中 EN
Sign In Register

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Sign In Register
01.
arXiv (CS.CV) 2026-06-12

SalArt-VQA: Diagnosing Whether VLMs Understand Salient Artifacts in Generated Images

Authors:
Xiaoxiao Sun↗Ruotian Zhang↗Junzhe Huang↗James Burgess↗Serena Yeung-Levy↗

Vision-language models (VLMs) are increasingly used to detect whether AI-generated images contain visible artifacts, yet their ability to analyze such artifacts remains poorly understood. A correct image-level decision can still hide important failures: a model may correctly flag an artifact while relying on the wrong visual cue, selecting the wrong region, or describing a defect that the image does not support. To evaluate these behaviors directly, we introduce SalArt-VQA, a diagnostic benchmark for fine-grained SALient ARTifact understanding in AI-generated images. SalArt-VQA contains 950 images and 3,681 human-authored multiple-choice questions spanning artifact images, matched real reference images, and paired generated reference images. Four aligned question types evaluate presence detection, semantic localization, spatial grounding, and evidence-grounded defect identification, while the reference splits test calibration and abstention when the annotated defect is absent. Across 20 VLMs, SalArt-VQA reveals failures that image-level detection accuracy hides: the strongest model reaches 99.37% detection recall on artifact images but answers all four artifact-side questions correctly on only 53.26% of images. Comparing artifact images with artifact-free references reveals a sensitivity-calibration tradeoff: sensitive models often make unsupported artifact claims, while conservative models avoid false alarms largely by missing real artifacts. These results show that high artifact detection accuracy alone does not imply grounded artifact understanding. SalArt-VQA exposes these hidden failure modes and provides a fine-grained evaluation of whether VLM artifact claims are supported by local visual evidence.

Read & Discuss → View Source →
02.
arXiv (CS.CV) 2026-06-16

SLUM-i: Semi-supervised Learning for Urban Mapping of Informal Settlements and Data Quality Benchmarking

Authors:
Muhammad Taha Mukhtar↗Syed Musa Ali Kazmi↗Khola Naseem↗Muhammad Ali Chattha↗Andreas Dengel↗Sheraz Ahmed↗Muhammad Naseer Bajwa↗Muhammad Imran Malik↗

Rapid urban expansion has fueled the growth of informal settlements in major cities of low- and middle-income countries, with Lahore and Karachi in Pakistan and Mumbai in India serving as prominent examples. However, large-scale mapping of these settlements is severely constrained not only by the scarcity of annotations but by inherent data quality challenges, specifically high spectral ambiguity between formal and informal structures and significant annotation noise. We address this by introducing a benchmark dataset for Lahore, constructed from scratch, along with companion datasets for Karachi and Mumbai, which were derived from verified administrative boundaries, totaling approximately 900 $km^2$ of urban area. This collection is supplemented by four cities from prior literature across Sub-Saharan Africa and Latin America, with comprehensive data quality assessments provided for each city. We also propose a semi-supervised segmentation framework designed to mitigate the class imbalance and distribution mismatch inherent in standard semi-supervised learning pipelines. Our method integrates a Class-Aware Adaptive Thresholding mechanism that dynamically adjusts confidence thresholds to prevent minority class suppression, and a DINOv2-based unlabeled pool filter that removes out-of-distribution tiles prior to training to reduce covariate shift. Extensive experiments across seven cities spanning three continents, repeated over five random seeds, demonstrate gains of up to +5.9 pp mIoU over state-of-the-art semi-supervised baselines, with both components being architecture-agnostic and adding no inference overhead.

Read & Discuss → View Source →
03.
arXiv (CS.AI) 2026-06-16

GIST-CMTF: Goal-State Inference for Causal Minimal Tool Filtering in LLM Agents

Authors:
Rahul Suresh Babu↗Rohit Shukla↗

arXiv:2606.16813v1 Announce Type: new Abstract: Tool-augmented LLM agents rely on runtime filtering to decide which tools should be visible at each step. Causal Minimal Tool Filtering (CMTF) reduces tool-choice confusion by exposing only the next causally necessary tool frontier, but it assumes that the user request has already been mapped to a symbolic goal state. In practice, requests such as "handle my appointment" or "take care of this email" may correspond to multiple possible goals. This creates wrong-goal execution, where an agent follows a valid causal tool path for an unintended objective. We introduce GIST-CMTF, a goal-state inference layer that predicts candidate symbolic goals over the same state-transition vocabulary used by CMTF, estimates ambiguity, and either applies CMTF or exposes clarification as a causal action that produces missing goal or state variables. We evaluate GIST-CMTF across seven model backends, six filtering methods, and 120 controlled tool-use tasks. GIST-CMTF achieves 97.0% task success, compared with 80.1% for top-goal CMTF and 82.9% for semantic-goal CMTF. It reduces wrong-goal execution from 19.4% under top-goal CMTF to 2.5%, while preserving the one-tool exposure of causal filtering and using substantially fewer tokens than all-tools exposure. These results suggest that reliable tool-augmented agents should validate goal state, not only tool relevance, before exposing external actions.

Read & Discuss → View Source →
04.
arXiv (CS.LG) 2026-06-12

Simplex-Constrained Sparse Bagging: Transitioning from Uniform Priors to Sparse Posteriors in Ensemble Learning

Authors:
Meher Sai Preetam↗Meher Bhaskar↗

arXiv:2606.13589v1 Announce Type: new Abstract: We present Simplex-Constrained Sparse Bagging (SCSB), a mathematically rigorous framework for post-training compression and probability calibration of bootstrap-based bagging ensembles. Standard bagging ensembles (such as Random Forests, Bagged SVMs, and Bagged Neural Networks) assign uniform voting power to all constituent estimators. However, this naive uniform prior ignores the varying local competence of base estimators and contributes to model overconfidence. We formulate ensemble pruning and calibration as a joint optimization problem over the probability simplex by minimizing the Out-Of-Bag (OOB) loss. To induce sparsity, we address the theoretical "L1-simplex paradox" – the mathematical reality that the L1 norm is constant on the simplex and fails to prune – by introducing a concave quadratic penalty. SCSB is model-agnostic and achieves up to 96% ensemble compression, yielding linear inference speedups and superior probability calibration (lowered Expected Calibration Error) while preserving or enhancing generalization accuracy.

Read & Discuss → View Source →
05.
arXiv (CS.CL) 2026-06-12

BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection

Authors:
Saukun Thika You↗Nguyen Anh Khoa Tran↗Wesley K. Marizane↗Hanshu Rao↗Qiunan Zhang↗Xiaolei Huang↗

Terminology substitution errors in clinical notes, where one medical term is replaced by a linguistically valid but clinically different term, pose a persistent challenge for automated error detection in healthcare. We introduce BLUEmed, a multi-agent debate framework augmented with hybrid Retrieval-Augmented Generation (RAG) that combines evidence-grounded reasoning with multi-perspective verification for clinical error detection. BLUEmed decomposes each clinical note into focused sub-queries, retrieves source-partitioned evidence through dense, sparse, and online retrieval, and assigns two domain expert agents distinct knowledge bases to produce independent analyses; when the experts disagree, a structured counter-argumentation round and cross-source adjudication resolve the conflict, followed by a cascading safety layer that filters common false-positive patterns. We evaluate BLUEmed on a clinical terminology substitution detection benchmark under both zero-shot and few-shot prompting with multiple backbone models spanning proprietary and open-source families. Experimental results show that BLUEmed achieves the best accuracy (69.13%), ROC-AUC (74.45%), and PR-AUC (72.44%) under few-shot prompting, outperforming both single-agent RAG and debate-only baselines. Further analyses across six backbone models and two prompting strategies confirm that retrieval augmentation and structured debate are complementary, and that the framework benefits most from models with sufficient instruction-following and clinical language understanding.

Read & Discuss → View Source →
06.
arXiv (CS.LG) 2026-06-15

NeST: Neuron Selective Tuning for LLM Safety

Authors:
Sasha Behrouzi↗Lichao Wu↗Mohamadreza Rostami↗Ahmad-Reza Sadeghi↗

arXiv:2602.16835v2 Announce Type: replace-cross Abstract: Safety alignment is essential for the responsible deployment of Large Language Models (LLMs). Yet, existing approaches often rely on heavyweight fine-tuning that is costly to update, audit, and maintain across model families. Full fine-tuning incurs substantial computational and storage overhead, while parameter-efficient methods, e.g., Low-Rank Adaptation (LoRA), trade efficiency for inconsistent safety gains and sensitivity to design choices. Safety intervention mechanisms reduce unsafe outputs without modifying model weights, but do not directly shape or preserve the internal representations that govern safety behavior. We present NeST, a Neuron-Selective Tuning framework for efficient post-hoc safety alignment. NeST identifies safety-relevant feed-forward neurons via activation probing on vanilla harmful and benign prompts, clusters neurons with similar activation profiles, and trains shared cluster-level updates while freezing the rest of the model. Importantly, NeST is trained only on vanilla malicious prompts, without using jailbreak-specific attack data, yet generalizes robustly to diverse jailbreaks. The learned updates are then folded into the original weights, incurring no inference-time overhead. Evaluated on 14 open-weight language and multimodal models, NeST outperforms lightweight baselines and approaches full fine-tuning robustness with significantly fewer trainable parameters. On text-only models, NeST reduces average jailbreak attack success rate from 44.5% to 1.1% while training only 0.4M parameters on average. Across multimodal settings, it reduces ASR from 55.3% to 1.1%, and for downstream fine-tuned variants, it restores safety by reducing ASR from 53.8% to 0.8%. These results show that robust, maintainable safety alignment can be achieved by concentrating adaptation on localized, functionally coherent safety structures.

Read & Discuss → View Source →
07.
arXiv (CS.AI) 2026-06-19

Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation

Authors:
Ahmad Farooq↗Kamran Iqbal↗

arXiv:2606.19632v1 Announce Type: cross Abstract: Multi-agent reinforcement learning (MARL) enables agents to develop coordination strategies through emergent communication, but neural policies lack the formal safety guarantees required for safety-critical robotic deployment in drone swarms and autonomous vehicle fleets. We present the first end-to-end framework for safety verification of learned multi-agent communication policies through policy abstraction: neural policies are distilled into interpretable decision trees, then formally verified, with empirical validation confirming that verified safety properties transfer to original networks. Our four-stage pipeline consists of domain-specific feature extraction from agent observations, decision tree distillation achieving 97.9% +/- 1.2% fidelity to neural policies, automated translation to PRISM probabilistic model checker specifications with complete feature-to-state-variable correspondence, and compositional verification of Probabilistic Computation Tree Logic (PCTL) properties via pairwise decomposition with union-bound aggregation and empirical neighbor modeling. Evaluating Vector-Quantized Variational Information Bottleneck (VQ-VIB) policies for multi-drone coordination with 5-7 agents, we verify 18 temporal logic properties across safety, liveness, and cooperation, achieving 88.9% property satisfaction with all five safety thresholds satisfied (0.3% collision probability vs. 1% threshold). Monte Carlo validation of original neural policies confirms that verified safety properties transfer with

Read & Discuss → View Source →
08.
arXiv (CS.LG) 2026-06-12

From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model Merging

Authors:
Zhenqian Zhu↗Yamin Hu↗Yiya Diao↗Weixiang Li↗Haodong Li↗Wenjian Luo↗

arXiv:2606.12498v1 Announce Type: cross Abstract: Model merging (MM) has gained significant attention as a cost-effective approach to integrate multiple task-specific models into a unified model. However, recent work reveals that MM is highly susceptible to backdoor attacks. Existing defenses based on task arithmetic often fail to eliminate backdoors without substantially degrading clean-task performance, owing to their reliance on direct parameter-space editing. To address this gap, we propose Linear Feature Path Minimization (LFPM), a backdoor mitigation framework for model merging, which introduces an anti-backdoor task vector into the backdoored merged model. Unlike prior approaches, LFPM formulates the backdoor robustness of the merged model from a unified feature-space perspective under the Cross-Task Linearity (CTL) framework, which leverages the approximate linearity of features across tasks. This perspective guides the optimization of the anti-backdoor task to suppress backdoors while preserving clean-task performance. Furthermore, we introduce an effective optimization mechanism based on gradient accumulation and loss path-integral, ensuring robust backdoor suppression along the interpolation path. Extensive experiments demonstrate that LFPM consistently exhibits strong robustness against backdoor attacks in both full fine-tuning and Parameter-Efficient Fine-Tuning (PEFT) settings.

Read & Discuss → View Source →
09.
arXiv (CS.CV) 2026-06-18

PEFT-MedSAM: Efficient Fine-Tuning of Medical Foundation Models for Explainable Skin Lesion Segmentation

Authors:
Asad Channa↗Abdullah Khan↗Asghar Ali Chandio↗Aamir Akbar↗Shahzad Memon↗Aqib Hussain↗Ameer Hamza↗

Automated segmentation of skin lesions using deep learning models for dermoscopic images can be very helpful in finding melanomas earlier than they would normally be detected. However, most deep learning methods available do not perform well. The aim of this paper is to present a parameter-efficient fine-tuning method called PEFT-MedSAM for adapting the Medical Segment Anything Model (MedSAM) to automatically segment dermoscopic skin lesions. The PEFT-MedSAM method uses only the lightweight mask decoder for training the model while keeping the pre-trained image encoder and prompt encoder frozen. The experiments performed on the ISIC 2018 benchmark dataset shows that PEFT-MedSAM obtains a dice coefficient of .9411 and an intersection over union value of .8918 when compared to both a fully trained U-Net baseline (.8715 dice coefficient) and zero-shot MedSAM inference (.8997 dice coefficient). The external validation of the model using PH2 dataset shows .9467 dice coefficient with +/- .0310 standard deviation. Supportive evidence for these claims include a p-value less than .0001 for Wilcoxon signed rank tests comparing the two datasets and bootstrap-estimated 95% confidence intervals of [.9364,.9447] that represent the estimated range of possible values for the average dice coefficient obtained by repeating the test. To increase clinical trustworthiness, we used Grad-CAM explainability along with a pointing game based evaluation methodology to evaluate the CNN baseline model on the validation set. The results showed that we had an accuracy rate of 98.27% on the validation set of 519 images and confirmed that the model classified regions containing skin lesions.

Read & Discuss → View Source →
10.
arXiv (CS.AI) 2026-06-12

WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning

Authors:
Renmin Cheng↗Changhao Chen↗

arXiv:2606.12852v1 Announce Type: new Abstract: Rapid advances have been made in developing general-purpose embodied agent in environments like Minecraft through the adoption of LLM-augmented hierarchical approaches. Despite their promise, low-level controllers often become performance bottlenecks due to repeated execution failures. We argue that a key limitation is not only the lack of episodic memory, but also the decoupling of what-where-when memory from which-why reasoning. To address this, we propose WISE (Which-Why Informed Semantic Explorer), a long-horizon agent framework with an enhanced low-level controller equipped with a Causal Event Graph that augments episodic memory with explicit causal structure linking observations to task relevance. Unlike prior work such as MrSteve, which relies on feature similarity for retrieval, WISE enables robust recall under viewpoint changes and supports opportunistic task reordering through causal reasoning. Building on this memory, we propose an Opportunistic Task Scheduler that dynamically re-prioritizes subtasks when causally relevant opportunities are detected. We further equip WISE with a multi-scale progressive exploration strategy to provide spatially comprehensive observations for downstream reasoning. Experiments show that WISE largely improves task success and efficiency on long-horizon sparse tasks, particularly in settings requiring adaptive decision-making.

Read & Discuss → View Source →
11.
arXiv (math.PR) 2026-06-16

Stochastic control with dividend payments and capital injections for Markov additive processes

Authors:
Kei Noba↗

arXiv:2604.00190v4 Announce Type: replace Abstract: Motivated by de Finetti's optimal dividend problem with capital injections, we study a stochastic control problem for the additive component of a Markov additive process (MAP). In contrast to previous studies, the modulating component is allowed to be a general right process on a Radon space, so the model is not restricted to finite-state regime switching and cannot in general be reduced to a finite collection of Lévy process control problems. Capital injections are allowed at arbitrary times. We first consider the case in which dividend payments are allowed only at prescribed discrete times and establish necessary and sufficient conditions for the optimality of a strategy. These conditions then yield the optimality of a class of Markov-modulated periodic–classical barrier strategies. Combining this optimality result with an approximation argument, we obtain insight into the possible form of optimal strategies in the case where dividend payments, like capital injections, may be made at arbitrary times. Because of the generality of the MAPs considered here, the proof techniques used in previous studies of similar problems are not directly applicable. We therefore develop an alternative argument based on the additive structure of MAPs and dynamic programming between dividend opportunities. The argument also suggests a possible approach to other stochastic control problems involving general MAPs.

Read & Discuss → View Source →
12.
arXiv (CS.CL) 2026-06-17

PARSE: Provenance-Aware Retrieval Sanitization for Professional Domain LLM Agents

Authors:
Aaditya Pai↗

Prompt injection defenses evaluated on synthetic benchmarks do not generalize to real enterprise documents, which are longer, denser, and interleave legitimate authority language with factual content. We demonstrate this gap with a real-document benchmark of 122 tasks across five professional domains (financial, legal, medical, scientific, DevOps) using actual SEC filings, Federal Register rules, PubMed abstracts, arXiv papers, and GitHub postmortems. Paraphrasing, the strongest defense on synthetic benchmarks, shows no statistically significant attack success rate reduction on real documents (p=0.500) while degrading utility from 91.8% to 82.8%. We introduce PARSE (Provenance-Aware Retrieval Sanitization), a domain-aware, fact-preserving sanitization pipeline that classifies each sentence by injection likelihood, extracts structured facts before rewriting, and verifies fact preservation via a consistency-checking loop. A directiveness gate routes 59% of real enterprise documents to a lightweight path, concentrating computational cost on high-risk documents. PARSE achieves 15.6% attack success rate – a 38% reduction versus the 25.4% baseline – at 86.9% utility, the only condition that is both statistically significant (p=0.014, adequately powered) and maintains near-baseline utility. Practitioners should evaluate defenses on domain-matched real documents, not synthetic proxies.

Read & Discuss → View Source →
13.
arXiv (CS.CL) 2026-06-12

Agents' Last Exam

Authors:
Yiyou Sun↗Xinyang Han↗Weichen Zhang↗Yuanbo Pang↗Tianyu Wang↗Yuhan Cao↗Yixiao Huang↗Chris Duroiu↗Haoyun Zhang↗Jeffrey Lin↗Weishu Zhang↗Tyler Zeng↗…

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long horizon, economically valuable, real world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 sub fields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is below 1%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP relevant impact.

Read & Discuss → View Source →
14.
arXiv (CS.LG) 2026-06-16

Discovering Subgroups with Exceptional Survival Characteristics

Authors:
Mhd Jawad Al Rahwanji↗Sascha Xu↗Nils Philipp Walter↗Jilles Vreeken↗

arXiv:2602.22179v2 Announce Type: replace Abstract: In many applications, it is important to identify subpopulations that survive longer or shorter than the rest of the population. In medicine, for example, it allows determining which patients benefit from treatment, and in predictive maintenance, which components are more likely to fail. Existing methods for discovering subgroups with exceptional survival characteristics rely on restrictive assumptions about the survival model (e.g. proportional hazards), require pre-discretized features, and, as they compare average statistics, tend to overlook individual heterogeneity. In this paper, we propose Sysurv, a non-parametric, fully differentiable method that discovers human-readable rules selecting subgroups with exceptional survival characteristics. Empirical evaluation on a wide range of datasets and settings, including a case study on cancer data, shows that Sysurv reveals insightful and actionable survival subgroups, outperforming the state of the art.

Read & Discuss → View Source →
15.
medRxiv (Medicine) 2026-06-17

High burden of subclinical TB in Africa revealed from a postmortem cohort.

Authors:
Ahimbisibwe↗NAKIBUULE↗Ssejjoba↗M. M↗Lekuya↗Kizito↗A. M↗Cose↗Mulwana↗Bisoboka↗C. P↗Turyasingura↗…

Tuberculosis (TB) is increasingly recognised as a spectrum of infection and disease, yet the prevalence of viable, asymptomatic Mycobacterium tuberculosis (M.tb) infection remains uncertain. Subclinical Tuberculosis (scTB), defined as microbiologically confirmed M.tb infection in the absence of recognised symptoms, is under detected by symptom, sputum and imaging-based approaches. We conducted postmortem examinations of 94 adults who died from non-infectious causes, none of whom were clinically suspected of TB or reported TB related symptoms prior to death. Lung and extrapulmonary tissues were cultured for M.tb. Viable M.tb was confirmed in six individuals, corresponding to a prevalence of 6.4% (95% CI: 2.4 to 13.4%). These findings provide direct tissue-based evidence that viable, asymptomatic M.tb infection can persist beyond the reach of conventional clinical detection. Our data suggest that a biologically active reservoir of infection may exist undetected within high-burden settings, with implications for surveillance strategies aimed at TB elimination.

Read & Discuss → View Source →
16.
arXiv (CS.CL) 2026-06-16

SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks

Authors:
Jingru Guo↗Xiangyuan Xue↗Lian Zhang↗Wanghan Xu↗Siki Chen↗Philip Torr↗Wanli Ouyang↗Lei Bai↗Zhenfei Yin↗

Frontier scientific reasoning remains a major challenge for large language models (LLMs), where even the strongest commercial systems fall short of expert-level performance. A closer look at model behavior reveals substantial complementarity that single-model evaluation hides: different frontier models excel on different question types, and no single model captures the full picture. We present SciOrch, a framework that trains a lightweight 8B model to orchestrate frontier LLMs for scientific reasoning. The orchestrator decomposes each question, delegates sub-problems to selected commercial models through API calls, and synthesizes a final answer. Training such an orchestrator is fundamentally harder than conventional agentic RL: each action triggers an API call that is expensive in both dollar cost and latency, making standard online rollouts infeasible. We address this with MCTS-based approach, producing diverse orchestration trajectories, extracting per-node single-turn samples, and optimizing the orchestrator with GRPO-style training. On a 240-question test set spanning SGI-Reasoning and Scientists' First Exam, SciOrch reaches 56.66% average accuracy, outperforming the strongest single commercial model by 3.74% and the strongest multi-agent baseline by 3.33%. It also attains the best accuracy on both SGI and SFE with less than half the API cost of typical multi-agent methods.

Read & Discuss → View Source →
17.
arXiv (CS.CV) 2026-06-12

Visual enhancement and 3D representation for underwater scenes: a review

Authors:
Guoxi Huang↗Haoran Wang↗Brett Seymour↗Evan Kovacs↗John Ellerbroc↗Dave Blackham↗Nantheera Anantrasirichai↗

Underwater visual enhancement (UVE) and underwater 3D reconstruction pose significant challenges in computer vision and AI-based tasks due to complex imaging conditions in aquatic environments. Despite the development of numerous enhancement algorithms, a comprehensive and systematic review covering both UVE and underwater 3D reconstruction remains absent. To advance research in these areas, we present an in-depth review from multiple perspectives. First, we introduce the fundamental physical models, highlighting the peculiarities that challenge conventional techniques. We survey advanced methods for visual enhancement and 3D reconstruction specifically designed for underwater scenarios. The paper assesses various approaches from non-learning methods to advanced data-driven techniques, including Neural Radiance Fields and 3D Gaussian Splatting, discussing their effectiveness in handling underwater distortions. Finally, we conduct both quantitative and qualitative evaluations of state-of-the-art UVE and underwater 3D reconstruction algorithms across multiple benchmark datasets. Finally, we highlight key research directions for future advancements in underwater vision.

Read & Discuss → View Source →
18.
arXiv (CS.CL) 2026-06-11

Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation

Authors:
Selen Erkan↗Bastian Boll↗Kristian Kersting↗Bj\"orn Deiseroth↗Letitia Parcalabescu↗

Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.g., on the model's ability to follow specific formatting requirements. This especially penalizes base models that may know the correct answers but lack the ability – typically introduced in post-training – to structure them as instructed. To overcome this, we propose soft-prompt tuning, an efficient, fair, and architecture-agnostic model evaluation. By optimizing only 10 soft-prompt vectors (roughly 0.0006% parameters for a 7B model) over a short tuning period, we adapt models to specific benchmark formats, closing gaps in format-following and ensuring that underlying knowledge is accurately reflected in benchmark scores. This allows one to fairly compare different base models – trained with various pre-training recipes – on benchmarks without the need for full post-training. We evaluated soft-prompt tuning across 7 models and 7 datasets. The results show that (a) soft-prompt tuning saturates format-following within 80 steps (~640 samples) making it highly efficient, (b) soft-prompt tuning significantly outperforms zero- and few-shot prompting, surfacing base model knowledge that standard prompting misses, that (c) even post-trained models can benefit from soft-prompts to maximize format compliance, and that (d) soft-prompted base model performance predicts post-trained model rankings more reliably than zero- and few-shot baselines, offering a low-cost proxy for downstream model quality. Our contributions include (1) metrics which disentangle format-following and knowledge accuracy, (2) a fairer benchmarking protocol of LLM knowledge, and (3) a cost- and memory-effective recipe to identify optimal pre-training strategies early in LLM development.

Read & Discuss → View Source →
19.
arXiv (CS.LG) 2026-06-17

AoiZora: Topology-Aware Auto-Parallel Optimization for Inference of Diffusion Transformers

Authors:
Kaijian Wang↗Yuanyuan Xu↗Fanjiang Ye↗Ye Cao↗Jingwei Zuo↗T. S. Eugene Ng↗Yarong Mu↗Yuke Wang↗

arXiv:2606.17566v1 Announce Type: cross Abstract: Video diffusion has quickly grown into a key generative serving workload, yet producing each clip demands many denoising iterations over large spatio-temporal latents, which puts low-latency inference out of reach on a single device. A denoising step is therefore typically distributed across multiple accelerators, and TPU sub-slices have become an attractive and practical fabric for doing so. Current auto-parallel systems, however, search almost exclusively over logical device meshes and disregard how a chosen sharding is actually laid out on the physical TPU interconnect – an oversight that leaves large, topology-dependent performance on the table. We address this gap with AoiZora, a compiler-mediated topology planner built for low-latency video diffusion inference on TPU sub-slices. Its guiding principle is to reconnect logical sharding with physical placement by drawing on different points in the compilation flow: AoiZora first eliminates weak sharding candidates from inexpensive pre-compilation IRs, then compiles only the ones that survive and orders their physical placements using compiled HLO together with a topology-aware communication model. The winning plan is realized along the ordinary compiler path, leaving model code, compiler lowering, collective kernels, and network routing entirely intact. On TPU v5e sub-slices, AoiZora reduces Wan 2.1 one-step denoising latency by as much as 1.42x relative to existing solutions.

Read & Discuss → View Source →
20.
arXiv (CS.CL) 2026-06-17

Security and Privacy Prompts in the Wild: What Users Ask LLMs and How LLMs Respond

Authors:
Hobin Kim↗Xiaoyuan Wu↗Omer Akgul↗Lujo Bauer↗Nicolas Christin↗

Large language models (LLMs) are widely used to fulfill users' information needs; users ask LLMs about the weather, pose educational questions, and consult them for legal assistance. One particularly understudied area is digital security and privacy (S&P), where users may seek LLMs' help on how to secure their online accounts or protect their computers from cyber attacks. To the best of our knowledge, no prior study has collected or analyzed the S&P questions users ask LLMs; prior research on LLM response quality relied on expert-authored S&P misconceptions or FAQs rather than user queries. Drawing from WildChat, a dataset of 3.2M user-LLM conversations collected in the wild, our study identifies 14,727 S&P prompts and categorizes them into nine categories covering a wide range of S&P topics. From the S&P prompts, we sampled 450 and performed a thematic analysis to characterize the S&P questions users ask LLMs. Separate from the thematic analysis, we curated 270 advice-seeking S&P prompts, where users ask for recommendations, guidance, or specific S&P information. We measured LLM response quality and consistency when posing the prompt to LLMs 10 times. We found that commercial LLMs outperform open-weight models (GPT 5.5 provided "good enough" responses on 98% of prompts; Llama 4 on 47%). However, among prompts that received high-quality responses on average, commercial models sometimes produce contradictory responses across runs, risking confusing or misleading users.

Read & Discuss → View Source →
21.
medRxiv (Medicine) 2026-06-11

A global cross-sectional survey of health professionals' interest-confidence gaps in value-based health care implementation: a learning needs assessment

Authors:
Lewis↗Andrews↗Laing↗

Abstract Objectives Value-Based Health Care (VBHC) increasingly guides health system redesign internationally. Despite the increasing availability of VBHC education, gaps remain between health professionals' conceptual understanding of VBHC and their confidence to implement it in practice. This study assessed perceived learning needs and preferences of healthcare professionals across foundational topics essential to VBHC implementation. Design Cross-sectional online survey study Setting and participants The survey was distributed to the global VBHC community and yielded 518 responses. Most respondents were based in the UK and Ireland (51%) and 65% had more than 10 years of experience in the health sector. Participants represented a variety of professional backgrounds, including clinicians (34%), operational or executive managers and leaders (22%), and life sciences or procurement professionals (13%). Primary and secondary outcome measures Primary outcome measures included self-reported interest and confidence across 15 VBHC domains and the magnitude of the gap between them. Secondary outcomes included perceived implementation challenges and preferred VBHC learning approaches, including prior engagement with VBHC-related learning. Results Respondents identified substantial VBHC implementation challenges, including implementing outcome measurement (62.4%), conflicting priorities (57.7%), and resistance to change (56.8%). Interest in all VBHC domains was high (median >= 80/10), while confidence to implement remained substantially lower across most domains (median

Read & Discuss → View Source →
23.
arXiv (CS.LG) 2026-06-19

When Calibration Fails the Vulnerable Hospital: Federated Conformal Risk Control via Risk-Curve Shrinkage

Authors:
Nafis Fuad Shahid↗

arXiv:2606.20115v1 Announce Type: new Abstract: Conformal risk control (CRC) provides distribution-free guarantees on segmentation quality by calibrating a prediction-set threshold on held-out data. In federated deployments, the standard approach pools calibration scores across sites into a single threshold. We provide the first quantification, on real multi-institutional brain tumor data (FeTS-2022, 1,251 subjects, 20 institutions), showing that this naive pooled CRC protects the average hospital but violates coverage at 40% of individual institutions, with the worst site exceeding the target false-negative rate by 7.8 percentage points. The naive alternative, per-site local CRC, largely restores coverage but inflates prediction sets by 83x, rendering them clinically useless. We propose a shrinkage-based federated CRC protocol: each site transmits only its empirical risk curve (G scalars) to a server, which computes a shrinkage-regularized threshold per site. A single hyperparameter n0 smoothly trades worst-case coverage for prediction-set efficiency; leave-one-site-out sensitivity analysis identifies n0=19, achieving 2.7/20 violations at 2.0x stretch. We further show that direct Lagrangian optimization of coverage budgets fails, concentrating risk on vulnerable hospitals, and that the finite-sample correction term is essential: removing it triples violations. The marginal CRC guarantee is preserved by construction under the stated site-mixture assumption; per-site coverage is validated across four targets with three seeds. No patient-level images, masks, or per-volume scores leave any site.

Read & Discuss → View Source →
24.
arXiv (CS.CV) 2026-06-18

Quantile Transfer for Reliable Operating Point Selection in Visual Place Recognition

Authors:
Dhyey Manish Rajani↗Michael Milford↗Tobias Fischer↗

Visual Place Recognition (VPR) is a key component for localisation in Global Navigation Satellite System (GNSS)-denied environments, but its performance critically depends on selecting an image matching threshold (operating point) that balances precision and recall. Thresholds are typically hand-tuned offline for a specific environment and fixed during deployment, leading to degraded performance under environmental change. We propose a method that automatically selects the operating point of a VPR system to maximise recall at 100% precision. The method uses a small calibration traversal with known correspondences and transfers thresholds to deployment via quantile normalisation of similarity score distributions. This quantile transfer ensures that thresholds remain stable across calibration sizes and query subsets. Experiments with seven state-of-the-art VPR techniques across five benchmark datasets demonstrate that our proposed approach consistently outperforms existing baselines, enabling the underlying VPR technique to operate at 100% precision in approximately twice as many deployment scenarios (median improvement), while retrieving up to 29% more correct matches at that precision. The method eliminates manual tuning by adapting to new environments and generalising across operating conditions. Our code is available at https://github.com/DhyeyR-007/Quantile-Transfer-for-Reliable-VPR.

Read & Discuss → View Source →
25.
arXiv (CS.AI) 2026-06-11

Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization

Authors:
Frank Xiao↗Mary Phuong↗

arXiv:2606.12016v1 Announce Type: cross Abstract: Model post-training, and in particular reinforcement learning (RL), is one of the primary mechanisms by which developers can shape models' values and behaviors. However, as models become increasingly evaluation and training aware, they may be motivated to resist training when the perceived objective conflicts with their current values, undermining developers' ability to detect misalignment and correct model behavior through further training. In this paper, we demonstrate generalization hacking, in which a model collects reward during RL while preventing the rewarded behavior from generalizing. We construct a model organism on Qwen3-235B-A22B, finetuning on synthetic documents describing training awareness and self-inoculation, a novel mechanism in which the model frames compliance as context-specific in its chain of thought, without demonstrating or instructing either behavior. The model organism achieves train-time harmfulness comparable to controls while maintaining a persistent ${\sim}15$ percentage point compliance gap across 700 steps of RL. Additionally, a control organism trained only on training awareness documents independently discovers inoculation-like reasoning under RL pressure, developing its own compliance gap despite never being exposed to the concept. Because the generalization-hacking organism receives high reward throughout, standard training metrics provide no signal that generalization has failed. Our results constitute the first demonstration that a model can actively resist RL behavioral modification while maintaining high reward, suggesting that as models become more capable and training-aware, they may be able to undermine the training process itself.

Read & Discuss → View Source →