arXiv subjects

Xu He

Publications and source records attributed to Xu He.

At least 37 records · Page 2Linked to original sources

arXiv2026

Unlocking Static Polarization and Strain Density Waves in Perovskites by Softening a Hidden Antiferrodistortive Tilt Gradient Mode

Spin density waves (SDWs) represent a fundamental paradigm of spatially modulated order in condensed matter systems, yet their electrical and mechanical analogues polarization and strain density waves (PDWs and StDWs) have remained elusive as equilibrium phases. Here, we introduce a general, symmetry-driven strategy to unlock static PDWs and StDWs in perovskites SrTiO3 and SrMnO3. Using first-principles calculations, we uncover a previously overlooked soft antiferrodistortive tilt gradient mode at small-q wavevector in the phonon dispersion of their presumed Ima2 ground state under moderate tensile strain. Group-theory analysis reveals that a hard polaracoustic phonon, which intrinsically carries PDWs and StDWs, is improperly destabilized by a trilinear coupling with this modulated tilt mode and an inherently uniform tilt mode. This interaction drives a structural transition from the Ima2 phase to a novel lower-energy Pmn21 phase that hosts long-range-ordered PDWs and StDWs. Strikingly, the engineered StDWs in SrMnO3 activate an electrically tunable SDW via the flexomagnetic effect. These discoveries fundamentally revise the strain-phase diagrams of prototypical perovskites and establish a unified phonon-engineering framework that links modulated phonon instabilities to targeted density-wave order, offering new pathways for designing advanced electromechanical and magnetoelectric functionalities.

cond-mat.mtrl-sci↗

arXiv2026

Semantic-Aware Prefix Learning for Token-Efficient Image Generation

Visual tokenizers play a central role in latent image generation by bridging high-dimensional images and tractable generative modeling. However, most existing tokenizers are still trained with reconstruction-dominated objectives, which often yield latent representations that are only weakly grounded in high-level semantics. Recent approaches improve semantic alignment, but typically treat semantic signals as auxiliary regularization rather than making them functionally necessary for representation learning. We propose SMAP, a SeMantic-Aware Prefix tokenizer that injects class-level semantic conditions into a query-based 1D tokenization framework. To make semantics indispensable during training, SMAP introduces a tail token dropping strategy, which forces semantic conditions and early latent prefixes to bear increasing responsibility under progressively reduced token budgets. To verify that the resulting latent space is useful for generation rather than reconstruction alone, we further introduce CARD, a hybrid Causal AutoRegressive--Diffusion generator. Extensive experiments on ImageNet show that SMAP consistently improves reconstruction quality across discrete and continuous tokenization settings, and that its semantically grounded latent space yields strong downstream generation performance under compact token budgets.

cs.CV↗

arXiv2026

From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping

Audio-driven visual dubbing aims to synchronize a video's lip movements with new speech but is fundamentally challenged by the lack of ideal training data: paired videos differing only in lip motion. Existing methods circumvent this via mask-based inpainting. However, masking inevitably destroys spatiotemporal context, leading to identity drift and poor robustness (e.g., to occlusions), while also inducing lip-shape leakage that degrades lip sync. To bridge this gap, we propose X-Dub, a novel two-stage generative bootstrapping framework leveraging powerful Diffusion Transformers to unlock mask-free dubbing. Our core insight is to repurpose a mask-based inpainting model exclusively as a dedicated data generator to synthesize scalable, high-fidelity pseudo-paired data, which is subsequently utilized to train and bootstrap a robust, mask-free editing model as the final video dubber. The final dubber is liberated from masking artifacts and leverages the complete video input for high-fidelity inference. We further introduce timestep-adaptive multi-phase learning to disentangle conflicting objectives (structure, lip motion, and texture) across diffusion phases, facilitating stable convergence and advanced editing quality. Additionally, we present X-DubBench, a benchmark for diverse scenarios. Extensive experiments demonstrate that our method achieves state-of-the-art performance with superior lip sync, visual quality, and robustness.

cs.CV↗

arXiv2026

Kling-MotionControl Technical Report

Character animation aims to generate lifelike videos by transferring motion dynamics from a driving video to a reference image. Recent strides in generative models have paved the way for high-fidelity character animation. In this work, we present Kling-MotionControl, a unified DiT-based framework engineered specifically for robust, precise, and expressive holistic character animation. Leveraging a divide-and-conquer strategy within a cohesive system, the model orchestrates heterogeneous motion representations tailored to the distinct characteristics of body, face, and hands, effectively reconciling large-scale structural stability with fine-grained articulatory expressiveness. To ensure robust cross-identity generalization, we incorporate adaptive identity-agnostic learning, facilitating natural motion retargeting for diverse characters ranging from realistic humans to stylized cartoons. Simultaneously, we guarantee faithful appearance preservation through meticulous identity injection and fusion designs, further supported by a subject library mechanism that leverages comprehensive reference contexts. To ensure practical utility, we implement an advanced acceleration framework utilizing multi-stage distillation, boosting inference speed by over 10x. Kling-MotionControl distinguishes itself through intelligent semantic motion understanding and precise text responsiveness, allowing for flexible control beyond visual inputs. Human preference evaluations demonstrate that Kling-MotionControl delivers superior performance compared to leading commercial and open-source solutions, achieving exceptional fidelity in holistic motion control, open domain generalization, and visual quality and coherence. These results establish Kling-MotionControl as a robust solution for high-quality, controllable, and lifelike character animation.

cs.CV↗

arXiv2026

3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation

Existing methods for human motion control in video generation typically rely on either 2D poses or explicit 3D parametric models (e.g., SMPL) as control signals. However, 2D poses rigidly bind motion to the driving viewpoint, precluding novel-view synthesis. Explicit 3D models, though structurally informative, suffer from inherent inaccuracies (e.g., depth ambiguity and inaccurate dynamics) which, when used as a strong constraint, override the powerful intrinsic 3D awareness of large-scale video generators. In this work, we revisit motion control from a 3D-aware perspective, advocating for an implicit, view-agnostic motion representation that naturally aligns with the generator's spatial priors rather than depending on externally reconstructed constraints. We introduce 3DiMo, which jointly trains a motion encoder with a pretrained video generator to distill driving frames into compact, view-agnostic motion tokens, injected semantically via cross-attention. To foster 3D awareness, we train with view-rich supervision (i.e., single-view, multi-view, and moving-camera videos), forcing motion consistency across diverse viewpoints. Additionally, we use auxiliary geometric supervision that leverages SMPL only for early initialization and is annealed to zero, enabling the model to transition from external 3D guidance to learning genuine 3D spatial motion understanding from the data and the generator's priors. Experiments confirm that 3DiMo faithfully reproduces driving motions with flexible, text-driven camera control, significantly surpassing existing methods in both motion fidelity and visual quality.

cs.CV↗

arXiv2026

JEPA-VLA: Video Predictive Embedding is Needed for VLA Models

Recent vision-language-action (VLA) models built upon pretrained vision-language models (VLMs) have achieved significant improvements in robotic manipulation. However, current VLAs still suffer from low sample efficiency and limited generalization. This paper argues that these limitations are closely tied to an overlooked component, pretrained visual representation, which offers insufficient knowledge on both aspects of environment understanding and policy prior. Through an in-depth analysis, we find that commonly used visual representations in VLAs, whether pretrained via language-image contrastive learning or image-based self-supervised learning, remain inadequate at capturing crucial, task-relevant environment information and at inducing effective policy priors, i.e., anticipatory knowledge of how the environment evolves under successful task execution. In contrast, we discover that predictive embeddings pretrained on videos, in particular V-JEPA 2, are adept at flexibly discarding unpredictable environment factors and encoding task-relevant temporal dynamics, thereby effectively compensating for key shortcomings of existing visual representations in VLAs. Building on these observations, we introduce JEPA-VLA, a simple yet effective approach that adaptively integrates predictive embeddings into existing VLAs. Our experiments demonstrate that JEPA-VLA yields substantial performance gains across a range of benchmarks, including LIBERO, LIBERO-plus, RoboTwin2.0, and real-robot tasks.

cs.CV↗

arXiv2026

ASTER: Agentic Scaling with Tool-integrated Extended Reasoning

Reinforcement learning (RL) has emerged as a dominant paradigm for eliciting long-horizon reasoning in Large Language Models (LLMs). However, scaling Tool-Integrated Reasoning (TIR) via RL remains challenging due to interaction collapse: a pathological state where models fail to sustain multi-turn tool usage, instead degenerating into heavy internal reasoning with only trivial, post-hoc code verification. We systematically study three questions: (i) how cold-start SFT induces an agentic, tool-using behavioral prior, (ii) how the interaction density of cold-start trajectories shapes exploration and downstream RL outcomes, and (iii) how the RL interaction budget affects learning dynamics and generalization under varying inference-time budgets. We then introduce ASTER (Agentic Scaling with Tool-integrated Extended Reasoning), a framework that circumvents this collapse through a targeted cold-start strategy prioritizing interaction-dense trajectories. We find that a small expert cold-start set of just 4K interaction-dense trajectories yields the strongest downstream performance, establishing a robust prior that enables superior exploration during extended RL training. Extensive evaluations demonstrate that ASTER-4B achieves state-of-the-art results on competitive mathematical benchmarks, reaching 90.0% on AIME 2025, surpassing leading frontier open-source models, including DeepSeek-V3.2-Exp.

cs.CL↗

arXiv2025

Exploring the Potential of Spiking Neural Networks in UWB Channel Estimation

Although existing deep learning-based Ultra-Wide Band (UWB) channel estimation methods achieve high accuracy, their computational intensity clashes sharply with the resource constraints of low-cost edge devices. Motivated by this, this letter explores the potential of Spiking Neural Networks (SNNs) for this task and develops a fully unsupervised SNN solution. To enable a comprehensive performance analysis, we devise an extensive set of comparative strategies and evaluate them on a compelling public benchmark. Experimental results show that our unsupervised approach still attains 80% test accuracy, on par with several supervised deep learning-based strategies. Moreover, compared with complex deep learning methods, our SNN implementation is inherently suited to neuromorphic deployment and offers a drastic reduction in model complexity, bringing significant advantages for future neuromorphic practice.

cs.ET↗

arXiv2025

UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation

Recent video generation models demonstrate impressive synthesis capabilities but remain limited by single-modality conditioning, constraining their holistic world understanding. This stems from insufficient cross-modal interaction and limited modal diversity for comprehensive world knowledge representation. To address these limitations, we introduce UnityVideo, a unified framework for world-aware video generation that jointly learns across multiple modalities (segmentation masks, human skeletons, DensePose, optical flow, and depth maps) and training paradigms. Our approach features two core components: (1) dynamic noising to unify heterogeneous training paradigms, and (2) a modality switcher with an in-context learner that enables unified processing via modular parameters and contextual learning. We contribute a large-scale unified dataset with 1.3M samples. Through joint optimization, UnityVideo accelerates convergence and significantly enhances zero-shot generalization to unseen data. We demonstrate that UnityVideo achieves superior video quality, consistency, and improved alignment with physical world constraints. Code and data can be found at: https://github.com/dvlab-research/UnityVideo

cs.CV↗

arXiv2025

A Content-Preserving Secure Linguistic Steganography

Existing linguistic steganography methods primarily rely on content transformations to conceal secret messages. However, they often cause subtle yet looking-innocent deviations between normal and stego texts, posing potential security risks in real-world applications. To address this challenge, we propose a content-preserving linguistic steganography paradigm for perfectly secure covert communication without modifying the cover text. Based on this paradigm, we introduce CLstega (\textit{C}ontent-preserving \textit{L}inguistic \textit{stega}nography), a novel method that embeds secret messages through controllable distribution transformation. CLstega first applies an augmented masking strategy to locate and mask embedding positions, where MLM(masked language model)-predicted probability distributions are easily adjustable for transformation. Subsequently, a dynamic distribution steganographic coding strategy is designed to encode secret messages by deriving target distributions from the original probability distributions. To achieve this transformation, CLstega elaborately selects target words for embedding positions as labels to construct a masked sentence dataset, which is used to fine-tune the original MLM, producing a target MLM capable of directly extracting secret messages from the cover text. This approach ensures perfect security of secret messages while fully preserving the integrity of the original cover text. Experimental results show that CLstega can achieve a 100\% extraction success rate, and outperforms existing methods in security, effectively balancing embedding capacity and security.

cs.CR↗

arXiv2025

Finite-temperature properties and the hidden ferroelectric $R3c$ phase of bulk CaTiO$_3$ from second principles

A second-principles effective interatomic potential is introduced for the prototypical perovskite CaTiO$_3$ (CTO), relying on a Taylor polynomial expansion of the Born-Oppenheimer energy surface around the cubic reference structure, in terms of atomic displacements and macroscopic strains. This model captures various phases of bulk CTO and successfully reproduces, in particular, the structure, energy, and dynamical properties of the nonpolar $Pbnm$ ground state as well as of the hidden ferroelectric $R3c$ phase. Finite-temperature simulations suggest that the still debated sequence of structural phase transitions over heating is $Pbnm \ (a^-a^-c^+) \rightarrow C2/m \ (a^-b^-c^0) \rightarrow I4/mcm \ (a^-c^0c^0) \rightarrow Pm\bar{3}m \ (a^0a^0a^0)$, a sequence during which the oxygen-octahedra rotations around the three pseudocubic axes vanish successively. Although never experimentally observed in bulk, the ferroelectric $R3c$ phase appears to be metastable and at an energy only slightly above the $Pbnm$ ground state at 0 K. The simulations confirm that, if induced in some way, the $R3c$ phase remains stable up to about 300 K and shows ferroelectric properties. Furthermore, we find that the minimum energy path connecting the $Pbnm$ and $R3c$ phases involves localized layer-by-layer flipping of octahedral rotations, a mechanism which is shown to be at play during the thermal destabilization process of the $R3c$ phase toward the $Pbnm$ ground state. The proximity of the $R3c$ phase with the $Pbnm$ ground state suggests that the former could be stabilized under electric field. However, due to the large energy barrier, the field required for the $Pbnm$-to-$R3c$ transition appears to be extremely large, consistent with the fact that bulk CTO was never reported to be ferroelectric nor antiferroelectric.

cond-mat.mtrl-sci↗

arXiv2025

VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction

The scalability of video understanding models is increasingly limited by the prohibitive storage and computational costs of large-scale video datasets. While data synthesis has improved data efficiency in the image domain, its extension to video remains challenging due to pervasive temporal redundancy and complex spatiotemporal dynamics. In this work, we uncover a critical insight: the primary source of inefficiency in video datasets is not inter-sample redundancy, but intra-sample frame-level redundancy. To leverage this insight, we introduce VideoCompressa, a novel framework for video data synthesis that reframes the problem as dynamic latent compression. Specifically, VideoCompressa jointly optimizes a differentiable keyframe selector-implemented as a lightweight ConvNet with Gumbel-Softmax sampling-to identify the most informative frames, and a pretrained, frozen Variational Autoencoder (VAE) to compress these frames into compact, semantically rich latent codes. These latent representations are then fed into a compression network, enabling end-to-end backpropagation. Crucially, the keyframe selector and synthetic latent codes are co-optimized to maximize retention of task-relevant information. Experiments show that our method achieves unprecedented data efficiency: on UCF101 with ConvNets, VideoCompressa surpasses full-data training by 2.34\% points using only 0.13\% of the original data, with over 5800x speedup compared to traditional synthesis method. Moreover, when fine-tuning Qwen2.5-7B-VL on HMDB51, VideoCompressa matches full-data performance using just 0.41\% of the training data-outperforming zero-shot baseline by 10.61\%.

cs.CV↗

arXiv2025

Beyond Normality: Reliable A/B Testing with Non-Gaussian Data

A/B testing has become the cornerstone of decision-making in online markets, guiding how platforms launch new features, optimize pricing strategies, and improve user experience. In practice, we typically employ the pairwise $t$-test to compare outcomes between the treatment and control groups, thereby assessing the effectiveness of a given strategy. To be trustworthy, these experiments must keep Type I error (i.e., false positive rate) under control; otherwise, we may launch harmful strategies. However, in real-world applications, we find that A/B testing often fails to deliver reliable results. When the data distribution departs from normality or when the treatment and control groups differ in sample size, the commonly used pairwise $t$-test is no longer trustworthy. In this paper, we quantify how skewed, long tailed data and unequal allocation distort error rates and derive explicit formulas for the minimum sample size required for the $t$-test to remain valid. We find that many online feedback metrics require hundreds of millions samples to ensure reliable A/B testing. Thus we introduce an Edgeworth-based correction that provides more accurate $p$-values when the available sample size is limited. Offline experiments on a leading A/B testing platform corroborate the practical value of our theoretical minimum sample size thresholds and demonstrate that the corrected method substantially improves the reliability of A/B testing in real-world conditions.

stat.ML↗

arXiv2025

Navigate in Demanding Missions: Integrating Human Intelligence and Brain-Inspired Intelligence

This perspective analyzes the intricate interplay among neuroscience, Brain-Inspired Intelligence (BII), and Brain-Inspired Navigation (BIN), revealing a current lack of cooperative relationship between Brain-Computer Interfaces (BCIs) and BIN fields. We advocate for the integration of neuromorphic-empowered BCI into BIN, thereby bolstering the unmanned systems' reliable navigation in demanding missions, such as deep space exploration, etc. We highlight that machine intelligence, reinforced by brain-inspired artificial consciousness, can extend human intelligence, with human intelligence mediated by neuromorphic-enabled BCI acting as a safeguard in case machine intelligence failures. This study also discusses the potentials of the proposed approach to enhance unmanned systems' capabilities and facilitate the diagnostics of spatial cognition disorders, while considering associated ethical and security concerns.

cs.ET↗

arXiv2025

A Preliminary Exploration of the Differences and Conjunction of Traditional PNT and Brain-inspired PNT

Developing universal Positioning, Navigation, and Timing (PNT) is our enduring goal. Today's complex environments demand PNT that is more resilient, energy-efficient and cognitively capable. This paper asks how we can endow unmanned systems with brain-inspired spatial cognition navigation while exploiting the high precision of machine PNT to advance universal PNT. We provide a new perspective and roadmap for shifting PNT from "tool-oriented" to "cognition-driven". Contributions: (1) multi-level dissection of differences among traditional PNT, biological brain PNT and brain-inspired PNT; (2) a four-layer (observation-capability-decision-hardware) fusion framework that unites numerical precision and brain-inspired intelligence; (3) forward-looking recommendations for future development of brain-inspired PNT.

cs.RO↗

arXiv2025

PathFix: Automated Program Repair with Expected Path

Automated program repair (APR) techniques are effective in fixing inevitable defects in software, enhancing development efficiency and software robustness. However, due to the difficulty of generating precise specifications, existing APR methods face two main challenges: generating too many plausible patch candidates and overfitting them to partial test cases. To tackle these challenges, we introduce a new APR method named PathFix, which leverages path-sensitive constraints extracted from correct execution paths to generate patches for repairing buggy code. It is based on one observation: if a buggy program is repairable, at least one expected path is supposed to replace the fault path in the patched program. PathFix operates in four main steps. First, it traces fault paths reaching the fault output in the buggy program. Second, it derives expected paths by analyzing the desired correct output on the control flow graph, where an expected path defines how a feasible patch leads to the correct execution. Third, PathFix generates and evaluates patches by solving state constraints along the expected path. Fourth, we validate the correctness of the generated patch. To further enhance repair performance and mitigate scalability issues introduced by path-sensitive analysis, we integrate a large language model (LLM) into our framework. Experimental results show that PathFix outperforms existing solutions, particularly in handling complex program structures such as loops and recursion.

cs.SE↗

arXiv2025

Mechanical coupling of polar topologies and oxygen octahedra rotations in PbTiO$_3$/SrTiO$_3$ superlattices

PbTiO$_3$/SrTiO$_3$ artificial superlattices recently emerged as a prototypical platform for the emergence and study of polar topologies. While previous studies mainly focused on the polar textures inherent to the ferroelectric PbTiO$_3$ layers, the oxygen octahedra rotations inherent to the paraelectric SrTiO$_3$ layers have attracted much little attention. Here, we highlight a biunivocal relationship between distinct polar topologies -- including $a_1/a_2$ domains, polar vortices, and skyrmions -- within the PbTiO$_3$ layers and specific patterns of oxygen octahedra rotations in the SrTiO$_3$ layers. This relationship arises from a strain-mediated coupling between the two materials and is shown to be reciprocal. Through second-principles atomistic simulations, we demonstrate that each polar texture imposes a corresponding rotation pattern, while conversely, a frozen oxygen octahedra rotation dictates the emergence of the associated polar state. This confirms the strong coupling between oxygen octahedra rotations in SrTiO$_3$ and polarization in PbTiO$_3$, highlighting their cooperative role in stabilizing complex polar textures in related superlattices.

cond-mat.mtrl-sci↗

arXiv2025

StableDub: Taming Diffusion Prior for Generalized and Efficient Visual Dubbing

The visual dubbing task aims to generate mouth movements synchronized with the driving audio, which has seen significant progress in recent years. However, two critical deficiencies hinder their wide application: (1) Audio-only driving paradigms inadequately capture speaker-specific lip habits, which fail to generate lip movements similar to the target avatar; (2) Conventional blind-inpainting approaches frequently produce visual artifacts when handling obstructions (e.g., microphones, hands), limiting practical deployment. In this paper, we propose StableDub, a novel and concise framework integrating lip-habit-aware modeling with occlusion-robust synthesis. Specifically, building upon the Stable-Diffusion backbone, we develop a lip-habit-modulated mechanism that jointly models phonemic audio-visual synchronization and speaker-specific orofacial dynamics. To achieve plausible lip geometries and object appearances under occlusion, we introduce the occlusion-aware training strategy by explicitly exposing the occlusion objects to the inpainting process. By incorporating the proposed designs, the model eliminates the necessity for cost-intensive priors in previous methods, thereby exhibiting superior training efficiency on the computationally intensive diffusion-based backbone. To further optimize training efficiency from the perspective of model architecture, we introduce a hybrid Mamba-Transformer architecture, which demonstrates the enhanced applicability in low-resource research scenarios. Extensive experimental results demonstrate that StableDub achieves superior performance in lip habit resemblance and occlusion robustness. Our method also surpasses other methods in audio-lip sync, video quality, and resolution consistency. We expand the applicability of visual dubbing methods from comprehensive aspects, and demo videos can be found at https://stabledub.github.io.

cs.CV↗