Explore the Frontier of Global Academia

01.

medRxiv (Medicine) 2026-06-17 DOI: HASH:df041ec0ec230670ae40dbce596186e3

Clinician knowledge and self-efficacy in snakebite management: A cross-sectional assessment in Northern Uganda

Authors:

Kamugisha↗MUSOKE↗Ssewante↗Bongomin↗

Background: Snakebite envenomation (SBE) is a major public health crisis in rural Uganda, yet it remains a neglected tropical disease. Effective management is often compromised by systemic barriers and a lack of clinician training. This study assessed clinician self-efficacy and objective knowledge regarding SBE management in Northern Uganda. Methods: A descriptive, cross-sectional study was conducted between February and July 2025 among 379 healthcare workers in Gulu, Omoro, and Pader districts. A validated questionnaire was used to collect data on socio-demographics, self-reported efficacy (scale 1-10), and objective knowledge. Knowledge scores [&ge;]70% were categorized as adequate. Multivariable logistic regression identified independent predictors of adequate knowledge, and Spearmans correlation ({rho}) assessed the relationship between knowledge and self-efficacy. Results: The participants had a mean age of 35.6 years (SD {+/-}7.3), were predominantly female (56.5%, 214/379), and most (83.6%, 317/379) practiced at Health Centre III level facilities. While 53.8% (204/379) reported prior training, 48.3% (183/379) of these had not received an update in over 10 years. Adequate knowledge was demonstrated by 51.5% (195/379) of participants. In the multivariable analysis, practicing in Omoro (adjusted odds ratio [aOR]: 0.3, 95% CI: 0.1-0.6, p < 0.001) or Pader (aOR: 0.2, 95% CI: 0.1-0.4, p < 0.001) was associated with lower odds of adequate knowledge compared to Gulu district. Prior training significantly increased the odds of adequate knowledge (aOR: 2.3, 95% CI: 1.3-4.2, p = 0.006). A moderate positive correlation was observed between self-efficacy and objective knowledge (Spearmans {rho} = 0.33, p < 0.0001). Conclusion: Approximately half of the frontline healthcare workers in Northern Uganda lack adequate knowledge on SBE management, with significant geographic differences and outdated training. The gap between clinician self-efficacy and objective knowledge poses a risk to patient safety. Regular, mandatory refresher training and targeted educational outreach to remote districts are required to reduce SBE-related morbidity and mortality.

Read & Discuss → View Source →

02.

medRxiv (Medicine) 2026-06-17 DOI: HASH:3eea85dd95332d9ff6d33073607a5595

Short-term relaxation after cervical rotatory manipulation is more closely associated with somatosensory input than cracking sound: a randomized controlled EEG study

Authors:

Lin↗Zhong↗yu↗Tang↗Xue↗Wei↗Li↗

Background Cervical rotatory manipulation is commonly used for neck-related symptoms and is often accompanied by a cracking sound. This sound is frequently regarded as a sign of successful manipulation, but whether it contributes substantially to the immediate relaxation response remains unclear. Objective This study examined whether short-term relaxation after cervical rotatory manipulation is more closely related to manipulation-associated sensory input than to the cracking sound cue alone. Methods In this single-session, three-arm, parallel randomized controlled study, 54 healthy volunteers were allocated to cervical rotatory manipulation, sham manipulation, or sham manipulation plus simulated cracking sound. Subjective outcomes were assessed before and after intervention, including positive affect, negative affect, comfort, and satisfaction. Eyes-closed resting-state electroencephalography was recorded before and after intervention. Prespecified neural outcomes included frontal alpha power, frontal alpha/beta ratio, occipital individual alpha frequency, and alpha-band fronto-parietal and fronto-temporal functional connectivity. Results Cervical rotatory manipulation produced greater improvements in positive affect, comfort, and satisfaction than sham manipulation or sham manipulation plus simulated cracking sound, whereas negative affect remained generally stable across groups. These subjective responses were accompanied by short-term electroencephalography changes, particularly in frontal alpha/beta and alpha-band fronto-parietal and fronto-temporal functional connectivity. Changes in frontal alpha/beta ratio were positively associated with changes in positive affect. In contrast, simulated cracking sound alone did not reproduce the full subjective or electroencephalography response observed after real manipulation. Conclusions The immediate relaxation response after cervical rotatory manipulation appears to be more closely related to manipulation-associated sensory input than to the cracking sound cue alone. These findings provide preliminary neurophysiological evidence for distinguishing real manipulation effects from sound-related contextual cues.

Read & Discuss → View Source →

03.

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

Latent Action Pretraining Through World Modeling

Authors:

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.

Read & Discuss → View Source →

04.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15987

A Text Recognition Dataset from Sahidic Coptic Ancient Manuscripts

Authors:

Fabio Quattrini↗Carmine Zaccagnino↗Costanza Bianchi↗Silvia Cascianelli↗Rita Cucchiara↗

In this work, we target Handwritten Text Recognition (HTR) in low-resource scenarios, which arise from underrepresented languages, rare scripts, and degraded visual conditions typical of historical documents. We introduce SCAM (Sahidic Coptic Ancient Manuscripts), a new line-level dataset built from digitized ancient manuscripts written in the extinct Sahidic Coptic dialect. The dataset reflects a realistic and challenging setting, as it combines heterogeneous acquisition conditions across libraries with typical manuscript degradations such as ink fading, bleed-through, and material deterioration. In addition to visual complexity, SCAM poses significant linguistic challenges due to the scarcity of resources for Sahidic Coptic, its uncommon alphabet, and dialect-specific diacritics. To support research in low-resource HTR, we benchmark several state-of-the-art approaches based on different paradigms, highlighting their limitations and strengths in this setting. Our results underline the gap between current HTR performance on well-resourced modern scripts and historically grounded, low-resource scenarios, thus providing a reference point for future developments.

Read & Discuss → View Source →

05.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2510.16928

ChiKhaPo: A Large-Scale Multilingual Benchmark for Evaluating Lexical Comprehension and Generation in Large Language Models

Authors:

Emily Chang↗Niyati Bafna↗

Existing benchmarks for large language models (LLMs) are largely restricted to high- or mid-resource languages, and often evaluate performance on higher-order tasks in reasoning and generation. However, plenty of evidence points to the fact that LLMs lack basic linguistic competence in the vast majority of the world's 3800+ written languages. We introduce ChiKhaPo, consisting of 8 subtasks of varying difficulty designed to evaluate the lexical comprehension and generation abilities of generative models. ChiKhaPo draws on existing lexicons, monolingual data, and bitext, and provides coverage for 2700+ languages for 2 subtasks, surpassing any existing benchmark in terms of language coverage. We further show that 6 SOTA models struggle on our benchmark, and discuss the factors contributing to performance scores, including language family, language resourcedness, task, and comprehension versus generation directions. With ChiKhaPo, we hope to enable and encourage the massively multilingual benchmarking of LLMs.

Read & Discuss → View Source →

06.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2505.14368

From ASR to ASP: Evaluating Prompt Attack Vulnerabilities Against Open-Source LLMs

Authors:

Jiawen Wang↗Pritha Gupta↗Ivan Habernal↗Eyke H\"ullermeier↗Xiaoxue Gao↗Nancy F. Chen↗

Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to attacks that generate harmful or sensitive outputs. As open-source LLMs are increasingly adopted in high-impact applications such as finance, law, and healthcare, systematically investigating their security risks is becoming increasingly important towards trustworthy LLM era. This paper comprehensively studies effective prompt injection attacks against 14 widely used open-source and three closed-source LLMs on five attack benchmarks. Moreover, existing evaluation metrics mostly only consider the attack success rate, overlooking uncertainty in model responses. Our proposed Attack Success Probability (ASP) additionally captures uncertain behaviors for evaluation, where the model may initially refuse a harmful request but subsequently provide harmful guidance or vice versa, reflecting inconsistency and ambiguity in attack feasibility. By systematically analyzing the effectiveness of prompt injection attacks, we propose a straightforward and effective hypnotism attack; results show that this attack causes aligned language models, including Stablelm2, Mistral, Openchat, and Vicuna, to generate objectionable behaviors, achieving around 90% ASP. They also indicate that ignore prefix attacks can break all 14 open-source LLMs, achieving over 60% ASP on a multi-categorical dataset. We find that moderately well-known LLMs exhibit higher vulnerability to prompt injection attacks, highlighting the need to raise public awareness and prioritize efficient mitigation strategies.

Read & Discuss → View Source →

07.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18824

Where Will They Go? Modelling Multimodal Pedestrian Manoeuvres from Ego-centric Videos

Authors:

Yuxuan Xie↗Nicolas Pugeault↗Chongfeng Wei↗Hubert P. H. Shum↗Edmond S. L. Ho↗

Pedestrian trajectory prediction from an ego-centric camera is challenging since it depends on complex interactions with vehicles and scene context, as well as the intention of the pedestrian. By modelling correlation and intent from the historical and future trajectories of the pedestrian, it will usually result in a multimodal (i.e. multiple modes) distribution. Existing stochastic predictors often sample multiple futures from a single unimodal distribution, which can yield sub-optimal 'mixed-mode' trajectories that lie between distinct motion patterns and become implausible in real scenes. In this paper, we propose MMPM, a mode-aware framework that separately models future trajectory distributions into semantically meaningful modes based on the pedestrian's crossing behavior. MMPM consists of two modules: behavior-aware Pedestrian Interaction Module (PIM) that jointly captures pedestrian-vehicle and pedestrian-environment interactions by introducing gaze, head and hand gesture, and a CVAE-based Mode-aware Trajectory Predictor (MTP) module to model the future trajectory distributions on two modes, crossing and non-crossing the road, separately. A query-based decoder further enforces mode consistency during decoding. Experiments on PIE and JAAD datasets show that our method surpasses state-of-the-art baselines. Our proposed MTP is model-agnostic, which can be integrated into existing frameworks such as BiTrap-NP and SGNet-ED to further improve future trajectory prediction performance. We additionally introduce a data-driven validation protocol that matches predictions to spatio-temporally consistent ground-truth trajectories, demonstrating improved frame-wise displacement errors over previous work.

Read & Discuss → View Source →

08.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2412.06133

Symmetry and Topology of Monitored Quantum Dynamics

Authors:

Zhenyu Xiao↗Kohei Kawabata↗

arXiv:2412.06133v4 Announce Type: replace-cross Abstract: The interplay between unitary dynamics and quantum measurements induces diverse phenomena in open quantum systems with no counterparts in closed quantum systems at equilibrium. Here, we generally classify Kraus operators and their effective non-Hermitian dynamical generators, thereby establishing the tenfold classification for symmetry and topology of monitored free fermions. Our classification elucidates the role of topology in measurement-induced phase transitions and identifies potential topological terms in the corresponding nonlinear sigma models. Furthermore, we establish the bulk-boundary correspondence in monitored quantum dynamics: nontrivial topology in spacetime manifests itself as topologically nontrivial steady states and gapless boundary states in Lyapunov spectra, such as Lyapunov zero modes and chiral edge modes, leading to the topologically protected slowdown of dynamical purification.

Read & Discuss → View Source →

09.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2506.11139

Grids Often Outperform Implicit Neural Representations at Compressing Dense Signals

Authors:

Namhoon Kim↗Sara Fridovich-Keil↗

Implicit Neural Representations (INRs) have recently shown impressive results, but their fundamental capacity, implicit biases, and scaling behavior remain poorly understood. We investigate the performance of diverse INRs across a suite of 2D and 3D real and synthetic signals with varying effective bandwidth, as well as both overfitting and generalization tasks including tomography, super-resolution, and denoising. By stratifying performance according to model size as well as signal type and bandwidth, our results shed light on how different INR and grid representations allocate their capacity. We find that, for many tasks involving dense signals, a simple regularized grid with interpolation trains faster and to higher or comparable quality than any INR with the same number of parameters. We also find limited settings – namely fitting binary signals such as shape contours – where INRs outperform grids, to guide future development and use of INRs towards the most advantageous applications.

Read & Discuss → View Source →

10.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14072

Diffusion-Refined Segmentation and Vision-Language Interpretation for Pediatric Brain Tumor MRI

Authors:

Wentao Ke↗Jianche Liu↗

Accurate pediatric brain tumor segmentation remains challenging due to limited annotated data, heterogeneous imaging phenotypes, diffuse tumor boundaries, and class imbalance across tumor subregions. Here, we present a two-stage deep learning framework for improving multi-modal pediatric brain MRI segmentation and clinical interpretation. First, we evaluate 3D Res U-Net and Swin-UNETR baselines on BraTS-PEDs MRI scans, using four co-registered modalities to predict tumor core, whole tumor, and enhancing tumor regions. Second, we introduce diffusion-based refinement models conditioned on coarse Swin-UNETR predictions, including a 3D DDPM refiner and MedSegDiff. Conditioning substantially improves diffusion stability and performance, particularly for enhancing tumor boundary segmentation. Conditioned MedSegDiff achieves the strongest boundary agreement with the lowest HD95. Finally, predicted tumor volumes and representative segmentation overlays are integrated with a multimodal language model to generate structured radiology-style reports. Together, our results suggest that coarse-to-refined diffusion segmentation can improve pediatric tumor boundary delineation and support end-to-end interpretable AI-assisted neuro-oncology workflows.

Read & Discuss → View Source →

11.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11724

Mind the Perspective: Let's Reason Recursively for Theory of Mind

Authors:

Chao Lei↗Guang Hu↗Meng Yang↗Yanbei Jiang↗Nir Lipovetzky↗

arXiv:2606.11724v1 Announce Type: new Abstract: Theory of Mind (ToM) reasoning requires inferring agents' beliefs from partial and asymmetric observations, which remains an open challenge for LLMs. Existing prompting-based approaches improve ToM reasoning through observable-event filtering or temporal belief chains, without explicitly modeling nested beliefs. We introduce RecToM, an inference-time framework for ToM reasoning that models nested beliefs via recursive perspective construction. RecToM constructs each character perspective from the preceding character perspective along the character chain specified by the question, reducing higher-order belief questions to actual-world questions within the final constructed perspective. We further provide a KD45 analysis showing that RecToM's perspective construction induces a well-formed belief modality beyond simple event filtering. Experiments on ToM benchmarks, including Hi-ToM, Big-ToM, and FanToM, across multiple LLM backbones show that RecToM consistently outperforms recent advanced approaches, achieving state-of-the-art performance. Notably, RecToM reaches 100\% accuracy on Hi-ToM with GPT-5.4 and Qwen3.5, a benchmark requiring higher-order ToM reasoning.

Read & Discuss → View Source →

12.

medRxiv (Medicine) 2026-06-18 DOI: HASH:0102be157fe057bbcb06da21920c5c72

Diabetes is associated with increased nocturnal respiratory rate

Authors:

Gupta↗K. S↗Pedros-Valls↗Harrington↗Torres Barba↗King↗K. R↗

Background and Objective: Diabetes mellitus (DM) causes autonomic neuropathy, which may alter nocturnal respiratory rate (NRR). To test the association between DM and NRR, we analyzed elective polysomnograms of four large observational cohorts. Research Design and Methods: We performed cross-sectional analysis of over 25,000 individuals with polysomnograms (PSGs) from the Sleep Heart Health Study (SHHS), Hispanic Community Health Study/Study of Latinos (HCHS/SOL), Osteoporotic Fractures in Men Study (MrOS), and Wisconsin Sleep Cohort (WSC). Patient-level NRRs were derived from inductance plethysmography waveforms. DM status was determined by self-report, physician diagnosis, medication use, or laboratory values, depending on the cohort. We related DM and NRR (continuous and dichotomized) using logistic regression models and adjusted for potential confounders. Cohort-specific results were combined using random-effects meta-analysis. Results: Meta-analysis of unadjusted models showed a pooled odds ratio (OR) of 1.10 (95% CI:1.04-1.17) for each breath-per-minute (brpm) increase in NRR. This association remained significant after multivariable adjustment (OR:1.06, 95% CI:1.02-1.11). Dichotomized analyses similarly showed higher odds of DM across dichotomization thresholds ranging from 15 to 21 brpm. At a threshold of 18 brpm, the unadjusted pooled OR was 1.77 (95% CI:1.23-2.55, P=0.0022), and the adjusted OR was 1.49 (95% CI:1.10-2.02, P=0.0098). Conclusions: Clinically stable outpatients with elevated NRR have an increased prevalence of DM. Additional studies are needed to investigate whether the mechanism is autonomic neuropathy and whether monitoring NRR can detect early complications of DM.

Read & Discuss → View Source →

13.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2603.15952

Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents

Authors:

Jacopo Teneggi↗S. M. Bargeen A. Turzo↗Tanya Marwah↗Alberto Bietti↗P. Douglas Renfrew↗Vikram Khipple Mulligan↗Siavash Golkar↗

arXiv:2603.15952v2 Announce Type: replace Abstract: Large language models (LLMs) are capable of emulating reasoning and using tools, creating opportunities for autonomous agents that execute complex scientific tasks. Protein design provides a natural testbed: although machine learning (ML) methods achieve strong results, these are largely restricted to canonical amino acids and narrow objectives, leaving unfilled need for a generalist tool for broad design pipelines. We introduce Agent Rosetta, an LLM agent paired with a structured environment for operating Rosetta, the leading physics-based heteropolymer design software, capable of modeling non-canonical building blocks and geometries. Agent Rosetta iteratively refines designs to achieve user-defined objectives, combining LLM reasoning with Rosetta's generality. We evaluate Agent Rosetta on design with canonical amino acids, matching specialized models and expert baselines, and with non-canonical residues – where ML approaches fail – achieving comparable performance. Critically, prompt engineering alone often fails to generate Rosetta actions, demonstrating that environment design is essential for integrating LLM agents with specialized software. Our results show that properly designed environments enable LLM agents to make scientific software accessible while matching specialized tools and human experts.

Read & Discuss → View Source →

14.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13934

Adversarial Concept Search: Predicting Compositional Errors From Feature Geometry

Authors:

Jennifer Meng Lu↗Ruochen Zhang↗Isabelle Lee↗David Alvarez-Melis↗Ellie Pavlick↗Naomi Saphra↗

arXiv:2606.13934v1 Announce Type: new Abstract: Humans cannot always intuit what scenarios are most challenging to LLMs. Hoping to capture challenging edge cases, developers either design problems to be difficult for humans or curate extensive benchmarks. What if we could instead anticipate which scenarios a model will fail on? In this paper, we use an LLM's representational geometry to predict which concept combinations it will fail on. We attribute this compositional failure to interference between salient features. In tasks that require systematic composition - toy programmatic settings, multihop reasoning, multilingual factual recall - we find that when a pair of concepts is encoded near-orthogonally, the model reliably composes them. When their linear encodings are close, producing interference, the model fails to compose them. Our method reliably anticipates failure modes across different compositional tasks, without evaluating specific inputs. These results lay the groundwork to use representational geometry to identify high-risk examples, construct targeted stress tests, and provide a scalable foundation for active learning in real-world deployment.

Read & Discuss → View Source →

15.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18733

SWE-Future: Forecast-Conditioned Data Synthesis for Future-Oriented Software Engineering Agents

Authors:

Qiao Zhao↗JianYing Qu↗Jun Zhang↗Yehua Yang↗Hanwen Du↗Zhongkai Sun↗

arXiv:2606.18733v1 Announce Type: cross Abstract: Realistic coding-agent benchmarks often replay public GitHub issues and pull requests, making them vulnerable to overlap with model pretraining, fine-tuning, synthetic-data generation, or benchmark-driven model selection. Fully synthetic tasks avoid direct historical replay, but can drift away from real repository needs. We propose SWE-Future, a forecast-conditioned data synthesis method for future-oriented coding tasks. Given a forecast snapshot at time $T_0$, the method uses only pre-$T_0$ repository evidence to forecast future feature implementation/enhancement, bugfix, and refactor task families. We first validate this forecasting step retrospectively: after forecasts are fixed, later pull requests are used only to measure whether the predicted task families match future repository work. In an 80-repository study, the forecaster achieves 58.1\% future-work relevance under the main semantic matching metric. We then use validated forecast families as conditioning signals to synthesize a 200-task coding-agent dataset across 61 repositories from a task-generation snapshot, rather than replaying the later pull requests used for validation. SWE-Future shows that repository-evolution forecasts can guide realistic, future-oriented coding-task synthesis while reducing direct dependence on historical pull-request replay.

Read & Discuss → View Source →

16.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2512.16242

Hardy-type self-testing and exposedness of tripartite GHZ correlations

Authors:

Smritikana Patra↗Soumyajit Pal↗Ranendu Adhikary↗

arXiv:2512.16242v2 Announce Type: replace Abstract: Nonlocality can be witnessed either through Bell-inequality violations or through logical contradictions such as Hardy's paradox. In the bipartite two input two outcome scenario, these two routes have distinct geometric behavior: CHSH-maximal correlations are exposed points of the quantum set, whereas known Hardy-type self-testing correlations on the no-signaling boundary are non-exposed. Here we show that this bipartite intuition fails in the tripartite two input two outcome scenario. We study the tripartite instance of a multipartite Hardy-type paradox and prove that the correlation attaining the maximal Hardy success probability self-tests the Greenberger–Horne–Zeilinger state and the associated measurements. Although this correlation lies on the no-signaling boundary, we show that it is an extremal and exposed point of the quantum correlation set. Moreover, it coincides with the correlation attaining the maximal violation of the Mermin inequality. Thus, in the tripartite GHZ scenario, the logical-paradox and Bell-inequality routes to nonlocality select the same exposed quantum boundary point. We also establish a robust version of the self-test, showing that small deviations from the ideal Hardy constraints imply quantitative closeness to the target state and measurements. Our results reveal a qualitative geometric difference between bipartite and tripartite Hardy-type nonlocality and suggest a broader investigation of exposedness for multipartite Hardy correlations in the multiparty setting.

Read & Discuss → View Source →

17.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2511.16672

EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards

Authors:

Omkar Thawakar↗Shravan Venkatraman↗Ritesh Thawkar↗Abdelrahman Shaker↗Hisham Cholakkal↗Rao Muhammad Anwer↗Salman Khan↗Fahad Khan↗

Recent advances in large multimodal models (LMMs) have enabled impressive reasoning and perception abilities, yet most existing training pipelines still depend on human-curated data or externally verified reward models, limiting their autonomy and scalability. In this work, we strive to improve LMM reasoning capabilities in a purely unsupervised fashion (without any annotated data or reward distillation). To this end, we propose a self-evolving framework, named EvoLMM, that instantiates two cooperative agents from a single backbone model: a Proposer, which generates diverse, image-grounded questions, and a Solver, which solves them through internal consistency, where learning proceeds through a continuous self-rewarding process. This dynamic feedback encourages both the generation of informative queries and the refinement of structured reasoning without relying on ground-truth or human judgments. When using the popular Qwen2.5-VL as the base model, our EvoLMM yields consistent gains upto $\sim$3\% on multimodal math-reasoning benchmarks, including ChartQA, MathVista, and MathVision, using only raw training images. We hope our simple yet effective approach will serve as a solid baseline easing future research in self-improving LMMs in a fully-unsupervised fashion. Our code and models are available at https://github.com/mbzuai-oryx/EvoLMM.

Read & Discuss → View Source →

18.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16990

Analytic Torsion and Spectral Gap Capture Persistent-Laplacian Performance

Authors:

Jernej Grlj↗Aaron D. Lauda↗

arXiv:2606.16990v1 Announce Type: new Abstract: While persistent Laplacians (PL) offer a richer geometric representation of data than persistent homology, utilizing their full eigenspectrum for learning tasks is often hampered by high dimensionality and the ``varying length'' problem across different filtration scales. We propose a compact spectral representation that distills the persistent Laplacian into three mathematically grounded invariants: Betti numbers, the spectral gap, and analytic torsion. Across benchmark datasets including MNIST, QM-3D, and SKEMPI WT, we demonstrate that this reduced feature space captures the essential predictive signal of the full spectrum, and in some cases outperforms it, while significantly reducing computational overhead and preventing the noise introduced by higher-frequency eigenvalues. Our results suggest that these invariants provide a principled, fixed-length interface between spectral geometry and topological learning.

Read & Discuss → View Source →

19.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16920

Demystifying Variance in Circuit Discovery of LLMs

Authors:

Frank Zhengqing Wu↗Francesco Tonin↗Volkan Cevher↗

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

Read & Discuss → View Source →

20.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2510.14217

Spectral Analysis of Molecular Features: When Richer Features Do Not Guarantee Better Generalization

Authors:

Asma Jamali↗Tin Sum Cheng↗Rodrigo A. Vargas-Hern\'andez↗

arXiv:2510.14217v2 Announce Type: replace Abstract: The spectral properties of feature embeddings offer critical insights into model generalization and representation quality. While deep learning models are widely used for molecular property prediction, kernel methods remain competitive in low-data regimes, yet their spectral behavior is largely unexplored. We present the first comprehensive spectral analysis of kernel ridge regression across diverse representations-including molecular fingerprints (ECFP), pretrained transformers, graph neural networks, and 3D descriptors-evaluated on QM9 and 3 MoleculeNet benchmarks. Surprisingly, richer spectral features do not consistently yield better generalization performance, contradicting common representation heuristics used in self-supervised learning (SSL). Across 4 spectral metrics, only ECFP-based kernels show a strictly positive correlation with performance. Transformer and global 3D representations exhibit mixed behavior, whereas local 3D representations show consistently negative correlations. Truncation analysis further emphasizes this disparity: for local 3D representations on thermodynamic targets, fewer than 2\% of eigenvalues (and occasionally as few as 0.02\%) are needed to recover 95\% of performance, whereas ECFP and transformer kernels require significantly more. By demonstrating a strong dependence on both task and representation, our results challenge the heuristic that richer spectra inherently improve generalization, providing new guidance for evaluating representations in SSL and in label-limited scientific tasks.

Read & Discuss → View Source →

21.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2602.15707

Proactive Conversational Assistant for a Procedural Manual Task based on Audio and IMU

Authors:

Rehana Mahfuz↗Yinyi Guo↗Erik Visser↗Phanidhar Chinchili↗

Real-time conversational assistants for procedural manual tasks often depend on video input, which can be computationally expensive and compromise user privacy. For the first time, we propose a real-time conversational assistant that provides comprehensive guidance for procedural manual tasks using only lightweight privacy-preserving modalities such as audio and IMU inputs from a user's wearable device to understand the context. Using a furniture assembly task and a cooking task, we show how this assistant proactively communicates step-by-step instructions to a user performing a procedural task, and answers user questions. We illustrate the data generation method and the system design to achieve such an assistant. On observing that an off-the-shelf language model is a talkative assistant but is not always able to answer questions correctly, we demonstrate how finetuning the model improves its ability to limit unnecessary dialogues with a 50% increase in the precision, while also improving its ability to answer questions correctly, measured by a 150% increase in the recall of answers. We further describe how such an assistant is implemented on an edge device with no dependence on the cloud.

Read & Discuss → View Source →

22.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2605.25929

Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?

Authors:

Franka Bause↗Jonas Niederle↗Martin Pawelczyk↗Rebekka Burkholz↗

arXiv:2605.25929v2 Announce Type: replace-cross Abstract: The effectiveness of multi-agent LLM deliberation depends not only on the agents' individual predictions, but also on how they communicate and collaborate. We study this mechanism through the lens of Friedkin-Johnsen (FJ) opinion dynamics, a tractable model for analyzing stubbornness, influence, and opinion change in multi-agent systems that captures empirically observed deliberation patterns. We show that the FJ parameters are input-dependent, turning multi-agent deliberation into a mixture of experts. This perspective implies that multi-agent systems can outperform single agents and static ensembles when routing reflects agent competence. Since competence is latent in practice, we analyze how influence is established through observable proxies: agents' self-assessed confidence, their perceived confidence, and initial alignment with other agents' views.

Read & Discuss → View Source →

23.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11416

MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation

Authors:

Yukuan Zhang↗Mengxin Zheng↗Qian Lou↗

arXiv:2606.11416v1 Announce Type: cross Abstract: Repository-level benchmarks for evaluating Large Language Model (LLM) code repair on Secure Multi-Party Computation (MPC) software do not yet exist, and directly transplanting general-purpose benchmarks such as SWE-bench fails on three structural fronts: (i) MPC repositories are dominated by generic Python infrastructure rather than cryptographic logic; (ii) high-value MPC fixes lack the standardized tests rigid extraction pipelines require; and (iii) standard fail-to-pass evaluation is insufficient for code that must also be cryptographically safe. MPC is increasingly deployed for privacy-preserving machine learning, biomedical collaboration, and secure analytics. Existing MPC-specific code-synthesis efforts cover only operator-level or single-framework tasks; evaluating LLM agents on real repository-level MPC repair instead demands MPC-aware data curation and a verifier matched to the security and numerical-fidelity guarantees MPC programs must obey neither of which existing benchmarks provide. We introduce MPC-Patch-Bench, a repository-level benchmark organised around two frameworks. (1)The Data Curation Framework combines a domain-specific curation agent that filters raw pull requests through three cryptographic layers with a human-AI completion engine that synthesizes missing problem statements and Fail-to-Pass/Pass-to-Pass tests, yielding 205 fully verified instances. (2)The MPC Verifier provides dedicated security and numerical-fidelity checks via dynamic differential testing against plaintext oracles and MPC-specific static analysis rules that flag unsafe reveals, insecure arithmetic, and illegal public/private casts. The strongest evaluated LLM functionally resolves only 22.9% of MPC-Patch-Bench tasks; the MPC Verifier further reduces verified resolution to 17.1%, with up to 40% of functionally-passing patches rejected for cryptographic or numerical-fidelity violations.

Read & Discuss → View Source →

24.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17542

Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings

Authors:

Ryo Fukuda↗Takatomo Kano↗Siddhant Arora↗Marc Delcroix↗Naohiro Tawara↗Atsunori Ogawa↗Yuya Chiba↗Atsushi Ando↗William Chen↗Shinji Watanabe↗

We investigate turn-taking in multimodal multi-party conversations using large language models (LLMs). We construct an evaluation framework for three tasks: addressee detection, turn-change prediction, and next speaker prediction. We compare supervised models trained for these tasks, text-based LLMs, multimodal LLMs (MM-LLMs), and human subjects. Experiments on the AMI corpus showed that LLMs outperformed supervised models and humans in next speaker prediction, despite not being trained on the target domain and without access to audio or visual information. An MM-LLM performed better than text-based LLMs on addressee detection and turn-change prediction but remained below human performance, indicating difficulty leveraging raw audio-visual signals. Ablation analyses revealed that conversational context was critical, particularly for next speaker prediction. We observed that human and LLM prediction patterns were similar, and intervals with frequent turn changes were difficult for both.

Read & Discuss → View Source →

25.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2505.03201

Enhancing Visual Feature Attribution via Weighted Integrated Gradients

Authors:

Kien Tran Duc Tuan↗Tam Nguyen Trong↗Son Nguyen Hoang↗Khoat Than↗Anh Nguyen Duc↗

arXiv:2505.03201v4 Announce Type: replace-cross Abstract: Integrated Gradients (IG) is a widely used attribution method in explainable AI, particularly in computer vision applications where reliable feature attribution is essential. A key limitation of IG is its sensitivity to the choice of baseline (reference) images. Multi-baseline extensions such as Expected Gradients (EG) assume uniform weighting over baselines, implicitly treating all baseline images as equally informative. In high-dimensional vision models, this assumption often leads to noisy or unstable explanations. This paper proposes Weighted Integrated Gradients (WG), a principled approach that evaluates and weights baselines to enhance attribution reliability. WG introduces an unsupervised criterion for baseline suitability, enabling adaptive selection and weighting of baselines on a per-input basis. The method preserves the core axiomatic properties of IG in a generalized weighted-baseline form. Under an expected, proxy-based fitness–relevance monotonicity assumption, WG provides a probabilistic justification for assigning larger weights to more informative baselines. Experiments on commonly used image datasets and models show that WG improves over EG under our protocol, with up to 36% gains across evaluated convolutional and Transformer architectures. These gains come with additional fitness-evaluation cost, so WG should be viewed as an attribution-fidelity trade-off rather than a faster alternative to EG. By moving beyond the assumption that all baselines contribute equally, Weighted Integrated Gradients offers a clearer and more reliable approach to explaining computer-vision models, improving both understanding and practical usability in explainable AI.

Read & Discuss → View Source →