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.

01.
arXiv (CS.AI) 2026-06-19

AI4SE and SE4AI Exploration: A Decade Looking Back and Forward

arXiv:2606.19630v1 Announce Type: new Abstract: The March 2020 INCOSE INSIGHT special issue on AI and Systems Engineering (SE) became the most downloaded issue in the publication's history and launched a research community that now draws over 250 registrants to its annual workshop. In this article, we trace the progress in AI and SE across three phases (labeled here foundational, applied, and LLM inflection) based on the authors' reading of the field's core papers, and describe our opinions of where the community has converged and where critical gaps remain. Separately, a human-AI agreement literature review leveraging both human expertise and six AI models was performed to assess the relevance of 1,712 INCOSE INSIGHT articles and 889 SERC publications. The results identify five critical research gaps and offer guidance for practitioners navigating AI adoption, assurance, and workforce transformation in SE. We share the agreement data and the AI4SE/SE4AI Explorer web application so readers can compare their own relevance judgments with the human and AI raters.

02.
bioRxiv (Bioinfo) 2026-06-18

Bioinf-Farma: supervised integration of epitope prediction and recombinant protein developability for automated vaccine candidate prioritization

Vaccine antigen discovery requires prioritizing protein candidates according to both immunogenic potential and recombinant expression feasibility. These properties are typically evaluated using separate computational tools, requiring researchers to integrate heterogeneous outputs through ad hoc workflows. Here, we present BIOINF-farma, a modular platform integrating epitope prediction and developability assessment for rational antigen selection within a unified environment. Candidates can be submitted as amino acid sequences or three-dimensional structures. When experimental structures are unavailable, BIOINF-farma automatically searches for models in AlphaFold DB or performs structure prediction using Boltz-2, ensuring a standardized structural representation for downstream analyses. Antigenicity is quantified by combining structure-based conformational epitope signals (MLCE/REBELOT-BEPPE) and sequence-based linear epitope propensity scores (BepiPred 3.0) into a protein-level Antigenicity Score, with a classification threshold optimized on a manually curated validation dataset. Developability is evaluated through two supervised Random Forest meta-learners that integrate three solubility predictors (DeepSoluE, SoluProt, Protein-Sol) and three thermal stability predictors (TemStaPro, ProLaTherm, BertThermo), whose outputs are combined into an Expression Efficiency Score (EES). By integrating complementary predictive signals, the meta-learning framework achieves greater accuracy and robustness than individual predictors while maintaining performance across a broad range of sequence identities. The Antigenicity Score effectively discriminates antigenic from non-antigenic proteins with a large effect size, whereas EES successfully distinguishes soluble from insoluble outcomes on an independent panel of recombinant proteins expressed in Escherichia coli. BIOINF-farma jointly assesses antigenicity and expression feasibility within a single framework. Its modular architecture facilitates the incorporation of future predictive methods, while its web-based interface makes the full pipeline accessible to users without programming expertise, supporting rapid candidate triage in vaccine research and emerging pathogen responses.

03.
arXiv (CS.AI) 2026-06-12

Graph Reduction in Multirelational Networks: A Spreading-Oriented Reduction Benchmark

arXiv:2606.12581v1 Announce Type: cross Abstract: Real-world networks are inherently incomplete, noisy, and dynamically evolving, making it difficult to capture all actors and their relationships. Their scale often renders direct analysis computationally demanding. While influence maximisation (IM) has been widely studied, the role of graph reduction as a preprocessing step, and its impact on IM accuracy, remains underexplored. In this work, we introduce the Spreading-Oriented Reduction Benchmark (SORB), an open-source, standardised framework for systematically evaluating IM models across diverse task settings. SORB provides an extensible pipeline operating on a representative collection of real-world networks, including single- and multilayer structures, and accounts for graph reduction directly into the evaluation process. This design shifts the focus from analysing IM algorithms in isolation to quantifying how graph reduction alters predictive performance. Using SORB, we study the effects of sparsification and coarsening across multiple IM scenarios. Our results show that the impact of reduction is strongly dependent on both the network type (single-layer vs. multirelational) and the downstream task ($Gain@k$ vs. $\mathrm{AUC}_{\mathrm{cutoff}}$): sparsification preserves seed set quality on single-layer networks, whereas flattened multilayer networks exhibit systematic ranking degradation regardless of reduction strategy. These findings highlight the importance of reduction-aware, multi-task evaluation when studying spreading processes in complex networks.

04.
arXiv (CS.CL) 2026-06-11

Language Shapes Mental Health Evaluations in Large Language Models

Multilingual large language models (LLMs) are increasingly used in socially sensitive mental health contexts, including support chatbots, screening, and content moderation. This raises a reliability question: do semantically equivalent mental health inputs elicit comparable evaluations across languages, or systematic shifts consistent with language-associated social and cultural contexts? We examine this question in an English-Chinese setting with GPT-4o and Qwen3-32B using a two-level framework: construct-level evaluative orientation, measured by psychometric stigma instruments, and decision-level behavior, measured by binary stigma detection and four-class depression severity classification. Across instruments and models, Chinese prompts elicit higher stigma-related scores than English prompts. At the decision level, Chinese prompts reduce sensitivity to stigmatizing content and produce more conservative depression severity judgments, leading to more under-estimation errors. These findings show that prompt language can shift both evaluative orientation and downstream behavior in LLM-based mental health evaluation. They highlight the need to evaluate multilingual LLMs not only for aggregate performance, but also for whether they apply comparable evaluative standards across languages in socially sensitive domains.

05.
arXiv (CS.AI) 2026-06-16

Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains

Authors:

arXiv:2606.15841v1 Announce Type: new Abstract: Large language model (LLM) systems increasingly use uncertainty signals to allocate limited computation across verification, test-time scaling, tool execution, and other selective-compute decisions. Such policies rely on a global signal comparability assumption: equal scores should carry comparable decision value across inputs. Using budgeted verification as a controlled diagnostic setting, we identify a failure mode of this assumption: uncertainty quality is heteroskedastic across cost strata, with some regions exhibiting near-random discriminability despite concentrating many errors. Under an explicit local model, we characterize the resulting distortion of global allocation and show that its upper bound scales with cross-stratum signal-quality dispersion. We separate weak signals, optimization instability, and structural heterogeneity through a controlled intervention hierarchy: Threshold, MP-Adapt, MP-Strat, and a deliberately simple cost-stratified thresholding intervention (CST). Across MBPP and MATH using Qwen3-8B, LLaMA3-8B, and GPT-4o-mini, global online adaptation yields inconsistent gains over static thresholding; MP-Strat partially recovers performance, while CST improves hit rate by up to 17 percentage points in strongly heterogeneous settings without gradient updates. These results identify structural heterogeneity, rather than optimizer weakness alone, as the primary bottleneck in the observed settings. More broadly, misaligned feedback structure cannot always be repaired by stronger optimization.

06.
medRxiv (Medicine) 2026-06-24

Automated Text Message Outreach to Increase Diabetes Screening: A Pragmatic Randomized Trial

Background Despite evidence that early intervention can prevent or delay progression to type 2 diabetes, more than 80% of individuals with prediabetes in the United States remain undiagnosed, underscoring the need for scalable strategies to increase uptake. In this study, we evaluated whether a single text message could increase completion of HbA1c-based diabetes screening in routine clinical practice. Methods We conducted a pragmatic randomized controlled trial within Duke University Health System (DUHS). Patients aged 35 years or older who met American Diabetes Association 2022 screening criteria, had no previous diagnosis of diabetes, had not undergone HbA1c testing within the preceding 3 years, and had opted to receive text messages from DUHS were randomly assigned to receive either a single text message encouraging guideline-based diabetes screening and discussion with a primary care provider (intervention group; n=55,494) or usual care (control group; n=5,748). The primary outcome was HbA1c test completion within 24 weeks following message delivery (or no message for controls), analyzed using a Cox proportional hazards model stratified by wave. Secondary outcomes included piecewise hazard ratios for early (weeks 1-4), mid (weeks 5-12), and late (weeks 13-24) intervals and the between-group difference in cumulative testing rate. Findings Text message outreach significantly increased HbA1c test completion over 24 weeks (HR, 1.18 [95% CI, 1.07-1.03]) with the strongest effect in the first four weeks (HR, 1.48 [95% CI, 1.18-1.86]). By the end of the 24-week observation period, cumulative testing reached 9.14% in the messaged group vs 7.83% in controls (between-group difference, 1.31% [95% CI, 0.59-2.07]), corresponding to one additional HbA1c test per 76 messages delivered ($0.51 in messaging costs per additional HbA1c test performed). Rates of prediabetes and diabetes among those screened were similar between groups, indicating no selection bias of higher-risk patients. One additional dysglycemia case was identified per 213 messages sent ($1.43 per case detected).

07.
medRxiv (Medicine) 2026-06-23

Multivariate Echocardiographic Phenotyping of Hypertensive Heart Failure Using Unsupervised Machine Learning: A Pilot Study

Background Heart failure in hypertensive patients is heterogeneous and poorly captured by traditional left ventricular ejection fraction (LVEF) based classification. Multivariate echocardiographic data combined with unsupervised machine learning may provide a more precise phenotypic characterization. This pilot study evaluated the feasibility of unsupervised clustering of routine transthoracic echocardiographic data to identify phenotypic subgroups of hypertensive heart failure. Methods This retrospective pilot study analyzed transthoracic echocardiography reports from hypertensive patients with clinical heart failure. After data cleaning and exclusion of incomplete records, 102 patients with 11 echocardiographic variables were included. Variables describing left ventricular geometry, systolic function, and diastolic performance were standardized and subjected to K-means clustering. Optimal cluster number was determined using the elbow method and silhouette analysis. Cluster characteristics were assessed using descriptive statistics and Kruskal Wallis testing. Concordance with LVEF based heart failure categories was evaluated. Results Three distinct echocardiographic phenotypes were identified. Cluster 0 (n = 50) demonstrated preserved LVEF with concentric remodeling, consistent with heart failure with preserved ejection fraction (HFpEF) phenotype. Cluster 1 (n = 37) showed marked ventricular dilation and reduced systolic function, consistent with heart failure with reduced ejection fraction (HFrEF). Cluster 2 (n = 15) exhibited concentric hypertrophy with intermediate LVEF, consistent with heart failure with mildly reduced ejection fraction (HFmrEF) like phenotype. All echocardiographic variables differed significantly across clusters (p < 0.001). While Cluster 0 showed strong concordance with HFpEF (96%), Clusters 1 and 2 demonstrated substantial overlap across LVEF categories, indicating partial discordance between structural phenotypes and LVEF based classification. Conclusion Application of unsupervised machine learning to routine echocardiographic data identifies distinct heart failure phenotypes in hypertensive patients. These phenotypes demonstrate significant structural heterogeneity beyond LVEF based classification, supporting the utility of data-driven approaches for refined cardiac phenotyping. This pilot study provides a foundation for larger prospective studies.

08.
medRxiv (Medicine) 2026-06-19

Rumination as a cognitive vulnerability factor in perinatal bereavement: evidence from the CARING study

Purpose. Perinatal loss is associated with a high risk of persistent psychological distress, including prolonged grief, depression, anxiety, and post-traumatic stress symptoms. Cognitive processes such as rumination may play a crucial role in maintaining and amplifying distress following loss, yet their specific contribution in perinatal bereavement remains underexplored. Methods. The CARING (Cognitive Analysis and Rumination INvestigation in perinatal Grief) study employed a cross-sectional design involving 298 parents who experienced perinatal loss within the previous five years. Participants completed an anonymous online survey including measures of depressive rumination (Ruminative Response Scale, RRS), angry rumination (Anger Rumination Scale, ARS), perinatal grief (Perinatal Grief Scale, PGS), general psychopathology (SCL-90), and post-traumatic stress symptoms (NSESSS). Non-parametric analyses were conducted to examine associations between rumination patterns and psychological outcomes. Results. Higher levels of rumination were significantly associated with greater perinatal grief, depressive and anxiety symptoms, and post-traumatic stress. Depressive rumination showed consistently stronger associations with all outcomes compared to angry rumination. Participants presenting both depressive and angry rumination exhibited the highest levels of grief intensity, psychological distress, and PTSD symptoms, suggesting a graded relationship between rumination patterns and severity of distress. Rumination levels were not significantly associated with gestational age at loss or with having received psychological support. Conclusions. Rumination, particularly in its depressive form, appears to function as a transdiagnostic cognitive vulnerability factor in perinatal bereavement. These findings highlight rumination as a potential target for early screening and tailored psychological interventions aimed at reducing long-term distress following perinatal loss.

09.
arXiv (CS.AI) 2026-06-16

Looking Is Not Picking: An Attention-Segment Account of Tool-Selection Failures in LLM Agents

Authors:

arXiv:2606.16364v1 Announce Type: new Abstract: LLM agents mis-call tools, and the natural guess is that the model failed to see the right tool in a crowded harness. We show the opposite through a lens concurrent work sets aside – the model's attention to labeled tool-definition segments. On real BFCL failures, by per-candidate attention argmax the model attends most to the correct tool 80% of the time (vs. 21% chance), and the gold is the under-attended segment on only 10%: it looks at the right tool and still picks wrong. This directly refutes the intuitive "crowded-harness / lost-in-the-middle" explanation: the failure is at the decision readout, not the harness, and we pin it there three ways. (1) Input vs. readout: repairing the prompt (reordering or duplicating the gold tool) recovers

10.
arXiv (CS.AI) 2026-06-16

No One-Size-Fits-All Neurons: Task-based Neurons for Artificial Neural Networks

arXiv:2405.02369v2 Announce Type: replace-cross Abstract: In the past decade, many successful networks are on novel architectures, which almost exclusively use the same type of neurons. Recently, more and more deep learning studies have been inspired by the idea of NeuroAI and the neuronal diversity observed in human brains, leading to the proposal of novel artificial neuron designs. Designing well-performing neurons represents a new dimension relative to designing well-performing neural architectures. Biologically, the brain does not rely on a single type of neuron that universally functions in all aspects. Instead, in our brain, neurons are often task-based. In this study, we address the following question: since the human brain is a task-based neuron user, can the artificial network design go from the task-based architecture design to the task-based neuron design? Since methodologically there are no one-size-fits-all neurons, given the same structure, task-based neurons can enhance the feature representation ability relative to the existing universal neurons due to the intrinsic inductive bias for the task. Specifically, we propose a two-step framework for prototyping task-based neurons. As the initial step, we evaluate the proposed framework using polynomials as base functions. Empirically, systematic experimental results on synthetic data, classic benchmarks, and real-world applications show that the proposed task-based neuron design is not only feasible but also delivers competitive performance over other state-of-the-art models.

11.
arXiv (CS.CL) 2026-06-11

AI Coding Agents Can Reproduce Social Science Findings

Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic evaluation across social sciences remains limited. Existing evaluation benchmarks are insufficient, either small or conflate agent performance with problems in the reproduction materials themselves, such as code that fails to execute correctly. Here we introduce SocSci-Repro-Bench, a benchmark of 221 tasks spanning four disciplines and 13 substantive domains, constructed from studies whose results are either fully reproducible with available materials or demonstrably non-reproducible due to missing data, allowing us to isolate agents' reproduction capacity. Evaluating two frontier coding agents, Claude Code and Codex, we find that both can reproduce a large share of social science findings, with Claude Code substantially outperforming Codex. These reproduction rates considerably exceed those previously reported for general-purpose LLM-based agents on comparable reproducibility benchmarks. Both agents also perform strongly on a reasoning task requiring identification of underlying research questions, and additional analyses suggest that results are not primarily driven by memorization. Providing the original paper PDF alongside replication materials modestly improves performance but introduces bias on tasks where reproduction is impossible. We also show that agents can be nudged toward confirmatory specification search through subtle prompt framing. Together, these findings suggest that at least some frontier coding agents can serve as reliable executors of computational workflows while underscoring the need for careful benchmarking and prompt design as AI systems assume larger roles in scientific production.

12.
arXiv (CS.CL) 2026-06-12

GENIE: A Fine-Grained Measure for Novelty

Large Language Models have consistently demonstrated a lack of creativity and diversity across tasks. Prior work has focused on addressing whether models are capable of generating creative outputs. Here, we aim to consider novelty and investigate what makes model-generated content novel or not novel in a task-specific manner. We propose a fine-grained evaluation metric GENIE to measure the novelty of responses along task-specific features with respect to a population of responses. We show that unlike GENIE, holistic metrics struggle to capture the high-dimensionality of novelty and do not provide insight on which properties they target. Finally, we use GENIE to measure the effectiveness of mitigation methods that address creativity to better understand where these methods can improve novelty.

13.
arXiv (CS.AI) 2026-06-25

The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems

arXiv:2606.26057v1 Announce Type: new Abstract: AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems. The dominant approach places controls inside the agent's own runtime: system prompts, output filters, and guardrail libraries. Any control in the agent's address space is reachable by inputs that influence it; this generalizes to any AI system with sufficient reach into its own runtime, a class we term escapable AI systems. We identify four properties that an authorization mechanism must satisfy for architectural control rather than for cooperative requests: process separation, pre-action enforcement on a structurally only path, fail-closed at both the request and system levels, and externalized signed evidence verifiable outside the controlled system's trust boundary. We position this layer as execution-time AI alignment, complementing training-time alignment (RLHF, Constitutional AI) and inference-time alignment. We present the Unfireable Safety Kernel, a Rust reference implementation realizing all four. Its fail-closed invariant is machine-checked at two levels: an SMT theorem (Z3) and an exhaustive bounded-model-checking proof of the production decision function (Kani, 4/4 harnesses). A Python-to-Rust migration was gated on byte-equivalence (1000/1000 fixtures; 17/17 adversarial classes). We evaluate the kernel governing a live, escapable AI system, a deterministic, self-improving world model, against an escape-seeking adversary driving its real self-modification seam: across 1,000 self-modifications, all 704 attempts on the safety-critical core are refused, with no escape; a further 300, under the operator kill switch, are also refused. A separate campaign of 6,240 authorization round-trips had no successful bypass. Against 3 contemporary systems claiming the agent control plane, the agent invokes control; here, it lacks that choice.

14.
arXiv (CS.AI) 2026-06-18

EMORSION: Examining the Impact of Audio Parameters on Emotional Responses and Immersion in Film

arXiv:2606.18266v1 Announce Type: cross Abstract: EMORSION is an exploratory proof-of-concept study examining how film audio design shapes audience emotion and immersion in acinema setting. Four film scenes were selected across the horror (2) and drama (2) genres, balanced between mainstream and independent productions. For each scene, multiple alternative audio mixes were created by systematically manipulating three core aspects of audio design, frequency (pitch), dynamics (loudness), and directionality (spatial placement). Three audience groups viewed the scenes, with each group exposed to one manipulated mix alongside a control mix for each scene. Audience responses were assessed through a triangulated multimodal framework combining self-reported emotion and immersion via a questionnaire, physiological measures including heart rate monitoring, and video-based motion tracking. The protocol successfully captured measurable, interpretable differences across audio conditions, indicating that even subtle changes in audio design can shape emotional perception and immersion. Unconventional mixes tended to produce greater variability in audience interpretation, while conventional immersive mixes were associated with stronger cross-audience agreement. These findings establish the feasibility of the EMORSION protocol and motivate larger-scale studies to characterise the role of specific audio parameters in shaping audience experience.

15.
arXiv (CS.AI) 2026-06-12

An Explainable AI Assistant for Introductory Programming Education: Improving Feedback Reliability with Instructor-AI Collaboration

arXiv:2606.12425v1 Announce Type: cross Abstract: Active learning is widely recognized as an effective approach for improving learning outcomes in introductory programming courses. However, insufficient instructional support often limits students' access to timely, personalized feedback, which is crucial for mastering foundational programming concepts. Although recent advances in AI, particularly large language models, offer scalable opportunities for feedback, concerns about explainability and reliability remain. In this paper, we present an AI-driven classroom assistant that leverages an explainable AI model to analyze student code, map logical errors to instructor-identified misconceptions, and deliver instructor-authored feedback, thereby grounding reliability in instructor-defined pedagogical knowledge. To evaluate the effectiveness of our framework, we conducted an expert evaluation to examine its alignment with instructor-verified feedback and deployed the system in a classroom setting to assess students' perceptions of its usability. Results indicate that the assistant can provide accurate, instructor-verified feedback to students while fostering a positive experience.

16.
arXiv (CS.CV) 2026-06-15

Representation Forcing for Bottleneck-Free Unified Multimodal Models

Unified multimodal models (UMMs) aim to handle perception and generation in a single model. Yet existing UMMs still rely on a frozen, separately pretrained VAE for image generation, imposing a structural bottleneck. Naively removing it introduces a quality gap, as the model must learn both high-level structure and low-level details from raw pixels. In this paper, we propose Representation Forcing (RF), a technique that closes this gap by making representation prediction a native capability of the model. Concretely, RF forces the decoder to autoregressively predict visual representations as intermediate tokens before pixels; these tokens then stay in context to guide pixel diffusion within the same backbone. By turning representations from perception outputs into generation targets, RF eliminates the need for any external generative latent space. We find that RF benefits both understanding and generation. On image generation, our pixel-space model with RF matches state-of-the-art VAE-based unified models. On image understanding, pixel-space RF generally outperforms its VAE-based variant. Together, these results offer an effective step toward end-to-end, bottleneck-free UMMs.

17.
arXiv (CS.CV) 2026-06-18

Bidirectional Cross-Attention Fusion of High-Resolution RGB and Low-Resolution Hyperspectral Inputs for Multimodal Semantic Segmentation

Multimodal semantic segmentation with heterogeneous sensors must reconcile complementary information across modalities that differ in spatial resolution and channel dimensionality. In particular, high-resolution RGB imaging provides detailed spatial structure but often fails to distinguish visually similar materials, whereas hyperspectral imaging (HSI) provides discriminative spectral signatures but at lower spatial resolution. We present Bidirectional Cross-Attention Fusion (BCAF), which aligns high-resolution RGB with low-resolution HSI at their native grids via localized, bidirectional cross-attention, avoiding pre-upsampling or early spectral collapse. BCAF uses two independent backbones: a standard Swin Transformer for RGB and an HSI-adapted Swin backbone that preserves spectral structure through 3D tokenization with spectral self-attention. Although our evaluation targets RGB-HSI fusion, BCAF is modality-agnostic and applies to co-registered RGB with lower-resolution, high-channel auxiliary sensors. On the benchmark SpectralWaste dataset, BCAF delivers strong performance, achieving 75.4% at 55 images/s. We further evaluate a novel industrial dataset: K3I-Cycling (first RGB subset already released on Fordatis). On this dataset, BCAF reaches 62.3% mIoU for material segmentation (paper, metal, plastic, etc.) and 66.2% mIoU for plastic-type segmentation (PET, PP, HDPE, LDPE, PS, etc.). These results show that preserving native-grid spatial detail and spectral structure improves multimodal segmentation under real-time constraints. Code and model checkpoints are publicly available at https://github.com/jonasvilhofunk/BCAF_2026.

18.
arXiv (quant-ph) 2026-06-19

Mapping molecular polariton transport via pump-probe microscopy

arXiv:2504.15501v4 Announce Type: replace Abstract: We demonstrate how the transport properties of molecular polaritons in optical cavities can be extracted from a microscopic modeling of pump-probe spectroscopy. Our approach combines a mean-field treatment of the light-matter Hamiltonian with a perturbative expansion of both light and matter components, along with spatial coarse-graining. This approach extends semiclassical cavity spectroscopy to multimode light-matter interactions, providing full access to spatially resolved transient spectra. By simulating a microscopy experiment with counter-propagating pump and probe pulses, we compute the differential transmission and show how molecular dephasing and persistent dark exciton populations drive sub-group-velocity transport of the root-mean-square displacement. We analyze transport across the polariton dispersion, showing how velocity renormalization correlates with excitonic weight, consistent with experimental observations, and further its dependence on the rate of molecular dephasing. Our results highlight the need to consider measured spectroscopic observables when characterizing transport in polaritonic systems.

19.
arXiv (CS.CV) 2026-06-12

DIMOS: Disentangling Instance-level Moving Object Segmentation

Moving instance segmentation (MIS) attracts increasing attention due to its broad applications in traffic surveillance, autonomous driving, and animal tracking. Event cameras record asynchronous brightness changes, providing high temporal resolution and dynamic range, which makes them highly sensitive to motion information. By fusing event and image features, motion cues from events can complement spatial details from images, enhancing the performance of MIS. However, current multimodal MIS methods still struggle to segment small moving instances, as event cameras often yield sparse features under limited resolution. Moreover, event features entangle appearance attributes with motion cues, which further restricts effective cross-modal fusion. To address these challenges, we first propose a dual-disentangling feature extraction framework that separates and extracts appearance and motion information within both image and event modalities, thereby improving feature density. Subsequently, a multi-granularity cross-modal alignment is introduced to align distributionally and semantically consistent features across modalities, enabling more effective fusion with rich spatial and temporal details. The experiment results demonstrate that our method achieves state-of-the-art performance in multimodal MIS, especially for small instances under challenging conditions such as fast motion and low-light settings.

20.
arXiv (CS.AI) 2026-06-25

GCT-MARL: Graph-Based Contrastive Transfer for Sample-Efficient Cooperative Multi-Agent Reinforcement Learning

arXiv:2606.25073v1 Announce Type: cross Abstract: In cooperative multi-agent reinforcement learning (MARL), from a deployment perspective, it is challenging and expensive to train agents from scratch for each new environment or task. In this work, we propose GCT-MARL, a transfer learning framework that builds on the multi-view graph contrastive backbone of MAIL and augments it with a per-view, adaptively weighted alignment loss and a two-phase training protocol specifically designed for transfer across populations of varying sizes and compositions. We empirically demonstrate that the proposed framework markedly accelerates convergence on the target task relative to from-scratch training, in both homogeneous (within-faction, varying N) and heterogeneous (cross-faction and mixed unit-type) transfer scenarios. Furthermore, we show that the framework naturally supports continual learning by sequentially chaining the two-phase transfer protocol across a series of related tasks. Overall, this work provides a unified approach to mitigating key limitations in current MARL transfer methods with new insights at both methodological and empirical levels.

21.
arXiv (CS.CL) 2026-06-12

Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior

Anticipating LLM behavioral tendencies from low-cost psychometric probes is critical for safe deployment, but only if self-reports (SR) reliably predict behavior. Recent work documented substantial SR-behavior dissociation in LLMs, but relied on broad personality traits (Big 5) that predict specific behaviors weakly, even in humans. Furthermore, the isolation of conversational sessions combined with weak context matching left open whether LLMs truly lack coherence or whether the conditions needed to detect such coherence were not met. We contrast Big 5 with the Theory of Planned Behavior (TPB), which measures intention targeted to a specific behavior and predicts human behavior substantially better than broad traits. We run experiments across four behavioral tasks and 11 frontier LLMs, while also varying session context and identity induction. We find that SR-behavior coherence exists but is selective. 1) Within a shared conversation, the Theory of Planned Behavior reaches human-level coherence; Big 5 does not. 2) Across separate conversations, coherence survives only for behaviors anchored outside the immediate prompt, such as implicit bias shaped by training, and collapses when behavior is strongly primed by context, as with sycophancy. 3) Persona prompting makes self-reports more consistent across conversations, but does not bring behavior into alignment. These findings suggest that coarse personality frameworks, such as Big 5 may not be the best tools for testing deployment behavior. More task- and behavior-specific instruments are needed, and even these must be evaluated across tasks and contexts.

22.
arXiv (CS.AI) 2026-06-19

Advancing DialNav through Automatic Embodied Dialog Augmentation

arXiv:2606.19948v1 Announce Type: new Abstract: For embodied agents capable of physical interaction, the capability to create and understand dialog is crucial to ensure both safety and effectiveness. While DialNav[han2025dialnav] provides a framework for holistic evaluation of the dialog–execution loop in photorealistic indoor navigation, its performance remains limited by a critical scarcity of training data (2K episodes). To address this, we propose an automatic generation pipeline, and construct the RAINbow dataset, a large-scale training dataset with 238K episodes for DialNav. Our pipeline converts existing VLN datasets into multi-turn dialog and creates cost-efficient and high-quality dataset. Then, we introduce two additional complementary advances to unlock the data's full potential: (1) Dual-Strategy Training, a navigation training scheme to align the navigation training with the dynamic dialog-navigation loop, and (2) a localization model that leverages VLN knowledge. By combining these complementary solutions, our model substantially outperforms the baseline in success rate on both Val Seen (58.24, +89\%) and Val Unseen (29.05, +100\%) splits, establishing a new state of the art.

23.
arXiv (CS.AI) 2026-06-24

FP8 is All You Need (Part 2): Efficient Ozaki-Bailey Style FFT Through Tensor-core Garner Reformulation and Kulisch Escape Route

arXiv:2606.23698v1 Announce Type: cross Abstract: NVIDIA's Blackwell Ultra (B300) cuts FP64 vector throughput to ~1.3 TFLOPS per GPU, roughly 30x below B200 and well below the level at which bandwidth-limited FP64 workloads stay memory-bound. The Ozaki Scheme II framework recovers FP64-equivalent throughput by routing dense matrix multiply through FP8 tensor cores with a mantissa-sliced Chinese-remainder reconstruction. A companion Part (1) paper covers dense GEMM, batched GEMV, stencils, and SpMV; this paper adds the fifth canonical primitive, the 3-D FFT. We present Ozaki-Bailey FFT, an emulated 3-D FFT via the Bailey six-step decomposition with both 1-D FFT GEMMs on FP8 tensor cores. Bailey's small inner factor k ~ sqrt(N) (k=32 for N=1024) puts the kernel in the regime k

24.
arXiv (CS.CV) 2026-06-24

Trimming the Long-Tail of Visual World Modeling Evaluation

Physical interactions follow a long-tailed distribution: a set of common and regular interactions dominates human experience and visual data, while a broad spectrum of rare and irregular interactions remains underrepresented. Although recent visual world models, including image and video generation models, achieve impressive realism on existing benchmarks, they primarily focus on simulating common physical interactions. This raises a central question: Do current visual world models internalize and generalize physical principles? In this work, we introduce Tailor-Bench, a benchmark that challenges world models to simulate irregular physical interactions. To enable systematic evaluation, we design three scenario modes that progressively challenge model reasoning: Regular scenarios reflect common tool-task pairs, Unconventional scenarios replace conventional tools with attribute-compatible substitutes to test affordance generalization, and Impossible scenarios introduce attribute-violating tools to probe constraint awareness. Additionally, we design two complementary settings under a unified evaluation protocol: predictive generation requires inferring outcomes without guidance, while descriptive generation specifies the target outcome for faithful realization. Our experimental results reveal a clear long-tail gap in physical world modeling: performance degrades from Regular to Unconventional and Impossible scenarios, indicating limited generalization beyond common interactions. Failure analysis further shows that models rely on superficial visual patterns: image models fail to realize correct state changes, while video models further suffer from temporal inconsistencies.

25.
arXiv (CS.CL) 2026-06-16

Benchmarking LLM Agents on Meta-Analysis Articles from Nature Portfolio

Meta-analysis is a demanding form of evidence synthesis that combines literature retrieval, PI/ECO-guided study selection, and statistical aggregation. Its structured, verifiable workflow makes it an ideal substrate for evaluating systematic scientific reasoning, yet existing benchmarks lack ground truth across the full retrieval-screening-synthesis pipeline. We introduce MetaSyn, a dataset of 442 expert-curated meta-analyses from Nature Portfolio journals. Each entry pairs a research question with PI/ECO criteria, a retrieval corpus of 140k PubMed articles, verified positive studies, hard negatives that are topically similar but PI/ECO-ineligible, and complete search strategies and date bounds. Benchmarking twelve pipeline configurations (nine RAG variants and a protocol-driven agent) reveals a critical screening bottleneck: despite a retrieval ceiling of 90.9% recall at K=200, no system recovers more than 52.7% of ground-truth included literature. Current LLMs fail to reliably separate eligible studies from PI/ECO-failing distractors in pools of comparable topical relevance. Stage-attributed metrics capture where systems succeed and fail; a single end-to-end score does not.