Recently, inference-time reasoning strategies have further improved the accuracy of large language models (LLMs), but their effectiveness on smaller models remains unclear. Based on the observation that conventional approaches often fail to improve performance in this context, we propose \textbf{C}ycle-\textbf{C}onsistency in \textbf{Q}uestion \textbf{A}nswering (CCQA), a novel reasoning method that can be effectively applied to SLMs. Inspired by cycle consistency, CCQA generates a question from each reasoning path and answer, evaluates each by its similarity to the original question, and then selects the candidate solution with the highest similarity score as the final response. Since conventional SLMs struggle to generate accurate questions from their own reasoning paths and answers, we employ a lightweight Flan-T5 model specialized for question generation to support this process efficiently. From the experimental results, it is verified that CCQA consistently outperforms existing state-of-the-art (SOTA) methods across eight models on mathematical and commonsense reasoning benchmarks. Furthermore, our method establishes a new practical baseline for efficient reasoning in SLMs. Source code can be found at https://github.com/scai-research/ccqa_official.

ABSTRACT The widespread adoption of ChatGPT has raised concerns about its misuse, highlighting the need for robust detection of AI-generated text. Current word-level detectors are vulnerable to paraphrasing or simple prompts (PSP), suffer from biases induced by ChatGPT's word-level patterns (CWP) and training data content, degrade on modified text, and often require large models or online LLM interaction. To tackle these issues, we introduce a novel task to detect both original and PSP-modified AI-generated texts, and propose a lightweight framework that classifies texts based on their internal structure, which remains invariant under word-level changes. We employ contrastive learning to mitigate embedding biases from autoregressive generation and incorporate a causal graph with counterfactual methods to isolate structural features from topic-related biases. Experiments on two curated datasets, including abstract comparisons and revised life FAQs, validate the effectiveness of our method.

A fundamental property of DNA is that the reverse complement (RC) of a sequence often carries identical biological meaning. However, state-of-the-art DNA language models frequently fail to capture this symmetry, producing inconsistent predictions for a sequence and its RC counterpart, which undermines their reliability. In this work, we introduce Reverse-Complement Consistency Regularization (RCCR), a simple and model-agnostic fine-tuning objective that directly penalizes the divergence between a model's prediction on a sequence and the aligned prediction on its reverse complement. We evaluate RCCR across three diverse backbones (Nucleotide Transformer, HyenaDNA, DNABERT -2) on a wide range of genomic tasks, including sequence classification, scalar regression, and profile prediction. Our experiments show that RCCR substantially improves RC robustness by dramatically reducing prediction flips and errors, all while maintaining or improving task accuracy compared to baselines such as RC data augmentation and test-time averaging. By integrating a key biological prior directly into the learning process, RCCR produces a single, intrinsically robust, and computationally efficient model fine-tuning recipe for diverse biology tasks. DNA language models (DNA LMs) (Zhou et al., 2024; Dalla-Torre et al., 2025; Nguyen et al., 2023; Ma et al., 2025) have become general-purpose backbones for genomic prediction and sequence design: after pretraining on raw genomes, a single backbone can be fine-tuned for diverse downstream tasks. Many of these tasks possess an explicit symmetry: labels are reverse-complement (RC) invariant at the sequence level (e.g., promoter classification), or RC equivariant at the profile level, where outputs must be aligned by a task-specific operator Π (e.g., bin-wise outputs should be flipped along the sequence length axis, and strand channels swapped when present). Y et standard fine-tuning pipelines neither encode RC symmetry nor evaluate it systematically, leaving models sensitive to input orientation.

High-dimensional imaging of neural activity, such as widefield calcium and functional ultrasound imaging, provide a rich source of information for understanding the relationship between brain activity and behavior. Accurately modeling neural dynamics in these modalities is crucial for understanding this relationship but is hindered by the high-dimensionality, complex spatiotemporal dependencies, and prevalent behaviorally irrelevant dynamics in these modalities. Existing dynamical models often employ preprocessing steps to obtain low-dimensional representations from neural image modalities. However, this process can discard behaviorally relevant information and miss spatiotemporal structure. We propose SBIND, a novel data-driven deep learning framework to model spatiotemporal dependencies in neural images and disentangle their behaviorally relevant dynamics from other neural dynamics. We validate SBIND on widefield imaging datasets, and show its extension to functional ultrasound imaging, a recent modality whose dynamical modeling has largely remained unexplored. We find that our model effectively identifies both local and long-range spatial dependencies across the brain while also dissociating behaviorally relevant neural dynamics. Doing so, SBIND outperforms existing models in neural-behavioral prediction. Overall, SBIND provides a versatile tool for investigating the neural mechanisms underlying behavior using imaging modalities.

Large language models (LLMs) are increasingly used for text-rich graph machine learning tasks such as node classification in high-impact domains like fraud detection and recommendation systems. Yet, despite a surge of interest, the field lacks a principled understanding of the capabilities of LLMs in their interaction with graph data. In this work, we conduct a large-scale, controlled evaluation across several key axes of variability to systematically assess the strengths and weaknesses of LLM-based graph reasoning methods in text-based applications. The axes include the LLM-graph interaction mode, comparing prompting, tool-use, and code generation; dataset domains, spanning citation, web-link, e-commerce, and social networks; structural regimes contrasting homophilic and heterophilic graphs; feature characteristics involving both short- and long-text node attributes; and model configurations with varying LLM sizes and reasoning capabilities. We further analyze dependencies by methodically truncating features, deleting edges, and removing labels to quantify reliance on input types. Our findings provide practical and actionable guidance. (1) LLMs as code generators achieve the strongest overall performance on graph data, with especially large gains on long-text or high-degree graphs where prompting quickly exceeds the token budget. (2) All interaction strategies remain effective on heterophilic graphs, challenging the assumption that LLM-based methods collapse under low homophily. (3) Code generation is able to flexibly adapt its reliance between structure, features, or labels to leverage the most informative input type. Together, these findings provide a comprehensive view of the strengths and limitations of current LLM-graph interaction modes and highlight key design principles for future approaches.

Generative adversarial networks (GANs) and diffusion models have dramatically advanced deepfake technology, and its threats to digital security, media integrity, and public trust have increased rapidly. This research explored zero-shot deepfake detection, an emerging method even when the models have never seen a particular deepfake variation. In this work, we studied self-supervised learning, transformer-based zero-shot classifier, generative model fingerprinting, and meta-learning techniques that better adapt to the ever-evolving deepfake threat. In addition, we suggested AI-driven prevention strategies that mitigated the underlying generation pipeline of the deepfakes before they occurred. They consisted of adversarial perturbations for creating deepfake generators, digital watermarking for content authenticity verification, real-time AI monitoring for content creation pipelines, and blockchain-based content verification frameworks. Despite these advancements, zero-shot detection and prevention faced critical challenges such as adversarial attacks, scalability constraints, ethical dilemmas, and the absence of standardized evaluation benchmarks. These limitations were addressed by discussing future research directions on explainable AI for deepfake detection, multimodal fusion based on image, audio, and text analysis, quantum AI for enhanced security, and federated learning for privacy-preserving deepfake detection. This further highlighted the need for an integrated defense framework for digital authenticity that utilized zero-shot learning in combination with preventive deepfake mechanisms. Finally, we highlighted the important role of interdisciplinary collaboration between AI researchers, cybersecurity experts, and policymakers to create resilient defenses against the rising tide of deepfake attacks.

This paper proposes GluMind, a transformer-based multimodal framework designed for continual and long-term blood glucose forecasting. GluMind devises two attention mechanisms, including cross-attention and multi-scale attention, which operate in parallel and deliver accurate predictive performance. Cross-attention effectively integrates blood glucose data with other physiological and behavioral signals such as activity, stress, and heart rate, addressing challenges associated with varying sampling rates and their adverse impacts on robust prediction. Moreover, the multi-scale attention mechanism captures long-range temporal dependencies. To mitigate catastrophic forgetting, GluMind incorporates a knowledge retention technique into the transformer-based forecasting model. The knowledge retention module not only enhances the model's ability to retain prior knowledge but also boosts its overall forecasting performance. We evaluate GluMind on the recently released AIREADI dataset, which contains behavioral and physiological data collected from healthy people, individuals with prediabetes, and those with type 2 diabetes. We examine the performance stability and adaptability of GluMind in learning continuously as new patient cohorts are introduced. Experimental results show that GluMind consistently outperforms other state-of-the-art forecasting models, achieving approximately 15% and 9% improvements in root mean squared error (RMSE) and mean absolute error (MAE), respectively.

Shared decision-making (SDM) is necessary to achieve patient-centred care. Currently no methodology exists to automatically measure SDM at scale. This study aimed to develop an automated approach to measure SDM by using language modelling and the conversational alignment (CA) score. A total of 157 video-recorded patient-doctor conversations from a randomized multi-centre trial evaluating SDM decision aids for anticoagulation in atrial fibrillations were transcribed and segmented into 42,559 sentences. Context-response pairs and negative sampling were employed to train deep learning (DL) models and fine-tuned BERT models via the next sentence prediction (NSP) task. Each top-performing model was used to calculate four types of CA scores. A random-effects analysis by clinician, adjusting for age, sex, race, and trial arm, assessed the association between CA scores and SDM outcomes: the Decisional Conflict Scale (DCS) and the Observing Patient Involvement in Decision-Making 12 (OPTION12) scores. p-values were corrected for multiple comparisons with the Benjamini-Hochberg method. Among 157 patients (34% female, mean age 70 SD 10.8), clinicians on average spoke more words than patients (1911 vs 773). The DL model without the stylebook strategy achieved a recall@1 of 0.227, while the fine-tuned BERTbase (110M) achieved the highest recall@1 with 0.640. The AbsMax (18.36 SE7.74 p=0.025) and Max CA (21.02 SE7.63 p=0.012) scores generated with the DL without stylebook were associated with OPTION12. The Max CA score generated with the fine-tuned BERTbase (110M) was associated with the DCS score (-27.61 SE12.63 p=0.037). BERT model sizes did not have an impact the association between CA scores and SDM. This study introduces an automated, scalable methodology to measure SDM in patient-doctor conversations through explainable CA scores, with potential to evaluate SDM strategies at scale.

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 $π_{0}$, 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 designed to be effective for transferring across tasks, environments, and embodiments. It outperforms models trained with ground-truth robotics actions and similar pretraining methods on the LIBERO benchmark and real-world setup, while being significantly more efficient and practical for real-world settings.

Function calling is a core capability of Large Language Models (LLMs), essential for AI agents. We introduce IFEval-FC, a benchmark inspired by IFEval (Zhou et al., 2023), which assesses precise instruction following in function calling. IFEval-FC encodes verifiable formats directly within JSON schema descriptions, such as "a value must not contain punctuation". It offers 750 test cases, each consisting of a function with an embedded format for one of its input parameters and a corresponding user query. The evaluation is fully algorithmic, ensuring objectivity, reproducibility, and scalability. Our results indicate that even state-of-the-art proprietary models, such as GPT -5 (OpenAI, 2025) and Claude Opus 4.1 (Anthropic, 2025), frequently fail to adhere to basic formatting rules, highlighting a significant limitation for practical applications in real-world agent systems.