedicated experts for video generation and action prediction, preserving the intrinsic distributional properties of each task. To enhance efficiency, we introduce an asymmetric attention mask that enables joint training of both experts while allowing the action model to bypass explicit video generation during inference. This design ensures training-inference consistency and significantly reduces computational costs without compromising planning performance. Extensive experiments demonstrate state-of-the-art performance on the NAVSIM navhard and navtest benchmarks and the CityWalker navigation benchmark, validating both the generalizability and efficiency across diverse tasks. Real-robot deployments further confirm the practical feasibility of our approach.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17246

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 →

24.

bioRxiv (Bioinfo) 2026-06-11 DOI: HASH:27cb170cbe30e2162a3bbe81453ecaab

An AI-Powered Trisomy 21 Research Assistant

作者:

NANDI↗Sundararajan↗Subirana-Granes↗Espinosa↗J. M↗Pividori↗Sullivan↗K. D↗Galbraith↗M. D↗Costello↗

Down syndrome, caused by trisomy 21, increases the risk of diverse co-occurring conditions. With more than 34,000 related publications indexed in PubMed as of early 2026, keeping pace with this expanding literature is challenging. While general-purpose large language models are widely used for information retrieval, they often rely on broad training data rather than specific evidence. Retrieval-augmented generation (RAG) improves rigor and reliability of responses by linking model outputs to source texts. In research, source texts are peer-reviewed articles. Standard implementations treat all manuscript sections equally, allowing background text to rank as highly as experimental results. To focus model outputs on experimentally supported responses, we developed the T21 Research Assistant, a section-aware RAG system that prioritizes Results sections to ground responses in primary experimental evidence. The system draws exclusively from 1,789 open-access Down syndrome publications from PubMed Central, including 327 NIH INCLUDE-funded studies, and uses a multistage pipeline for query validation, retrieval, reranking, synthesis, and citation verification. Built on NVIDIA Nemotron models, it generates structured, cited responses. Evaluation using expert-curated questions demonstrated strong performance, achieving a BERTScore F1 of 0.712 and recall of 0.758, comparable to or exceeding leading proprietary and open-source models. T21 Research Assistant is available at: https://bioinformatics.cuanschutz.edu/t21-res-assi/

阅读与讨论 → 访问原文 →

25.

arXiv (CS.LG) 2026-06-24 DOI: arXiv:2507.09839

Stabilizing Black-Box Prompt Optimization with Textual Regularization and Signal Aggregation

作者:

MohammadReza Davari↗Utkarsh Garg↗Weixin Cai↗Eugene Belilovsky↗

arXiv:2507.09839v2 Announce Type: replace Abstract: An increasing number of NLP applications interact with large language models (LLMs) through black-box APIs, making prompt engineering critical for controlling model behavior. Recent Automatic Prompt Optimization (APO) methods iteratively refine prompts using model-generated critiques (often called textual gradients), but they predominantly optimize from failures and underutilize information contained in correct predictions, leading to instability and semantic drift. We propose TRAS (Textual Regularization with Aggregated Signals), a feedback-centric framework that is plug-and-play with existing APO search backbones. It retains the standard textual gradient signal from prior work for error correction and introduces a complementary textual regularizer derived from successful predictions to preserve beneficial prompt components. Because both signals are stochastic and can be noisy, we further introduce Monte Carlo Signal Aggregation (MCSA), which samples multiple gradients or regularizers and aggregates them into a single actionable directive, emphasizing consistent, actionable advice while filtering out outliers. Motivated by rapid model churn, we also formalize Automatic Prompt Migration (APM), the practical problem of adapting an expert prompt across model versions or API providers without losing critical instructions. Across standard APO and APM scenarios, our approach consistently outperforms strong baselines, yielding higher accuracy, faster convergence, and lower query cost, while substantially reducing the degradation observed under naive prompt migration.

阅读与讨论 → 访问原文 →