arXiv subjects

Zhe Gao

Publications and source records attributed to Zhe Gao.

At least 19 recordsLinked to original sources

arXiv2026

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction, supported by a multi-source data infrastructure spanning AAA games, simulation engines, and internet videos to learn controllable world dynamics. WorldExplorer performs agent-driven collection guided by training feedback, while a unified pipeline applies 14 deterministic quality checks, VLM-based assessment, and synchronized action and text annotation. We progressively distill a bidirectional action-conditioned teacher into a causal student through teacher forcing and ODE distillation, and introduce LongForcing to align long student self-rollouts with an extended-horizon teacher, mitigating accumulated distribution shift and autoregressive drift. Raw keyboard actions provide a unified control interface for scene roaming and third-person character interaction, while reference-character memory provides persistent appearance cues for identity consistency during third-person rollouts. For deployment, we co-design a streaming inference stack with a lightweight VAE decoder, efficient attention, memory-aware scheduling, and low-bit DiT inference. Across optimized low-bit configurations, ABot-World-0 streams 720P video at up to 16 FPS on a single NVIDIA RTX 5090 desktop GPU, with 1.2s action-to-first-frame latency and approximately 19GiB peak VRAM. Experiments on WorldRoamBench and extended interactive rollouts demonstrate competitive controllability and coherent long-horizon world evolution.

cs.CV↗

arXiv2026

Task-Specific Feature Fusion Method for Multi-Task Affective Behavior Analysis

The 11th Affective Behavior Analysis in-the-wild (ABAW11) Multi-Task Learning Challenge requires a unified system to predict valence-arousal, categorical expressions, and facial action units from the official s-Aff-Wild2 images. Although these tasks are naturally related through facial behavior, our validation experiments show that they benefit from different visual features, temporal processing strategies, fusion mechanisms, and calibration procedures. In this paper, we study task-adaptive feature fusion for ABAW11 multi-task affective behavior analysis. We first adapt two pretrained visual backbones, DINOv2 ViT-L and DINOv3 ConvNeXt-base, on an external expression-oriented facial image set and then freeze them to extract complementary frame-level features from the official ABAW11 data. On top of these frozen features, we systematically compare frame-level prediction heads, temporal convolutional heads, post-hoc temporal smoothing, LightGBM models, feature concatenation, gated fusion, residual fusion, late logit fusion, threshold calibration, and shared MTL structures. The final system selects task-specific fusion and prediction strategies rather than forcing all tasks to share a single architecture. On the ABAW11 validation set, the selected system achieves an EXPR macro-F1 of 0.4222, an AU macro-F1 of 0.5402, and a mean VA CCC of 0.6717, resulting in an overall validation score of 1.6341. The results suggest that task-adaptive fusion of frozen visual features is a simple and effective strategy for ABAW-style multi-task affective behavior analysis.

cs.CV↗

arXiv2026

Implicit discretization schemes for full-kinetic ion and drift-kinetic electron simulations

We present a new electromagnetic plasma simulation model with full-kinetic ions and drift-kinetic electrons. This model (termed as FIDES) solves the electric field using the implicit perpendicular Ohm's law and a novel implicit parallel Ampere's law, where the latter requires an implicit scheme for the parallel electric field in advancing the electron weights. To suppress unphysical high-frequency instabilities, ion weights are advanced using an implicit scheme for perpendicular electric fields. Simulations of perpendicular and parallel waves validate the model's capability in handling high-frequency physics. Low-frequency wave simulations demonstrate that the implicit parallel Ampere's law can mitigate the cancellation problem more effectively than the conventional schemes using the parallel Ohm's law. To reduce the numerical damping from implicit time-stepping, we develop a second-order scheme for particle pushing. Meanwhile, an integrated strategy combining the first- and second-order schemes is employed to suppress odd-even decoupling while maintaining the accuracy of the second-order formulation.

physics.plasm-ph↗

arXiv2026

WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models

Despite rapid progress in interactive world models (IWMs), existing benchmarks evaluate action following only at trajectory level and ignore memory and interaction physics. We introduce WorldRoamBench, an open-world benchmark for long-horizon stability across four dimensions, each with tailored innovations: (i) Action: per-frame action metric bypassing cross-model semantic scale disparity and exposing failures hidden by trajectory; (ii) Vision: segment-based drift metric capturing non-monotonic mid-sequence collapse missed by start-vs-end comparisons; (iii) Physics: controllability-gated evaluation over mechanics, optics, and 3D consistency, scoring plausibility under faithful action execution; (iv) Memory: action-decoupled protocol evaluating scene memory via transition-localized 3D point-cloud reconstruction and subject memory via tracking-plus-VLM reasoning. The benchmark comprises 600+ test cases across Nature, Urban, and Indoor scenes in first/third-person views with WASD 10-60s continuous interaction. Evaluating 10+ open/closed-source models reveals none reliably satisfies all dimensions; even the best achieves only moderate scores. Advances on WorldRoamBench are steps toward IWMs that are stable, physically grounded, memory-faithful, and deployable in real-world applications.

cs.CV↗

arXiv2026

VideoWeave: Unlocking Geometric Consistency in Video Generation via Joint Geometry-Video Modeling

Large-scale video diffusion models often fail to preserve 3D structure over time, causing geometric drift and implausible motion under viewpoint changes. Existing methods usually enforce geometric consistency by using explicit geometry reconstructions, such as depth maps, point clouds, or reconstructed 3D structures, to define conditions, supervision, or reward signals, making the generator sensitive to errors from upstream geometry pipelines. We propose VideoWeave, a latent-space post-training framework that uses implicit geometry-model features to constrain the generative distribution, providing a more flexible and non-rigid form of guidance that mitigates the impact of reconstruction errors from geometry models. Specifically, VideoWeave adapts these features into geometry latents and jointly models them with video latents in a shared denoising space, allowing geometry to shape the generative distribution during training. To support this process, we build GeoVid-80K, an 80K-video dataset with paired appearance and geometry representations. Experiments on text-to-video and image-to-video generation show that VideoWeave improves geometric coherence while preserving strong visual quality. VideoWeave project page at https://videoweave.github.io/

cs.CV↗

arXiv2026

King Function for Shifted Gaussian: Laguerre Structure, Spectral Theory and Density

We study King function arising as radial kernels in the laboratory-frame spherical harmonic expansion of shifted Gaussian distributions. We first clarify their relation with the co-moving Laguerre hierarchy by means of a King--Laguerre expansion. We then derive the King differential equation and show that the associated self-adjoint operator in a Gaussian-weighted Hilbert space is unitarily equivalent to the free radial Schr\"odinger operator on the half-line. This yields the spectral representation and generalized eigenfunction. Finally, we prove that real-parameter King function, lies in the resolvent set, form a dense non-orthogonal system in a natural radial velocity space, providing an approximation-theoretic basis for King mixture representations. Weighted $L^1$-integrability criteria and closed-form moment formulas are also derived, justifying the normalization of King function.

math-ph↗

arXiv2026

VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning

Existing Multimodal Large Language Models (MLLMs) often suffer from hallucinations in long video understanding (LVU), primarily due to the imbalance between textual and visual tokens. Observing that MLLMs handle short visual inputs well, recent LVU works alleviate hallucinations by automatically parsing the vast visual data into manageable segments that can be effectively processed by MLLMs. SFT-based tool-calling methods can serve this purpose, but they typically require vast amounts of fine-grained, high-quality data and suffer from constrained tool-calling trajectories. We propose a novel VideoTIR that leverages Reinforcement Learning (RL) to encourage proper usage of comprehensive multi-level toolkits for efficient long video understanding. VideoTIR explores both Zero-RL and SFT cold-starting to enable MLLMs to retrieve and focus on meaningful video segments/images/regions, enhancing long video understanding both accurately and efficiently. To reduce redundant tool-calling, we propose Toolkit Action Grouped Policy Optimization (TAGPO), which enhances the efficiency of the calling process through stepwise reward assignment and reuse of failed rollouts. Additionally, we develop a sandbox-based trajectory synthesis framework to generate high-quality trajectories data. Extensive experiments on three long-video QA benchmarks demonstrate the effectiveness and efficiency of our method.

cs.CV↗

arXiv2026

A Two-Stage Dual-Modality Model for Facial Emotional Expression Recognition

This paper addresses the expression (EXPR) recognition challenge in the 10th Affective Behavior Analysis in-the-Wild (ABAW) workshop and competition, which requires frame-level classification of eight facial emotional expressions from unconstrained videos. This task is challenging due to inaccurate face localization, large pose and scale variations, motion blur, temporal instability, and other confounding factors across adjacent frames. We propose a two-stage dual-modal (audio-visual) model to address these difficulties. Stage I focuses on robust visual feature extraction with a pretrained DINOv2-based encoder. Specifically, DINOv2 ViT-L/14 is used as the backbone, a padding-aware augmentation (PadAug) strategy is employed for image padding and data preprocessing from raw videos, and a mixture-of-experts (MoE) training head is introduced to enhance classifier diversity. Stage II addresses modality fusion and temporal consistency. For the visual modality, faces are re-cropped from raw videos at multiple scales, and the extracted visual features are averaged to form a robust frame-level representation. Concurrently, frame-aligned Wav2Vec 2.0 audio features are derived from short audio windows to provide complementary acoustic cues. These dual-modal features are integrated via a lightweight gated fusion module, followed by inference-time temporal smoothing. Experiments on the ABAW dataset demonstrate the effectiveness of the proposed method. The two-stage model achieves a Macro-F1 score of 0.5368 on the official validation set and 0.5122 +/- 0.0277 under 5-fold cross-validation, outperforming the official baselines.

cs.CV↗

arXiv2026

Pathwise Test-Time Correction for Autoregressive Long Video Generation

Distilled autoregressive diffusion models facilitate real-time short video synthesis but suffer from severe error accumulation during long-sequence generation. While existing Test-Time Optimization (TTO) methods prove effective for images or short clips, we identify that they fail to mitigate drift in extended sequences due to unstable reward landscapes and the hypersensitivity of distilled parameters. To overcome these limitations, we introduce Test-Time Correction (TTC), a training-free alternative. Specifically, TTC utilizes the initial frame as a stable reference anchor to calibrate intermediate stochastic states along the sampling trajectory. Extensive experiments demonstrate that our method seamlessly integrates with various distilled models, extending generation lengths with negligible overhead while matching the quality of resource-intensive training-based methods on 30-second benchmarks.

cs.CV↗

arXiv2025

Contrastive Heliophysical Image Pretraining for Solar Dynamics Observatory Records

Deep learning has revolutionized solar image analysis, yet most approaches train task-specific encoders from scratch or rely on natural-image pretraining that ignores the unique characteristics of Solar Dynamics Observatory (SDO) data. We introduce SolarCHIP, a family of contrastively pretrained visual backbones tailored to multi-instrument SDO observations. SolarCHIP addresses three key challenges in solar imaging: multimodal sensing across AIA and HMI instruments, weak inter-class separability due to slow temporal evolution, and strong intra-class variability with sparse activity signals. Our pretraining framework employs a multi-granularity contrastive objective that jointly aligns (1) global class tokens across co-temporal AIA-HMI pairs to enhance temporal discrimination, (2) local patch tokens at fixed spatial indices to enforce position-consistent, modality-invariant features, and (3) intra-sample patches across different spatial locations to preserve fine-grained spatial structure. We train both CNN- and Vision Transformer-based autoencoders and demonstrate their effectiveness on two downstream tasks: cross-modal translation between HMI and AIA passbands via ControlNet, and full-disk flare classification. Experimental results show that SolarCHIP achieves state-of-the-art performance across both tasks, with particularly strong gains in low-resource settings where labeled data is limited. Ablation studies confirm that each contrastive component contributes essential discriminative capacity at different granularities. By publicly releasing pretrained weights and training code, we provide the heliophysics community with a practical, plug-and-play feature extractor that reduces computational requirements, improves label efficiency, and establishes a reusable foundation for diverse solar imaging applications.

cs.CV↗

arXiv2025

FusionMAE: large-scale pretrained model to optimize and simplify diagnostic and control of fusion plasma

In magnetically confined fusion device, the complex, multiscale, and nonlinear dynamics of plasmas necessitate the integration of extensive diagnostic systems to effectively monitor and control plasma behaviour. The complexity and uncertainty arising from these extensive systems and their tangled interrelations has long posed a significant obstacle to the acceleration of fusion energy development. In this work, a large-scale model, fusion masked auto-encoder (FusionMAE) is pre-trained to compress the information from 88 diagnostic signals into a concrete embedding, to provide a unified interface between diagnostic systems and control actuators. Two mechanisms are proposed to ensure a meaningful embedding: compression-reduction and missing-signal reconstruction. Upon completion of pre-training, the model acquires the capability for 'virtual backup diagnosis', enabling the inference of missing diagnostic data with 96.7% reliability. Furthermore, the model demonstrates three emergent capabilities: automatic data analysis, universal control-diagnosis interface, and enhancement of control performance on multiple tasks. This work pioneers large-scale AI model integration in fusion energy, demonstrating how pre-trained embeddings can simplify the system interface, reducing necessary diagnostic systems and optimize operation performance for future fusion reactors.

physics.plasm-ph↗

arXiv2025

Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation

Current autoregressive diffusion models excel at video generation but are generally limited to short temporal durations. Our theoretical analysis indicates that the autoregressive modeling typically suffers from temporal drift caused by error accumulation and hinders parallelization in long video synthesis. To address these limitations, we propose a novel planning-then-populating framework centered on Macro-from-Micro Planning (MMPL) for long video generation. MMPL sketches a global storyline for the entire video through two hierarchical stages: Micro Planning and Macro Planning. Specifically, Micro Planning predicts a sparse set of future keyframes within each short video segment, offering motion and appearance priors to guide high-quality video segment generation. Macro Planning extends the in-segment keyframes planning across the entire video through an autoregressive chain of micro plans, ensuring long-term consistency across video segments. Subsequently, MMPL-based Content Populating generates all intermediate frames in parallel across segments, enabling efficient parallelization of autoregressive generation. The parallelization is further optimized by Adaptive Workload Scheduling for balanced GPU execution and accelerated autoregressive video generation. Extensive experiments confirm that our method outperforms existing long video generation models in quality and stability. Generated videos and comparison results are in our project page.

cs.CV↗

arXiv2025

A kinetic CMA diagram

We present a kinetic Clemmow-Mullaly-Allis (CMA) diagram by systematically analysing the kinetic effects on the wave propagation in a homogeneous thermal plasma. The differences between the cold and kinetic CMA diagrams are outlined. It is found that new boundaries for weakly damped left- and right-handed circularly polarized waves are located above the ion and electron cyclotron frequency lines in the kinetic CMA diagram. Additionally, Langmuir waves in the kinetic CMA diagram occupy a specific region between the new Langmuir wave boundary and the plasma frequency line, while in the cold CMA diagram, they exist on the plasma frequency line. The extraordinary-Bernstein mode transformation frequency lines in the kinetic CMA diagram replace the hybrid resonant frequency lines of the cold CMA diagram, with discontinuities between different cyclotron harmonics. These new boundaries partition the parameter space in the kinetic CMA diagram differently, leading to new inverse wave normal surfaces in the regions bounded by new boundaries. The kinetic CMA diagram not only contributes to a basic understanding of wave properties in thermal plasmas, but also can provide a powerful tool to explore new possible propagation paths.

physics.plasm-ph↗

arXiv2025

Identification of Genetic Factors Associated with Corpus Callosum Morphology: Conditional Strong Independence Screening for Non-Euclidean Responses

The corpus callosum, the largest white matter structure in the brain, plays a critical role in interhemispheric communication. Variations in its morphology are associated with various neurological and psychological conditions, making it a key focus in neurogenetics. Age is known to influence the structure and morphology of the corpus callosum significantly, complicating the identification of specific genetic factors that contribute to its shape and size. We propose a conditional strong independence screening method to address these challenges for ultrahigh-dimensional predictors and non-Euclidean responses. Our approach incorporates prior knowledge, such as age. It introduces a novel concept of conditional metric dependence, quantifying non-linear conditional dependencies among random objects in metric spaces without relying on predefined models. We apply this framework to identify genetic factors associated with the morphology of the corpus callosum. Simulation results demonstrate the efficacy of this method across various non-Euclidean data types, highlighting its potential to drive genetic discovery in neuroscience.

stat.AP↗

arXiv2025

DeepSuM: Deep Sufficient Modality Learning Framework

Multimodal learning has become a pivotal approach in developing robust learning models with applications spanning multimedia, robotics, large language models, and healthcare. The efficiency of multimodal systems is a critical concern, given the varying costs and resource demands of different modalities. This underscores the necessity for effective modality selection to balance performance gains against resource expenditures. In this study, we propose a novel framework for modality selection that independently learns the representation of each modality. This approach allows for the assessment of each modality's significance within its unique representation space, enabling the development of tailored encoders and facilitating the joint analysis of modalities with distinct characteristics. Our framework aims to enhance the efficiency and effectiveness of multimodal learning by optimizing modality integration and selection.

cs.LG↗

arXiv2024

On Density Limit of Lower Hybrid Current Drive caused by Parametric Decay Instability in Tokamak Plasmas

The density limit of lower hybrid current drive (LHCD) is scaled by coupling the saturation process of parametric decay instability induced by LH waves in the scrape off layer (SOL) plasma to the propagation of waves. It is shown that the density limit of LHCD satisfies $n_\text{lim}\propto L_y^{2/3} P_0^{-2/3}\omega_0^{2}B_0^{2/3}T_e$, which is consistent with results of simulations and previous experiments. Both theoretical analysis and simulation results indicate that the density limit is far from being reached for ITER baseline profile. Therefore, the density limit phenomena will not prevent LHCD from being a promising method of driving plasma current at ITER and future tokamaks.

physics.plasm-ph↗

arXiv2024

Studentized Tests of Independence: Random-Lifter approach

The exploration of associations between random objects with complex geometric structures has catalyzed the development of various novel statistical tests encompassing distance-based and kernel-based statistics. These methods have various strengths and limitations. One problem is that their test statistics tend to converge to asymptotic null distributions involving second-order Wiener chaos, which are hard to compute and need approximation or permutation techniques that use much computing power to build rejection regions. In this work, we take an entirely different and novel strategy by using the so-called ``Random-Lifter''. This method is engineered to yield test statistics with the standard normal limit under null distributions without the need for sample splitting. In other words, we set our sights on having simple limiting distributions and finding the proper statistics through reverse engineering. We use the Central Limit Theorems (CLTs) for degenerate U-statistics derived from our novel association measures to do this. As a result, the asymptotic distributions of our proposed tests are straightforward to compute. Our test statistics also have the minimax property. We further substantiate that our method maintains competitive power against existing methods with minimal adjustments to constant factors. Both numerical simulations and real-data analysis corroborate the efficacy of the Random-Lifter method.

stat.ME↗

arXiv2024

C$^3$DG: Conditional Domain Generalization for Hyperspectral Imagery Classification with Convergence and Constrained-risk Theories

Hyperspectral imagery (HSI) classification may suffer the challenge of hyperspectral-monospectra, where different classes present similar spectra. Joint spatial-spectral feature extraction is a popular solution for the problem, but this strategy tends to inflate accuracy since test pixels may exist in training patches. Domain generalization methods show promising potential, but they still fail to distinguish similar spectra across varying domains, in addition, the theoretical support is usually ignored. In this paper, we only rely on spectral information to solve the hyperspectral-monospectra problem, and propose a Convergence and Error-Constrained Conditional Domain Generalization method for Hyperspectral Imagery Classification (C$^3$DG). The major contributions of this paper include two aspects: the Conditional Revising Inference Block (CRIB), and the corresponding theories for model convergence and generalization errors. CRIB is the kernel structure of the proposed method, which employs a shared encoder and multi-branch decoders to fully leverage the conditional distribution during training, achieving a decoupling that aligns with the generation mechanisms of HSI. Moreover, to ensure model convergence and maintain controllable error, we propose the optimization convergence theorem and risk upper bound theorem. In the optimization convergence theorem, we ensure the model convergence by demonstrating that the gradients of the loss terms are not contradictory. In the risk upper bound theorem, our theoretical analysis explores the relationship between test-time training and recent related work to establish a concrete bound for error. Experimental results on three benchmark datasets indicate the superiority of C$^3$DG.

cs.CV↗