Explore the Frontier of Global Academia

01.

medRxiv (Medicine) 2026-06-18 DOI: HASH:b9b240144e14468c9193cf554e47f082

Artificial Intelligence-informed mobile behavioural interventions to support adolescents mental health in schools: protocol for a randomised controlled trial using the MindCraft app

Authors:

Freccero↗Elkes↗Kadirvelu↗Versi↗Faisal↗Dewa↗L. H↗Di Simplicio↗Nicholls↗

Background: Children and young people (CYP) are particularly affected by mental health problems. Mobile apps provide a scalable and accessible approach to adolescent mental health support, and schools are well-positioned to address multiple risk factors and deliver large-scale interventions. By combining active (self-reported) and passive (sensor-derived) data, mobile apps can model mental states and deliver context-aware support. Artificial Intelligence (AI) enables adaptive, context-aware recommendations tailored to each user. However, there is limited research on AI-based mental health interventions in community CYP. MindCraft is a mobile app designed to monitor adolescents mental health using active and passive data and provide AI-informed recommendations ("nudges"). This study aims to investigate the effectiveness of personalised AI nudges delivered through MindCraft on improving mental health outcomes among adolescents in schools in the United Kingdom. Methods: The study is a three-arm RCT using a prospective cohort of secondary school students aged 14-19. Following informed consent, participants complete a baseline online assessment at school and download MindCraft. The primary outcome is the Strengths and Difficulties Questionnaire global and subscale scores. Secondary outcomes include the Eating Disorders Diagnostic Scale, the Sleep Condition Indicator Questionnaire, the Self-Injurious Thoughts and Behaviours Interview, the Self-Efficacy Questionnaire for Children and the World Health Organisation-Five Well-Being Index. Participants are randomised to: (1) an AI-informed intervention group receiving personalised nudges, (2) an active control receiving non-personalised nudges, or (3) a control group with self-monitoring only. Participants use the app for four weeks, with follow-up at one month. Repeated-measures analyses will assess changes across time points. Discussion: We hypothesise that AI nudges will have a greater positive effect on mental health outcomes at one month than general nudges and self-monitoring. Our findings will provide key evidence on the effectiveness of personalised mobile AI recommendations for adolescents mental health and inform school-based mental health prevention and early intervention. This study will contribute evidence on the ethical, acceptable, and scalable integration of AI-enabled digital mental health tools within public health and educational systems, with implications for the design of future digital public health interventions and policies supporting their safe integration in schools.

Read & Discuss → View Source →

02.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19852

Prompt, Plan, Extract: Zero-Shot Agentic LLMs Workflows for Lung Pathology Extraction from Clinical Narratives

Authors:

Aman Pathak↗Cheng Peng↗Mengxian Lyu↗Ziyi Chen↗Reema Solan↗Sankalp Talankar↗Yasir Khan↗Hiren Mehta↗Aokun Chen↗Yi Guo↗Yonghui Wu↗

Information extraction from pathology reports is essential for cancer staging, tumor registry population. Yet key data remains embedded in narrative reports, making manual extraction labor-intensive and error-prone. Traditional supervised Natural Language Processing pipelines address this through fully supervised Named Entity Recognition and Relation Extraction, but require expensive manual annotation and suffer cascading failures when upstream entities are missed. In this study, we developed a zero-shot, agentic workflow, and evaluated five open-source generative Large Language Models (LLMs) to populate 13 College of American Pathologists synoptic fields from lung resection pathology reports. We compared them against a state-of-the-art supervised GatorTron NER-RE baseline using a novel, registry-aligned evaluation framework. The baseline achieved Micro-F1of 0.960, while the best zero-shot model (GPT-OSS-20B) achieved Micro-F1 of 0.893 (recall: 0.949), accurately extracting complex relations like Pathologic Stage without task-specific training. These results suggest that open-source, zero-shot agentic LLMs are a low-cost solution for extracting lung pathology information.

Read & Discuss → View Source →

03.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.11652

IAPO: Input Attribution-Aware Policy Optimization for Tool Use in Small Multimodal Agents

Authors:

Yifan Yang↗Zhen Zhang↗Jiayi Tian↗Liyan Tan↗Zheng Zhang↗

arXiv:2606.11652v1 Announce Type: new Abstract: This paper investigates reinforcement learning (RL) methods for improving tool-calling capabilities in multimodal small language model (SLM) agents. While existing works have explored various reward designs to improve agentic tool-calling ability, these approaches face inherent limitations for SLM training, especially under multimodal scenarios. First, many existing methods evaluate tool use correctness through exact matching against certain ground-truth or predefined formats. However, this assumption is often unsuitable for multimodal tasks, where multiple tool use paths may be valid and annotated tool trajectories are typically unavailable. Second, such sparse and brittle binary rewards provide little guidance on how to improve the underlying decision process, making them particularly difficult for multimodal SLM to learn from. To address these issues, we propose Input Attribution-Aware Policy Optimization (IAPO), an RL algorithm for improving tool use in multimodal SLM by aligning the model's attribution across input components with that of a stronger teacher. Experiments on Qwen2.5-VL-3B show that the proposed method improves visual question answering accuracy by an average of 3% across six test sets compared with existing visual tool use work, by helping the model attend to the most relevant input evidence.

Read & Discuss → View Source →

04.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.06794

TA-RAG: Tone-Aware Retrieval-Augmented Generation for Peer-Support Health Communication

Authors:

Yong-Bin Kang↗Anthony McCosker↗

Retrieval-augmented generation (RAG) successfully grounds large language model (LLM) outputs in trusted documents, but factual grounding alone is insufficient for sensitive peer-support health communication. In domains such as HIV peer support, responses must also be accessible, stigma-free, empathetic, and tailored to the recipient. This paper presents TA-RAG, a lightweight, prompt-based tone-aware RAG framework that embeds explicit tone control into a RAG pipeline without requiring model fine-tuning. We operationalise tone across four core components: stigma-free rewriting, readability adjustment, recipient adaptation, and empathy rephrasing. We evaluate TA-RAG through component-level tests using questions derived from HIV Online Learning Australia (HOLA), UNAIDS terminology guidance, readability metrics, peer-support standards from National Association of People with HIV Australia (NAPWHA), and a public empathy dataset. Results show that the TA-RAG's components improve their targeted communication quality while preserving key content. These findings emphasise that prompt-based tone control is a potential direction for making RAG outputs suitable for sensitive peer-support health communication.

Read & Discuss → View Source →

05.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12883

The Hidden Power of Scaling Factor in LoRA Optimization

Authors:

Zicheng Zhang↗Haoran Li↗Jiaxing Wang↗Guoqiang Gong↗Anqi Li↗Yudong Hu↗Ting Xiong↗Yurong Gao↗Junxing Hu↗Zhida Jiang↗Yifeng Zhang↗Pengzhang Liu↗…

arXiv:2606.12883v1 Announce Type: new Abstract: In Low-Rank Adaptation (LoRA), the scaling factor $\alpha$ is often treated as a mere complement to the learning rate, yet its role in optimization remains poorly understood. In this paper, we reveal that the scaling factor $\alpha$ and the learning rate function differently, with $\alpha$ emerging as the dominant driver of effective optimization, delivering gains that cannot be replicated by learning rate scaling alone. Through the synergy of extensive empirical analysis and a theoretical Signal-Drift framework, we uncover three findings into LoRA's scaling mechanism: First, LoRA's spectral suppression smooths the optimization landscape, rendering standard hyperparameters overly conservative and creating an optimization gap. Second, when leveraging this smoothness to accelerate convergence, $\alpha$ outperforms the learning rate by amplifying the task signal without increasing the drift ratio. Third, the optimal scaling factor follows a sublinear relationship with the rank, well characterized by a square-root law with an unexpectedly large coefficient, revealing the insufficient scaling of existing rank-tied heuristics. Based on these insights, we propose LoRA-$\alpha$, a minimalist framework that restores $\alpha$ to its principled regime, making LoRA compatible with standard small learning rates. Extensive evaluations across diverse tasks demonstrate that LoRA-$\alpha$ consistently improves performance while streamlining hyperparameter search, unleashing the learning potential of LoRA.

Read & Discuss → View Source →

06.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2407.02362

Mitigating scalability challenges in LUT-based neural networks via pruning optimisations

Authors:

Xuqi Zhu↗Huaizhi Zhang↗JunKyu Lee↗Jiacheng Zhu↗Chandrajit Pal↗Sangeet Saha↗Klaus D. McDonald-Maier↗Xiaojun Zhai↗

arXiv:2407.02362v3 Announce Type: replace-cross Abstract: Modern deep neural networks heavily rely on a large number of multiply-accumulate operations, which constitute the predominant computational cost. To address this, Look-Up Table (LUT)-based matrix multiplications have emerged as a promising alternative for reducing the computational cost and time of the multiply-accumulate operations in a neural network. However, the LUT-based neural network still faces the scalability challenge due to the inherent limitations of LUT-based matrix multiplication. To mitigate these scalability limitations, this paper proposes a scalable and energy-efficient LUT-based approximate matrix multiplication unit (LUT-MU) constituting the basic component of the neural networks by integrating a pruning strategy on the MADDNESS algorithm, a LUT-based matrix multiplication methodology. With increasing problem size and precision demands in matrix multiplication, our proposed LUT-MU architecture effectively constrains resource expansion. The case study shows that deploying our LUT-MU in neural network architectures, including fully connected layers (MNIST) and ResNets (CIFAR-10, ImageNet)-on XCZU7EV and XCZU19EG FPGAs, produces up to $1.6 \times$ throughput improvement and $4.2 \times$ energy efficiency gains over mainstream CUDA-based network implementations, and $1.8\times$ energy efficiency compared to leading quantised neural network implementations, with moderate impact on accuracy. Compared to original MADDNESS-based neural networks, our LUT-MU shows $1.3$ to $2.6\times$ resource savings based on various resolution configuration settings of MADDNESS.

Read & Discuss → View Source →

07.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13473

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

Authors:

Jiacheng Chen↗Xinyu Zhang↗Shunkai Zhang↗Yanmohan Wang↗Lin Li↗Tiancheng Qin↗Qin Wang↗Zhengmao Zhu↗Tianle Li↗Jingyang Li↗Zehan Li↗Binyang Jiang↗…

We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabilities – proof generation, proof verification, and critique-conditioned proof repair – using a defense-in-depth generative verifier engineered for low false-positive rate. These capabilities are merged into a single released M3 model. At test time, MaxProof treats the model as a generator, verifier, refiner, and ranker, searches over a population of candidate proofs, and returns one final proof through tournament selection. With MaxProof test-time scaling, the M3 model reaches 35/42 on IMO 2025 and 36/42 on USAMO 2026, exceeding the human gold-medal threshold on both.

Read & Discuss → View Source →

08.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2502.07531

VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation

Authors:

Sixiao Zheng↗Zimian Peng↗Yanpeng Zhou↗Yi Zhu↗Hang Xu↗Xiangru Huang↗Yanwei Fu↗

Controllable image-to-video (I2V) generation transforms a reference image into a coherent video guided by user-specified control signals. While precise control over camera motion, object motion, and lighting is essential for high-fidelity creation, existing methods often treat these factors independently. This overlooks the physical coupling among viewpoint, geometry, and illumination in dynamic scenes, leading to visual inconsistencies such as mismatched shadows and perspective drift under simultaneous changes. We present VidCRAFT3, a unified and flexible I2V framework that explicitly models cross-factor interactions among geometry, motion, and illumination, enabling both independent and joint control over camera motion, object motion, and lighting direction. Image2Cloud provides explicit 3D geometric priors for accurate camera motion control. ObjMotionNet encodes sparse object trajectories into multi-scale motion features to guide realistic object motion. A Spatial Triple-Attention Transformer integrates lighting direction through lighting cross-attention for consistent relighting. To address the scarcity of jointly annotated data, we construct the VideoLightingDirection (VLD) dataset with accurate per-frame lighting direction annotations, and introduce a three-stage progressive training strategy that enables robust learning without fully joint annotations. Extensive experiments demonstrate that VidCRAFT3 achieves state-of-the-art performance in control precision and visual coherence across diverse scenarios.

Read & Discuss → View Source →

09.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14578

A Qualitative Review of GenAI-Based Methods for Data Generation and Augmentation in Industrial Computer Vision Applications

Authors:

Paul Koch↗Paul Hofmann↗Ferdinand Wa{\ss}elewsky↗Adem Karakurt↗Andre S\'ers↗J\"org Kr\"uger↗

AI-driven computer vision applications require a profound database to ensure predictable behaviors and performance. Such predictable behaviors are especially important for industrial applications in gaining trust from users. However, such a database is not readily available in industrial applications, and its acquisition is not trivial either. Active learning methods can be applied to ramp up data within a project deployment to iteratively increase the database, and thus the application predictability. Unfortunately, we observe that this often leads to a loss of user trust in the application, which is difficult to regain once lost. This leads to a "chicken-and-egg" dilemma in which neither the database nor the application is developed. In this work, we review state-of-the-art methods and approaches to further boost the database the initial active data ramp-up phase. Here, we focus on recent advancements in GenAI-based data generation and augmentation methods and review their adaptability on an industrial computer vision classification use case. Although we observe a potential for automatic data ramp-up, we also see a domain miss match in between the source (training environment) and target (industrial use-case) - regarding context defined in natural language and object characteristics.

Read & Discuss → View Source →

10.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2511.15645

FDIO: Frequency Decomposed Inertial Odometry

Authors:

Shanshan Zhang↗Liqin Wu↗Wenying Cao↗Lingxiang Zheng↗Yu Yang↗

Pedestrian inertial odometry (PIO) estimates autonomous pedestrian motion using only acceleration and angular velocity measurements collected by an inertial measurement unit (IMU), making it highly valuable for consumer level localization applications. However, under a dual device acquisition setting, IMU signals collected by a freely carried mobile device are inherently composite signals in which the global motion of the human torso is coupled with perturbations induced by local limb motion. This coupling makes accurate human motion modeling more challenging. To address this issue, this paper proposes frequency decomposed inertial odometry (FDIO). The proposed method first decomposes input IMU signals into low frequency and high frequency components using a Laplacian pyramid. It then adopts a Mamba module to model long range motion information from the low frequency component and uses a multi scale convolution module to extract fine grained local dynamic features from the high frequency component. Experiments on five public PIO datasets show that FDIO achieves an average absolute trajectory error of 3.221~m and an average relative trajectory error of 2.550~m, reducing the errors by 33.3\% and 16.7\% compared with the RoNIN ResNet baseline, respectively. These results validate the effectiveness of the proposed frequency decomposition strategy. To the best of our knowledge, this work is among the first efforts to introduce Mamba and a frequency decomposition architecture into inertial odometry.

Read & Discuss → View Source →

11.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18322

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

Authors:

Mingyue Cui↗Linghui Shen↗Xingyi Yang↗

arXiv:2606.18322v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) decompose residual-stream activations into interpretable features. Recent latent-space defenses increasingly rely on these decompositions, assuming that identified "unsafe" SAE features serve as actionable handles for monitoring and intervention. In this paradigm, clamping a specific harmful feature is expected to reliably prevent model misbehavior. However, we show that this success may hide a recoverable failure mode: the clamp may block one visible route to a behavior without eliminating the behavior itself. We formulate this vulnerability as post-intervention recovery, a constrained residual-space optimization problem. Starting from the post-intervention residual state, we optimize residual perturbations to recover the pre-intervention behavior while preserving the post-intervention values of the targeted SAE features. Even under a strong threat model where the intervention remains active throughout optimization and generation, recovery remains possible. To rule out that recovery simply undoes the intervention, we use encoder-orthogonal updates for single-layer interventions and the corresponding feature-map Jacobian in the cross-layer setting. Across TPP, unlearning, IOI, and refusal steering experiments, this stress test reveals recoverable behavior despite successful feature-level intervention. Especially in the safety-critical refusal-steering setting, we achieve a 95.8% recovery rate on valid samples while keeping defended-feature relative drift to 0.131, substantially below suffix-based baselines. A recovery-path attribution analysis further localizes this recovery to the SAE reconstruction residual, the component left unexplained by the SAE. These results expose a gap between feature-level control and behavioral completeness: SAE features can support causal intervention, but controlling them does not guarantee control over the underlying behavior.

Read & Discuss → View Source →

12.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.12849

SemanticXR: Low Power and Real-time Queryable Semantic Mapping with an Object-Level Device-Cloud Architecture

Authors:

Rahul Singh↗Devdeep Ray↗Connor Smith↗Sarita Adve↗

Semantic mapping is a core service that enables grounded interactions in emerging Extended Reality (XR) applications such as AI assistants and spatial object search. Deploying this capability on mobile XR devices requires a system that is open-vocabulary, real-time, and low-power. Existing approaches are compute-intensive and assume server-class resources. Cloud offloading offers a practical path, but no existing system splits semantic mapping across the device-cloud boundary or manages its communication, execution, and memory footprint. We present SemanticXR, the first device-cloud system for real-time, open-vocabulary semantic mapping and querying under XR power, bandwidth, and memory constraints. Our key insight is to elevate semantically identifiable objects to first-class units of communication, execution, and memory across the device and server. On the server, object-level parallelism and geometry downsampling improve mapping latency, while object-level depth-mapping co-design reduces upstream bandwidth. On the device, an object-level sparse local map with incremental updates and update prioritization enables network-robust querying with bounded memory and downstream bandwidth. Object-level configurable resource usage vs. quality trade-offs let applications and the system adapt mapping to application requirements and operating conditions, respectively. Against a device-cloud baseline with the same perception models, object-level organization improves server-side mapping latency by 2.2X at equal semantic quality. Depth-mapping co-design maintains upstream bandwidth under 2.5 Mbps. On the device, SemanticXR sustains sub-100 ms query latency for up to 10,000 objects even under network drops, supports tens of thousands of objects within 500 MB, and scales downstream bandwidth with map changes, not total scene size. The system adds only 2% device power during normal operation.

Read & Discuss → View Source →

13.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18548

Engagement Intensity as a Learner-Modeling Signal for Adaptive AI Ethics Instruction

Authors:

Yongkyung Oh↗Lynn Talton↗Alex Bui↗

arXiv:2606.18548v1 Announce Type: cross Abstract: Adaptive AI ethics instruction in graduate research training benefits from intake measures that reflect differences in prior LLM experience. Prior coursework or workshop attendance is an obvious candidate, but it is not clear whether it is associated with pre-instruction ratings on key AI perception items. We compare three candidate intake features, self-reported usage frequency, self-rated LLM familiarity, and prior AI education, across five baseline perception outcomes in 93 bioscience graduate and postdoctoral trainees enrolled in a required research ethics course. Usage frequency shows Holm-corrected associations with all five outcomes, self-rated familiarity with three, and prior AI education with none. A threshold-like pattern at the lower end of the scale is most visible for training interest and accuracy trust rather than appearing as a uniform gradient across all five outcomes. In a short intake survey, reported LLM use is more consistently associated with these perceptions than prior coursework or workshops, with self-rated familiarity serving as a secondary indicator. These results suggest that simple pre-instruction behavioral signals can inform lightweight intake profiling for adaptive AI ethics education.

Read & Discuss → View Source →

14.

arXiv (quant-ph) 2026-06-12 DOI: arXiv:2601.16564

A Robust Strontium Tweezer Apparatus for Quantum Computing

Authors:

Marijn Venderbosch↗Rik van Herk↗Zhichao Guo↗Jes\'us del Pozo Mellado↗Max Festenstein↗Deon Janse van Rensburg↗Ivo Knottnerus↗Yu Chih Tseng↗Alexander Urech↗Robert Spreeuw↗Florian Schreck↗Rianne Lous↗…

arXiv:2601.16564v2 Announce Type: replace-cross Abstract: Neutral atoms for quantum computing applications show promise in terms of scalability and connectivity. We demonstrate the realization of a versatile apparatus capable of stochastically loading a 5x5 array of optical tweezers with single $^{88}$Sr atoms featuring flexible magnetic field control and excellent optical access. A custom-designed oven, spin-flip Zeeman slower, and deflection stage produce a controlled flux of Sr directed to the science chamber. In the science chamber, featuring a vacuum pressure of $3 \times 10^{-11}$ mbar, the Sr is cooled using two laser cooling stages, resulting in $\sim 3 \times 10^5$ atoms at a temperature of 5(1) $\mu$K. The optical tweezers feature a $1/e^2$ waist of 0.81(2) $\mu$m, and loaded atoms can be imaged with a fidelity of $\sim 0.997$ and a survival probability of $0.99^{+0.01}_{-0.02}$. The atomic array presented here forms the core of a full-stack quantum computing processor targeted for quantum chemistry computational problems.

Read & Discuss → View Source →

15.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16163

Dehaze-GaussianImage: Zero-Shot Dehazing via Efficient 2D Gaussian Splatting Representation

Authors:

Yuhan Chen↗Wenxuan Yu↗Guofa Li↗Kunyang Huang↗Ying Fang↗Yicui Shi↗Wenbo Chu↗Keqiang Li↗

Existing single image dehazing methods are often constrained by computational redundancy in pixel-level optimization and the lack of physical interpretability in implicit neural networks. These limitations hinder the balance between representation efficiency and reconstruction fidelity. To address these issues, we propose Dehaze-GaussianImage, the first zero-shot framework that introduces 2D Gaussian Splatting (2DGS) into the image dehazing domain to break the traditional pixel-grid processing paradigm. Distinct from static convolutional neural networks (CNNs) or Transformers, our approach models hazy images as continuous and dynamically evolvable anisotropic Gaussian fields. Specifically, we propose a novel reconstruction-decoupling zero-shot learning strategy that embeds the atmospheric scattering model into the Gaussian parameter space. This strategy drives Gaussian primitives to adaptively split, clone, and prune during optimization, achieving geometric-level decoupling of the transmission medium and clear textures. Furthermore, explicit structure-preserving constraints are introduced to suppress artifacts commonly caused by traditional physical priors. Experimental results demonstrate that the proposed method achieves state-of-the-art (SOTA) performance in a fully unsupervised manner with minimal parameters, highlighting the potential of explicit Gaussian representation for low-level vision tasks.

Read & Discuss → View Source →

16.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15694

MAF: Multimodal Adaptive Few-shot Prompting for Sentiment Analysis with MLLMs

Authors:

Hangling Xie↗

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in understanding complex multimodal content. However, their performance in sentiment analysis exhibits acute sensitivity to prompt design, rendering static, uniformly applied prompts inherently suboptimal for capturing the nuanced multimodal cues that vary across inputs. To address this limitation, we propose a Multimodal Adaptive Few-Shot Prompting (MAF) framework, which dynamically retrieves and integrates query-relevant demonstrations to elicit the sentiment reasoning capabilities of MLLMs in a context-sensitive manner. MAF constructs a demonstration retrieval module that holistically encodes facial expressions, scene context, and textual semantics, with a lip movement amplitude detection mechanism introduced for accurate speaker identification in multi-person scenarios. Departing from conventional fixed-weight fusion, a lightweight coefficient generation network is trained to output query-conditioned fusion weights in real time, enabling weighted aggregation of multimodal similarity scores to retrieve the top-K most informative demonstrations. Prediction stability is further enhanced through majority voting over multiple candidate outputs generated by the MLLM. Extensive experiments on public benchmark datasets demonstrate that MAF achieves substantial and consistent performance improvements over the corresponding backbone variants and remains competitive with strong multimodal sentiment-analysis baselines.

Read & Discuss → View Source →

17.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16328

AdaSTORM: Scaling LLM Reasoning on Dynamic Graphs via Adaptive Spatio-Temporal Multi-Agent Collaboration

Authors:

Bing Hao↗Ruijie Wang↗Haodong Qian↗Yunlong Chu↗Yuhang Liu↗Yumeng Lin↗Minglai Shao↗Jianxin Li↗

arXiv:2606.16328v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate remarkable potential in dynamic graph reasoning, but suffer from a scaling bottleneck: current models can only handle graphs with tens of nodes, constrained by exponential reasoning overhead and finite context windows. While multi-agent systems (MAS) offer collective reasoning and topology-aware orchestration, capabilities naturally suited for graph-structured tasks, their application to dynamic graphs remains unexplored. This paper presents Scaling LLM Reasoning on Dynamic Graphs via Adaptive Spatio-Temporal Multi-Agent Collaboration (AdaSTORM), a framework that reformulates large-scale dynamic graph reasoning into two stages: (i) Adaptive Partitioning, partitioning large-scale dynamic graphs into subregions that match the model's reasoning capacity while minimizing inference cost; and (ii) Collaborative Reasoning, aligning graph partition topologies with a spatio-temporal decoupled multi-agent architecture. AdaSTORM is the first multi-agent framework tailored for dynamic graph reasoning. Extensive experiments show that AdaSTORM successfully breaks through the scaling bottleneck, scaling reasoning to thousand-node graphs with over 90% accuracy across several large-scale dynamic graph settings without external tools, significantly outperforms seven competitive baselines. Furthermore, it achieves state-of-the-art accuracy on existing benchmarks and generalizes robustly to real-world datasets. The source code is available at: https://github.com/irisorchid107/AdaSTORM/.

Read & Discuss → View Source →

18.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.03504

BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language

Authors:

Muhammad Ali↗

We present BaltiVoice, a 16.8-hour read-speech corpus for Balti (ISO 639-3: bft), a Tibetic language spoken in Gilgit-Baltistan, Pakistan, with no prior publicly available ASR resources. The corpus contains 10,060 validated utterances in native Nastaliq script, derived from Mozilla Common Voice recordings. Fine-tuning OpenAI Whisper-small yields a Word Error Rate (WER) of 26.74% and a Character Error Rate (CER) of 8.67% on a 538-utterance speaker-disjoint validation set, down from a zero-shot baseline of 159.19% WER and 152.52% CER. A Whisper-base fine-tuned on the same data achieves 44.54% WER and 15.61% CER, confirming that model capacity matters for this low-resource setting. The dataset, fine-tuned model, and a live transcription demo are publicly available on HuggingFace.

Read & Discuss → View Source →

19.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18436

Pointwise is Pointless? A Multimodal Ablation Study for Precipitation Nowcasting with Graph Neural Networks

Authors:

Oph\'elia Miralles↗M\'at\'e Mile↗Christoffer Artturi↗Thomas Nipen↗Ivar Seierstad↗

arXiv:2606.18436v1 Announce Type: cross Abstract: Sparse point observations are increasingly available for precipitation nowcasting, but it is unclear how much they improve dense radar-field forecasts. We partially address this question with a multimodal graph neural network nowcasting system over the Nordic radar domain. The model predicts rain rate every five minutes up to two hours ahead and is trained with different combinations of radar history, MEPS numerical weather prediction, Netatmo surface observations, MSG satellite channels, stochastic noise, and CRPS-based ensemble losses. The study is designed as an ablation of operationally relevant information sources and training objectives. We compare radar-only, NWP-informed, station-informed, satellite-informed, noise-augmented, and CRPS-based configurations using complementary diagnostics on the radar grid, at station locations, for rain onset, and through oracle, displacement, and amplitude scores. The results show that each source improves a different part of the forecast problem. MEPS stabilises radar-only extrapolation, Netatmo observations improve local station and onset diagnostics, and satellite predictors reduce some station-level biases but may activate rain too early when used deterministically. CRPS-based configurations provide the most consistent radar-grid gains, while the combined satellite and CRPS setup gives the best overall oracle/DAS score. These results do not support the conclusion that point observations are uninformative for nowcasting, but they show that local observational skill and spatially coherent radar-field skill are distinct targets. The practical implication is that sparse observations can provide useful local constraints, but their benefit for radar-like fields depends on the training loss, uncertainty representation, and how observation support is encoded in the model.

Read & Discuss → View Source →

20.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2602.09379

LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis

Authors:

Shihao Xu↗Tiancheng Zhou↗Jiatong Ma↗Yanli Ding↗Yiming Yan↗Ming Xiao↗Guoyi Li↗Haiyang Geng↗Yunyun Han↗Jianhua Chen↗Yafeng Deng↗

Mental disorders are highly prevalent worldwide, but the shortage of psychiatrists and the inherent subjectivity of interview-based diagnosis create substantial barriers to timely and consistent mental-health assessment. Progress in AI-assisted psychiatric diagnosis is constrained by the absence of benchmarks that simultaneously provide realistic patient simulation, clinician-verified diagnostic labels, and support for dynamic multi-turn consultation. We present LingxiDiagBench, a large-scale multi-agent benchmark that evaluates LLMs on both static diagnostic inference and dynamic multi-turn psychiatric consultation in Chinese. At its core is LingxiDiag-16K, a dataset of 16,000 EMR-aligned synthetic consultation dialogues designed to reproduce real clinical demographic and diagnostic distributions across 12 ICD-10 psychiatric categories. Through extensive experiments across state-of-the-art LLMs, we establish key findings: (1) although LLMs achieve high accuracy on binary depression–anxiety classification (up to 92.3%), performance deteriorates substantially for depression–anxiety comorbidity recognition (43.0%) and 12-way differential diagnosis (28.5%); (2) dynamic consultation often underperforms static evaluation, indicating that ineffective information-gathering strategies significantly impair downstream diagnostic reasoning; (3) consultation quality assessed by LLM-as-a-Judge shows only moderate correlation with diagnostic accuracy, suggesting that well-structured questioning alone does not ensure correct diagnostic decisions. We release LingxiDiag-16K and the full evaluation framework to support reproducible research at https://github.com/Lingxi-mental-health/LingxiDiagBench.

Read & Discuss → View Source →

21.

medRxiv (Medicine) 2026-06-15 DOI: HASH:724a8bbb90fcb0d91059c9fdd5d5ed55

Cost-Performance Evaluation of Large Language Models for Aspect-Based Sentiment Analysis of HCAHPS Patient Comments: A Validation Study

Authors:

Nawab↗Ramsey↗Asfandiyar↗Atreya↗Hijjawi↗Rokkam↗Ghayur↗Rajesh↗Yousuf↗Shah↗Z. A↗Misra↗…

Background: Hospital Consumer Assessment of Healthcare Providers and Systems (HCAHPS) free-text comments contain actionable feedback, but timely, scalable, and affordable sentiment analysis remains challenging for health systems that rely on third-party vendors. Objectives: To evaluate cost-performance tradeoffs between a cost-optimized and a flagship large language model (LLM) for aspect-based sentiment analysis of HCAHPS comments, using human inter-rater agreement as a reproducibility benchmark. Methods: We analyzed 512 free-text HCAHPS comments collected from two community hospitals in calendar year 2023. Six trained reviewers (medical students, recent medical graduates, and practicing internists) independently assigned positive, negative, or neutral labels to each comment-aspect pair; the majority label among three reviewers formed the consensus reference standard. Two OpenAI models - GPT-5-nano (cost-optimized) and GPT-5 (flagship) - were prompted in a zero-shot setting via the OpenAI API. We calculated pairwise Cohen's {kappa} to establish a human inter-rater baseline, then compared each model's labels to the consensus using Cohen's {kappa}, accuracy, weighted F1, and per-call cost and latency. Results: Mean human inter-rater agreement was {kappa} = 0.79 (substantial). Both LLMs exceeded this baseline (cost-optimized {kappa} = 0.85; flagship {kappa} = 0.85) with nearly identical accuracy (0.92) and weighted F1 (0.93 vs. 0.93). Performance was strong on positive (F1 ~ 0.97) and negative (F1 ~ 0.90) classes but poor on the underrepresented neutral class (F1

Read & Discuss → View Source →

22.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2505.20076

ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior

Authors:

Florian Eichin↗Yupei Du↗Philipp Mondorf↗Maria Matveev↗Barbara Plank↗Michael A. Hedderich↗

arXiv:2505.20076v4 Announce Type: replace Abstract: Post-hoc interpretability methods typically attribute a model's behavior to its components, data, or training trajectory in isolation, and are often tied to a particular level of granularity along the local-to-global spectrum. This leads to explanations that lack a unified view and may miss key interactions. We present ExPLAIND, a theoretically grounded, unified framework that integrates model components, data, and training trajectory while supporting explanations across granularities. We generalize recent work on gradient path kernels, reformulating models trained by AdamW as kernel machines. From the resulting kernel feature maps, we derive novel parameter-wise and step-wise influence scores. We empirically validate the resulting decomposition of model behavior in several settings and apply ExPLAIND to two case studies. Our findings on a Transformer exhibiting Grokking support previously proposed learning phases, while refining the final phase as one in which outer layers align around a representation pipeline learned after memorization. For EuroLLM pretraining, ExPLAIND reveals a two-phase dynamic, with the first characterized by outer-layer MLP learning and the second by increased relative influence of intermediate attention layers. These results establish ExPLAIND as a unified framework for interpreting model behavior and training dynamics.

Read & Discuss → View Source →

23.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2601.22184

Tacit Coordination of Large Language Models

Authors:

Ido Aharon↗Emanuele La Malfa↗Michael Wooldridge↗Sarit Kraus↗

arXiv:2601.22184v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in multi-agent settings that require coordination without communication, from human-AI interaction to safety-critical scenarios. Humans often overcome the absence of communication through focal points: salient solutions that naturally stand out to all participants. We present the first large-scale evaluation of how, when, and why focal points emerge in LLMs, comparing their behaviour with humans across cooperative and competitive games, including realistic search and rescue scenarios, demonstrating when focal points enable effective coordination. Across more than 20 open- and closed-source models, we find that LLMs exhibit a remarkable ability to coordinate without communication, often matching or outperforming humans. However, the same models consistently fail in tasks requiring numerical common sense or culturally nuanced notions of salience. We additionally evaluate simple learning-free strategies that substantially improve coordination both among LLMs and between humans and LLMs. Our results reveal striking coordination capabilities, as well as social limitations in modern LLMs, and offer new insight into the latent notions of salience encoded within them. Our findings caution against assuming that LLMs share humans' cultural and perceptual substrate when deployed in coordination settings.

Read & Discuss → View Source →

24.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.05878

TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning

Authors:

Etienne Le Naour↗Tahar Nabil↗Adrien Petralia↗

arXiv:2606.05878v2 Announce Type: replace Abstract: Foundation models mark a profound paradigm shift in time series modeling, with task-specific models being superseded by general-purpose zero-shot models. Yet, current approaches primarily focus on forecasting, while real-world time series are often irregularly and partially observed, requiring models that can jointly forecast, impute missing values, and handle degraded sampling conditions. To address these challenges, we introduce TS-ICL, a novel probabilistic In-Context Learning encoder–regressor Transformer that unifies forecasting and imputation. TS-ICL formulates time series tasks as timestamp-aligned regression and naturally incorporates covariates by training on synthetic dependency structures generated from a novel causal data prior. Empirically, TS-ICL achieves a new state-of-the-art in imputation, while remaining competitive with leading forecasting foundation models across both univariate and covariate-aware benchmarks. It shows particularly strong performance in forecasting with partially observed look-back windows.

Read & Discuss → View Source →

25.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19475

Diffusion Language Models: An Experimental Analysis

Authors:

Thomas Bertolani↗Davide Bucciarelli↗Leonardo Zini↗Marcella Cornia↗Lorenzo Baraldi↗

Large Language Models (LLMs) have revolutionized language modeling through autoregressive generation, enabling strong performance across a wide range of tasks. Recently, Diffusion Language Models (DLMs) have emerged as an alternative paradigm that generates text through iterative denoising rather than next-token prediction, allowing parallel refinement of entire sequences. While numerous diffusion-based architectures have been proposed, differences in evaluation protocols, datasets, inference budgets, and generation hyperparameters make it difficult to compare their capabilities and understand the trade-offs they offer. In this work, we present a systematic experimental analysis of modern DLMs. Specifically, we evaluate eight state-of-the-art DLMs across eight benchmarks spanning reasoning, coding, translation, knowledge, and structured problem solving, while explicitly considering both generation quality and computational efficiency. Beyond downstream evaluation, we analyze the impact of key inference-time factors, including denoising steps, context length, block size, and parallel unmasking strategies, and complement large-scale experiments with controlled comparisons of smaller models trained under identical conditions. Our analysis highlights the strengths and limitations of diffusion-based language modeling across different tasks, architectures, and inference budgets. We show that the behavior of DLMs is strongly influenced by generation-time design choices, leading to distinct trade-offs between performance and computational efficiency. Overall, our study provides practical insights into the capabilities and deployment characteristics of contemporary DLMs.

Read & Discuss → View Source →