The \textit{Temporal Fusion Transformer} (TFT), proposed by Lim \textit{et al.}, published in \textit{International Journal of Forecasting} (2021), is a state-of-the-art attention-based deep neural network architecture specifically designed for multi-horizon time series forecasting. It has demonstrated significant performance improvements over existing benchmarks. In this work, we introduce the Quantum Temporal Fusion Transformer (QTFT), a quantum-enhanced hybrid quantum-classical architecture that extends the capabilities of the classical TFT framework. The core idea of this work is inspired by the foundation studies, \textit{The Power of Quantum Neural Networks} by Amira Abbas \textit{et al.} and \textit{Quantum Vision Transformers} by El Amine Cherrat \textit{et al.}, published in \textit{ Nature Computational Science} (2021) and \textit{Quantum} (2024), respectively. A key advantage of our approach lies in its foundation on a variational quantum algorithm, enabling implementation on current noisy intermediate-scale quantum (NISQ) devices without strict requirements on the number of qubits or circuit depth. Our results demonstrate that QTFT is successfully trained on the forecasting datasets and is capable of accurately predicting future values. In particular, our experimental results on two different datasets display that the model outperforms its classical counterpart in terms of both training and test loss. These results indicate the prospect of using quantum computing to boost deep learning architectures in complex machine learning tasks.

AI agents built on foundation models hold enormous promise. Current practice, however, focuses on a one-task-one-agent approach, which not only falls short of scalability and generality, but also faces practical limitations from black-box autoregressive reasoning, where decisions unfold token by token without explicit simulation or counterfactual evaluation of outcomes. Humans, on the other hand, reason and plan by mentally simulating the consequences of actions within an internal model of the world -- a capability that supports flexible, goal-directed behavior across diverse contexts. Moving towards a more general and powerful AI agent, we introduce SimuRA, a goal-oriented architecture for generalized agentic reasoning. Based on a principled formulation of an optimal agent in any general environment, SimuRA addresses the limitations of black-box autoregressive reasoning by incorporating the world model for planning via simulation. Our prototype world model is implemented using LLMs as a substrate, leveraging the natural language as a discrete, hierarchical representation grounded in concepts for planning, while remaining model-agnostic. On complex web-browsing tasks such as flight search, SimuRA improves the success rate from 0% to 32.2% compared to a representative open-web agent baseline. Across tasks, world-model-based planning achieves up to 124% higher task completion rates than a matched black-box autoregressive baseline, demonstrating the advantages of simulative reasoning. We release ReasonerAgent-Web, a web-browsing agent built on SimuRA, as an open-source research demo.

Large language models (LLMs) store vast amounts of knowledge, which often requires updates to correct factual errors, incorporate newly acquired information, or adapt model behavior. Model editing methods have emerged as efficient solutions for such updates, offering localized and precise knowledge modification at significantly lower computational cost than continual training. In parallel, LLMs are frequently fine-tuned for a wide range of downstream tasks. However, the effect of fine-tuning on previously edited knowledge remains poorly understood. In this work, we systematically investigate how different fine-tuning objectives interact with various model editing techniques. Our findings show that edited knowledge is substantially more susceptible to forgetting during fine-tuning than intrinsic knowledge acquired through pre-training. This analysis highlights a key limitation of current editing approaches and suggests that evaluating edit robustness under downstream fine-tuning is critical for their practical deployment. We further find that knowledge retention can be significantly improved by either augmenting edit knowledge with paraphrases or by freezing layers associated with edited content in fine-tuning stage, offering insight for developing more robust editing algorithms.

Despite advances in reinforcement learning (RL)-based video reasoning with large language models (LLMs), data collection and fine-tuning remain significant challenges. These methods often rely on large-scale supervised fine-tuning (SFT) with extensive video data and long Chain-of-Thought (CoT) annotations, making them costly and hard to scale. To address this, we present Video-RTS, a new approach to improve video reasoning capability with drastically improved data efficiency by combining data-efficient RL with a video-adaptive test-time scaling (TTS) strategy. Building on observations about the data scaling, we skip the resource-intensive SFT step and employ efficient pure-RL training with output-based rewards, requiring no additional annotations or extensive fine-tuning. Furthermore, to utilize computational resources more efficiently, we introduce a sparse-to-dense video TTS strategy that improves inference by iteratively adding frames based on output consistency. We validate our approach on multiple video reasoning benchmarks, showing that Video-RTS surpasses existing video reasoning models by 2.4% in accuracy using only 3.6% training samples. Specifically, Video-RTS achieves a 4.2% improvement on Video-Holmes, a recent and challenging video reasoning benchmark. Notably, our pure RL training and adaptive video TTS offer complementary strengths, enabling Video-RTS's strong reasoning performance.

Solving inverse problems -- recovering signals from incomplete or noisy measurements -- is fundamental in science and engineering. Score-based generative models (SGMs) have recently emerged as a powerful framework for this task. Two main paradigms have formed: unsupervised approaches that adapt pretrained generative models to inverse problems, and supervised bridge methods that train stochastic processes conditioned on paired clean and corrupted data. While the former typically assume knowledge of the measurement model, the latter have largely overlooked this structural information. We introduce System embedded Diffusion Bridge Models (SDBs), a new class of supervised bridge methods that explicitly embed the known linear measurement system into the coefficients of a matrix-valued SDE. This principled integration yields consistent improvements across diverse linear inverse problems and demonstrates robust generalization under system misspecification between training and deployment, offering a promising solution to real-world applications.

-- Human activity intensity prediction is crucial to many location - based services. Despite tremendous p rogress in modeling d ynamics of human activity, most existing methods overlook physical constraints of spatial interaction, leading to uninterpretable spatial correlations and over - smoothing phenomenon . To address these limitations, this work proposes a physics - informed deep learning framework, namely Gravity - informed Spatiotemporal Transformer (Gravityformer) by integrat ing the universal law of gravitation to refin e transformer attention. Specifically, it (1) estimates two spatially explicit mass parameters based on spatiotemporal embedding feature, (2) models the spatial interaction in end - to - end neural network using proposed adaptive gravity model to learn the physic al constrain t, and (3) utilizes the learned spatial interaction to guide and mitigate the over - smoothing phenomenon in transformer attention. Moreover, a parallel spatiotemporal graph convolution transformer is proposed for achieving a balance between coupled spatial and temporal learning. Systematic experiments on six real - world large - scale activity datasets demonstrate the quantitative and qualitative superiority of our model over state - of - the - art benchmarks. Additionally, the learned gravity attention matrix can be not only disentangled and interpreted based on geographical laws, but also improved the generalization in zero - shot cross - region inference . This work provides a novel insight into integrating physical laws with deep learning for spatiotemporal prediction . Index Terms -- Human activity intensity prediction; Gravity model; Spatial interaction; Physics - informed machine learning; Over - smoothing phenomenon; Spatiotemporal graph neural network . This work is supported by the National Natural Science Foundation of China ( Grant # 42430106, 42371468, 424B2013) . Y i Wang, Zhenghong Wang, Fan Zhang, Chengling Tang, Weiyu Zhang and Yu Liu are with Institute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University, Beijing 100871, China. Chaogui Kang is with National Engineering Research Center of Geographic Information System, China University of Geosciences (Wuhan) 430074, China. Sijie Ruan is with School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China . Di Zhu and Zhongfu Ma are with Department of Geography, Environment and Society, University of Minnesota, Twin Cities, Minneapolis, MN 55455, USA . Y u Zheng is with JD iCity, JD Technology, Beijing 100176, China . P hilip S. Yu is with Department of Computer Science, University of Illinois Chicago, Chicago 60607, USA .

A challenge in human-AI decision-making is to balance three factors: the correctness of predictions, the cost of knowledge and reasoning complexity, and the confidence about whether to abstain from automated answers or escalate to human experts. In this work, we present a cascaded LLM decision framework that adaptively delegates tasks across multiple tiers of expertise -- a base model for initial candidate answers, a more capable and knowledgeable (but costlier) large model, and a human expert for when the model cascade abstains. Our method proceeds in two stages. First, a deferral policy determines whether to accept the base model's answer or regenerate it with the large model based on the confidence score. Second, an abstention policy decides whether the cascade model response is sufficiently certain or requires human intervention. Moreover, to overcome static policies and accommodate changing task difficulty, we incorporate an online learning mechanism which uses human feedback. We demonstrate this approach to general question-answering (ARC-Easy, ARC-Challenge, and MMLU) and medical question-answering (MedQA and MedMCQA). Our results demonstrate that our cascaded strategy outperforms single-model baselines in most cases, achieving higher accuracy while reducing costs and providing a principled approach to handling abstentions.

Synthetic data generation is increasingly used in machine learning for training and data augmentation. Yet, current strategies often rely on external foundation models or datasets, whose usage is restricted in many scenarios due to policy or legal constraints. We propose ScoreMix, a self-contained synthetic generation method to produce hard synthetic samples for recognition tasks by leveraging the score compositionality of diffusion models. The approach mixes class-conditioned scores along reverse diffusion trajectories, yielding domain-specific data augmentation without external resources. We systematically study class-selection strategies and find that mixing classes distant in the discriminator's embedding space yields larger gains, providing up to 3% additional average improvement, compared to selection based on proximity. Interestingly, we observe that condition and embedding spaces are largely uncorrelated under standard alignment metrics, and the generator's condition space has a negligible effect on downstream performance. Across 8 public face recognition benchmarks, ScoreMix improves accuracy by up to 7 percentage points, without hyperparameter search, highlighting both robustness and practicality. Our method provides a simple yet effective way to maximize discriminator performance using only the available dataset, without reliance on third-party resources. Paper website: https://parsa-ra.github.io/scoremix/.

Anomaly Detection (AD) and Anomaly Localization (AL) are crucial in fields that demand high reliability, such as medical imaging and industrial monitoring. However, current AD and AL approaches are often susceptible to adversarial attacks due to limitations in training data, which typically include only normal, unlabeled samples. This study introduces PatchGuard, an adversarially robust AD and AL method that incorporates pseudo anomalies with localization masks within a Vision Transformer (ViT)-based architecture to address these vulnerabilities. We begin by examining the essential properties of pseudo anomalies, and follow it by providing theoretical insights into the attention mechanisms required to enhance the adversarial robustness of AD and AL systems. We then present our approach, which leverages Foreground-Aware Pseudo-Anomalies to overcome the deficiencies of previous anomaly-aware methods. Our method incorporates these crafted pseudo-anomaly samples into a ViT-based framework, with adversarial training guided by a novel loss function designed to improve model robustness, as supported by our theoretical analysis. Experimental results on well-established industrial and medical datasets demonstrate that PatchGuard significantly outperforms previous methods in adversarial settings, achieving performance gains of $53.2\%$ in AD and $68.5\%$ in AL, while also maintaining competitive accuracy in non-adversarial settings. The code repository is available at https://github.com/rohban-lab/PatchGuard .

Recent advances in Chain-of-Thought (CoT) reasoning have improved complex video understanding, but existing methods often struggle to adapt to domain-specific skills (e.g., event detection, spatial relation understanding, emotion understanding) over various video content. To address this, we propose Video-Skill-CoT (a.k.a. Video-SKoT), a framework that automatically constructs and leverages skill-aware CoT supervisions for domain-adaptive video reasoning. First, we construct skill-based CoT annotations: we extract domain-relevant reasoning skills from training questions, cluster them into a shared skill taxonomy, and create detailed multi-step CoT rationale tailored to each video-question pair for training. Second, we introduce a skill-specific expert learning framework. Each expert module specializes in a subset of reasoning skills and is trained with lightweight adapters using the collected CoT supervision. We demonstrate the effectiveness of the proposed approach on three video understanding benchmarks, where Video-SKoT consistently outperforms strong baselines. We also provide in-depth analyses on comparing different CoT annotation pipelines and learned skills over multiple video domains.