Visual AutoRegressive modeling (VAR) based on next-scale prediction has revitalized autoregressive visual generation. Although its full-context dependency, i.e., modeling all previous scales for next-scale prediction, facilitates more stable and comprehensive representation learning by leveraging complete information flow, the resulting computational inefficiency and substantial overhead severely hinder VAR's practicality and scalability. This motivates us to develop a new VAR model with better performance and efficiency without full-context dependency. To address this, we reformulate VAR as a non-full-context Markov process, proposing Markov-VAR. It is achieved via Markovian Scale Prediction: we treat each scale as a Markov state and introduce a sliding window that compresses certain previous scales into a compact history vector to compensate for historical information loss owing to non-full-context dependency. Integrating the history vector with the Markov state yields a representative dynamic state that evolves under a Markov process. Extensive experiments demonstrate that Markov-VAR is extremely simple yet highly effective: Compared to VAR on ImageNet, Markov-VAR reduces FID by 10.5\% (256×256) and decreases peak memory consumption by 83.8\% (1024×1024). We believe that Markov-VAR can serve as a foundation for future research on visual autoregressive generation and other downstream tasks.

Understanding how non-pharmaceutical interventions (NPIs) influence epidemic trajectories is critical for evidence-based public health planning. Most COVID-19 models either treat NPIs as fixed effects, ignoring behavioral fatigue, or use black-box learning approaches that lack epidemiological transparency. We propose NeuralSEIR, a hybrid modeling framework that links daily human mobility to time-varying disease transmission in a mechanistically interpretable way. The model integrates a vaccination-aware compartmental core (SVEIC), which estimates a baseline transmission rate, with a shallow multilayer perceptron (MLP) that adjusts this baseline using Google mobility data to produce a behavior-aware rate. These components are coupled via ordinary differential equations, ensuring epidemiological consistency while allowing adaptive learning.Applied to nine COVID-19 waves across Germany, Japan, and the Philippines, NeuralSEIR reduces 14-day mean absolute percentage error by up to 60 % compared to a mobility-free baseline. It also reveals country-specific correlations between mobility patterns and transmission, highlighting the role of retail, transit, and residential activity in shaping NPI effectiveness. Benchmarks on U.S. state-level data against six CDC-tracked models further demonstrate its accuracy. By capturing mobility-driven changes in transmission, NeuralSEIR offers a transparent, data-informed tool for tailoring NPIs to local behavioral dynamics-bridging mechanistic epidemiology and explainable AI.

Pre-trained language models advance patent classification and retrieval via encoding claims as flat token sequences, yet overlooking the dependency hierarchy among claims. Incorporating the hierarchy into self-attention poses two challenges. First, claim dependencies involve relation types with varying reliability: treating them indiscriminately allows noisy technical relations to corrupt cleaner legal citation signals. Second, when the dependency graph is defined over claims, Transformer models fail as they operate at the token level; broadcasting claim-level adjacency can dilute structural information across unrelated token pairs. A novel Patent Heterogeneous Attention Graph Encoder (PHAGE) addresses these challenges. To handle heterogeneous dependencies, PHAGE constructs a typed graph to separate legal citations from technical relations as distinct edge types. To bridge the hierarchy gap, PHAGE introduces a connectivity mask with learnable relation-aware biases to project a claim-level topology into token-level attention. PHAGE learns a dual-granularity contrastive objective to align representations with inter-patent taxonomy and intra-patent topology. Experiments show that PHAGE outperforms domain-adapted and citation-aware baselines on patent classification, retrieval, and clustering. PHAGE discloses that the intra-patent claim topology captures stronger inductive bias than the inter-patent structure.

Diffusion and flow-matching based text-to-speech (TTS) models excel in naturalness but often lack explicit emotion control, as emotional signals remain entangled with speaker identity. We discover that emotion embedding emerges as a linearly decodable direction of frozen hidden states, nearly orthogonal to the direction embedding speaker identity. This inspires a plug-and-play framework DUET for emotion control over pretrained diffusion and flow-matching based TTS models. During generation, DUET unifies dual-space control to achieve fine-grained emotion intervention in a single per-step update: hidden space steering shifts generation along the target emotion direction, while mel-space guidance refines spectral details through gradients backpropagated from a differentiable vocoder. We validate DUET on five architecturally diverse pretrained TTS backbones across three datasets, where it outperforms 10 supervised state-of-the-art emotional TTS baselines across paradigms and achieves the highest human-rated emotion appropriateness. To further showcase its qualitative behavior, we deploy DUET on an Ameca humanoid robot, where it produces richly expressive emotional speech on the humanoid, demonstrating the strong potential for plug-and-play affective interaction for embodied agents.

In the approximately century-long journey of robotics, humanoid robots made their debut around six decades ago. While current humanoids bear human-like appearances, none have embodied true humaneness, remaining distant from achieving human-like to human-level intelligence. The rapid recent advancements in generative AI and (multimodal) large language models have further reignited and escalated interest in humanoids toward real-time, interactive, and multimodal designs and applications, such as fostering humanoid workers, advisers, educators, medical professionals, caregivers, and receptionists. These unveil boundless opportunities of transforming (1) AI robotics into a research era of humanoid AI, and (2) AI robots into new-generation humanoid AI robots (AI humanoids). Our unique and comprehensive review of about 30 reported humanoids discloses a systematic terminology and a paradigmatic landscape of human-looking to human-like and human-level humanoids. It inspires comprehensive new perspectives and directions of humanoid AI as an area: transitioning from human-looking to humane humanoids, humanizing humanoids with functional and nonfunctional specifications, and cultivating technical and actionable advances of AI humanoids. Humanoid AI and AI humanoids nurture symbiotic advancements and future opportunities of synthesizing and transforming humanity modeling and conventional, generative to human-level AI into humanoid robotics.

Calibration is usually evaluated in aggregate, but the most dangerous failures are often local: predictions that remain highly confident despite being wrong. We study this failure mode as false-confidence concentration, the extent to which confident errors occupy compact, discoverable regions of prediction space. We introduce FALCON-Discover, a post-hoc, model-agnostic framework that ranks predictions using discrepancy signals from confidence, local support, neighborhood agreement, and perturbation stability. Across seven binary tabular datasets, four seeds, five-fold cross-fitting, and strong learners including XGBoost and CatBoost, we find that false-confidence concentration is recurrent but regime-dependent. At the main confidence threshold, discrepancy-based ranking substantially outperforms the strongest validation-selected calibration or trust-scoring baseline in the strongest regimes, while raw confidence recovers little dangerous-error mass. The best detector varies across datasets: learned discrepancy is strongest when multiple cues must be combined, whereas stability-centered ranking works best when local decisional fragility dominates. These results show that dangerous overconfidence is better treated as a family-level discovery problem than as a single-score calibration problem, and motivate calibration strategies that explicitly target regions where confidence, support, and stability diverge.

Fine-grained facial expression transfer from humans to humanoid agents presents a unique pattern recognition challenge due to the significant domain gap between biological facial dynamics and mechanical control spaces. While visual synthesis of talking heads has advanced rapidly, mapping high-dimensional visual cues to precise, physically constrained actuation signals remains an open problem, primarily due to the lack of large-scale paired data. To bridge this gap, we introduce X2C, a comprehensive benchmark dataset comprising 100,000 〈image,control value〉 pairs. Unlike existing resources, X2C features nuanced, physically grounded expressions annotated with 30 continuous control parameters, establishing a high-fidelity standard for this task. Building on this resource, we propose X2CNet, a two-stage deep learning framework that explicitly decouples visual motion features from mechanical control regression to model the correspondence between human perceptual cues and humanoid actuation. Extensive experiments, including quantitative benchmarking and real-world physical validation, demonstrate that our approach achieves superior cross-domain consistency and enables robust, in-the-wild expression imitation. Video demonstrations are available at: https://pi3-14159265324.github.io/X2C/.

Autoregressive decoders emit flat token sequences and cannot enforce hierarchical constraints across output segments, a limitation that becomes acute in patent claim generation, where a claim set forms a dependency forest whose scope must narrow monotonically with depth. Topology and content are mutually dependent: a dependent claim's wording must reflect its parent's scope, yet the parent must be chosen before that wording exists, so neither post-hoc parsing nor grammar-constrained decoding suffices. We propose SPG (Structure-aware Patent Generation), which predicts topology inside the autoregressive pass. A pointer head selects each dependent claim's parent, and its gradients, together with a depth-adaptive scope regularizer, reshape the shared decoder's representations during training. A second stage then applies a violation-weighted preference objective over self-generated deficient candidates, supplying the negative signal that granted-patent corpora lack. On HUPD-DCG, SPG on Llama-3-8B-Instruct recovers 79.0\% of gold parent links, a quantity its training reward never supervises, and raises antecedent consistency from 0.292 to 0.478 over a supervised baseline of equal scale, with expert evaluation corroborating these gains.

Separating multiple effects in time series is fundamental yet challenging for time-series forecasting (TSF). However, existing TSF models cannot effectively learn interpretable multi-effect decomposition by their smoothing-based temporal techniques. Here, a new interpretable frequency-based decomposition pipeline MLOW captures the insight: a time series can be represented as a magnitude spectrum multiplied by the corresponding phase-aware basis functions, and the magnitude spectrum distribution of a time series always exhibits observable patterns for different effects. MLOW learns a low-rank representation of the magnitude spectrum to capture dominant trending and seasonal effects. We explore low-rank methods, including PCA, NMF, and Semi-NMF, and find that none can simultaneously achieve interpretable, efficient and generalizable decomposition. Thus, we propose hyperplane-nonnegative matrix factorization (Hyperplane-NMF). Further, to address the frequency (spectral) leakage restricting high-quality low-rank decomposition, MLOW enables a flexible selection of input horizons and frequency levels via a mathematical mechanism. Visual analysis demonstrates that MLOW enables interpretable and hierarchical multiple-effect decomposition, robust to noises. It can also enable plug-and-play in existing TSF backbones with remarkable performance improvement but minimal architectural modifications.

Block-wise decoding effectively improves the inference speed and quality in diffusion language models (DLMs) by combining inter-block sequential denoising and intra-block parallel unmasking. However, existing block-wise decoding methods typically partition blocks in a rigid and fixed manner, which inevitably fragments complete semantic or syntactic constituents, leading to suboptimal performance. Inspired by the entropy reduction hypothesis (ERH), we recognize that constituent boundaries offer greater opportunities for uncertainty reduction, which motivates us to employ entropy analysis for identifying constituent boundaries. Therefore, we propose Swordsman, an entropy-driven adaptive block-wise decoding framework for DLMs. Swordsman adaptively partitions blocks by identifying entropy shifts between adjacent tokens to better align with semantic or syntactic constituent boundaries. In addition, Swordsman dynamically adjusts unmasking thresholds conditioned on the real-time unmasking status within a block, further improving both efficiency and stability. As a training-free framework, supported by KV Cache, Swordsman demonstrates state-of-the-art performance across extensive evaluations. Our code is now available.

In real-world scenarios, random modality missingness in multimodal federated learning (mFL) poses a significant challenge, diminishing the performance of global model inference. However, existing mFL methods are predominantly limited to simple scenarios that typically involve participant clients restricted to either a single modality or multimodal clients with complete modalities. They employ modality-specific encoders on each client and train modality fusion modules on the server, leading to severe task drift between clients and server, and struggling to generalize effectively in intricate modality-missing scenarios. To this end, we present a novel mFL framework to alleviate the task drift and performance degradation resulting from modality missingness during both training and inference. Inspired by prototype learning using the highly generalized proxy of specific information, we elaborately construct a prototype library to enhance FedAvg-based federated learning (FL). Naturally, we utilize prototypes as masks representing missing modalities to compensate for the missingness of modality information, formulating a task-calibrated training loss and devising a model-agnostic modality-incomplete inference strategy. In addition, a proximal term based on prototype contrastive learning is constructed to integrate interclient global information into each client, therefore enhancing local training. We conduct extensive experiments to evaluate our mFL framework, demonstrating its state-of-the-art performance across a series of missingness settings. Specifically, compared with existing mFL methods, our mFL framework improves inference performance under different modality missingness rates during training and by 23.8% during modality-incomplete inference.

Post-hoc calibration for time-series classification usually remaps output scores, but deployment decisions such as trust, abstention, and review depend on whether a confident prediction is supported by the current temporal signal. We address three time-series reliability gaps: identical confidence values can hide different temporal support, average calibration can miss false high-confidence errors, and output-space recalibration offers limited input-linked auditability. We introduce a validation-gated fixed-label reliability policy that keeps the backbone prediction unchanged while estimating whether it should be trusted. The method combines output-side cues with whole-sample spectral descriptors, including band energy, entropy, peak dominance, period support, and phase stability, to form a scalar reliability estimate and diagnostic band-level evidence. A validation gate enables spectral conditioning only when correctness ranking improves without breaching FalseConf@0.9 or AURC tolerances; otherwise it reverts to the safer output-space baseline. Across eight heterogeneous UCR/UEA datasets, eight time-series backbone families, and standard recalibrators, the unconstrained method improves fixed-label selective-reliability metrics on the matched evaluation subset, raising Corr-AURC from 0.693 to 0.779. The validation-gated policy further improves Corr-AURC to 0.786 and reduces FalseConf@0.9 to 0.094. These results suggest that reliability estimation for time-series classifiers benefits from bundling output confidence with spectral evidence, while validation gating prevents unsupported spectral conditioning.

Temporal point processes (TPPs) are effective for modeling event occurrences over time but struggle with sparse and uncertain events in federated systems, where privacy is a major concern. To address this, we propose FedPP, a federated neural nonparametric point process model. FedPP integrates neural embeddings into sigmoidal Gaussian Cox processes (SGCPs) on the client side. SGCPs is a flexible and expressive class of TPPs, allowing FedPP to generate highly flexible intensity functions that capture client-specific event dynamics and uncertainties while efficiently summarizing historical records. For global aggregation, FedPP introduces a divergence-based mechanism to communicate the distributions of kernel hyperparameters in SGCPs between the server and clients, while keeping client-specific parameters local to ensure privacy and personalization. FedPP effectively captures event uncertainty and sparsity. Extensive experiments demonstrate its superior performance in federated settings, showing global aggregation with the KL divergence and the Wasserstein distance.

Large Language Models (LLMs) hold significant promise for improving clinical decision support and reducing physician burnout by synthesizing complex, longitudinal cancer Electronic Health Records (EHRs). However, their implementation in this critical field faces three primary challenges: the inability to effectively process the extensive length and fragmented nature of patient records for accurate temporal analysis; a heightened risk of clinical hallucination, as conventional grounding techniques such as Retrieval-Augmented Generation (RAG) do not adequately incorporate process-oriented clinical guidelines; and unreliable evaluation metrics that hinder the validation of AI systems in oncology. To address these issues, we propose CliCARE, a framework for Grounding Large Language Models in Clinical Guidelines for Decision Support over Longitudinal Cancer Electronic Health Records. The framework operates by transforming unstructured, longitudinal EHRs into patient-specific Temporal Knowledge Graphs (TKGs) to capture long-range dependencies, and then grounding the decision support process by aligning these real-world patient trajectories with a normative guideline knowledge graph. This approach provides oncologists with evidence-grounded decision support by generating a high-fidelity clinical summary and an actionable recommendation. We validated our framework using large-scale, longitudinal data from a private Chinese cancer dataset and the public English MIMIC-IV dataset. In these settings, CliCARE significantly outperforms baselines, including leading long-context LLMs and Knowledge Graph-enhanced RAG methods. The clinical validity of our results is supported by a robust evaluation protocol, which demonstrates a high correlation with assessments made by oncologists.

Bayesian optimization is a powerful technique for optimizing expensive-to-evaluate black-box functions, consisting of two main components: a surrogate model and an acquisition function. In recent years, myopic acquisition functions have been widely adopted for their simplicity and effectiveness. However, their lack of look-ahead capability limits their performance. To address this limitation, we propose FigBO, a generalized acquisition function that incorporates the future impact of candidate points on global information gain. FigBO is a plug-and-play method that can integrate seamlessly with most existing myopic acquisition functions. Theoretically, we analyze the regret bound and convergence rate of FigBO when combined with the myopic base acquisition function expected improvement (EI), comparing them to those of standard EI. Empirically, extensive experimental results across diverse tasks demonstrate that FigBO achieves state-of-the-art performance and significantly faster convergence compared to existing methods.

Visual AutoRegressive modeling (VAR) suffers from substantial computational cost due to the massive token count involved. Failing to account for the continuous evolution of modeling dynamics, existing VAR token reduction methods face three key limitations: heuristic stage partition, non-adaptive schedules, and limited acceleration scope, thereby leaving significant acceleration potential untapped. Since entropy variation intrinsically reflects the transition of predictive uncertainty, it offers a principled measure to capture modeling dynamics evolution. Therefore, we propose NOVA, a training-free token reduction acceleration framework for VAR models via entropy analysis. NOVA adaptively determines the acceleration activation scale during inference by online identifying the inflection point of scale entropy growth. Through scale-linkage and layer-linkage ratio adjustment, NOVA dynamically computes distinct token reduction ratios for each scale and layer, pruning low-entropy tokens while reusing the cache derived from the residuals at the prior scale to accelerate inference and maintain generation quality. Extensive experiments and analyses validate NOVA as a simple yet effective training-free acceleration framework. Code is available.

Speech emotion recognition (SER) is essential for humanoid robot tasks such as social robotic interactions and robotic psychological diagnosis, where interpretable and efficient models are critical for safety and performance. Existing deep models trained on large datasets remain largely uninterpretable, often insufficiently modeling underlying emotional acoustic signals and failing to capture and analyze the core physiology of emotional vocal behaviors. Physiological research on human voices shows that the dynamics of vocal amplitude and phase correlate with emotions through the vocal tract filter and the glottal source. However, most existing deep models solely involve amplitude but fail to couple the physiological features of and between amplitude and phase. Here, we propose PhysioSER, a physiology-informed vocal spectrotemporal representation learning method, to address these issues with a compact, plug-and-play design. PhysioSER constructs amplitude and phase views informed by voice anatomy and physiology (VAP) to complement SSL models for SER. This VAP-informed framework incorporates two parallel workflows: a vocal feature representation branch to decompose vocal signals based on VAP, embed them into a quaternion field, and use Hamilton-structured quaternion convolutions for modeling their dynamic interactions; and a latent representation branch based on a frozen SSL backbone. Then, utterance-level features from both workflows are aligned by a Contrastive Projection and Alignment framework, followed by a shallow attention fusion head for SER classification. PhysioSER is shown to be interpretable and efficient for SER through extensive evaluations across 14 datasets, 10 languages, and 6 backbones, and its practical efficacy is validated by real-time deployment on a humanoid robotic platform.

Equipping humanoid robots with coherent and adaptable personas is crucial for fostering natural, engaging, and trustworthy human-robot interaction (HRI). However, existing approaches often rely on static, hard-coded identities that lack the flexibility to adapt to individual user contexts. In this paper, we present PACE (Persona Adaptation through Conversational Elicitation), a novel framework for the interactive generation and deployment of structured personas on the Ameca humanoid robot. Our system introduces an Interactive Persona Elicitation Pipeline, enabling the robot to dynamically synthesize a tailored, psychologically grounded identity through user Q A. This elicitation process feeds into a persona prompt compilation phase, generating a structured persona prompt built upon multi-perspective dimensions. We detail the Embodied System Integration required to translate this structured specification into expressive, multimodal humanoid behaviors. Through a comprehensive empirical HRI evaluation, we assess the impact of dynamically generated personas on user trust, perceived anthropomorphism, persona consistency, personal relevance, and interaction quality compared to a generic baseline. These contributions establish a scalable pathway for deploying personalized, interactive, and reliable identities in embodied humanoid assistants. Video demo is available at: https://lipzh5.github.io/PACE/

Understanding enzyme thermal properties is essential for biotechnology and protein engineering, yet experimental measurements of attributes such as temperature optimum, stability, and range remain labor-intensive and costly. Prior studies have shown that specific regions within enzyme sequences disproportionately influence thermal behavior—an aspect often overlooked by existing deep learning models. In this work, we introduce PatchET, a biologically inspired deep learning model that predicts enzyme thermal properties directly from amino acid sequences. PatchET employs a dual-stage, patch-based architecture that captures both intra-patch local features and inter-patch global dependencies, reflecting the hierarchical nature of protein thermal adaptation. Alongside the model, we curate a comprehensive benchmark, including a refined dataset for temperature optimum and the first publicly available dataset for temperature range prediction. PatchET achieves state-of-the-art performance across three key tasks—temperature optimum, stability, and range—and serves as the first dedicated model for temperature range prediction. Extensive ablation studies further validate the effectiveness of our architectural design. Together, PatchET and the accompanying benchmark provide a unified and generalizable framework for modeling enzyme thermal properties, offering new tools for the rational design of thermostable enzymes.

Training-free video editing (VE) models tend to fall back on gender stereotypes when rendering profession-related prompts. We propose \textbf{FAME} for \textit{Fairness-aware Attention-modulated Video Editing} that mitigates profession-related gender biases while preserving prompt alignment and temporal consistency for coherent VE. We derive fairness embeddings from existing minority representations by softly injecting debiasing tokens into the text encoder. Simultaneously, FAME integrates fairness modulation into both temporal self attention and prompt-to-region cross attention to mitigate the motion corruption and temporal inconsistency caused by directly introducing fairness cues. For temporal self attention, FAME introduces a region constrained attention mask combined with time decay weighting, which enhances intra-region coherence while suppressing irrelevant inter-region interactions. For cross attention, it reweights tokens to region matching scores by incorporating fairness sensitive similarity masks derived from debiasing prompt embeddings. Together, these modulations keep fairness-sensitive semantics tied to the right visual regions and prevent temporal drift across frames. Extensive experiments on new VE fairness-oriented benchmark \textit{FairVE} demonstrate that FAME achieves stronger fairness alignment and semantic fidelity, surpassing existing VE baselines.