Searcharxiv⌕ Search

arXiv subjects

Jiao Xie

Publications and source records attributed to Jiao Xie.

At least 19 recordsLinked to original sources
arXiv2026

Spatial Temporal Synergy: Balancing Change and Invariance in Text Driven 3D Human Motion Editing

Text-driven human motion editing aims to modify existing motion sequences according to natural language instructions while maintaining the structural consistency of the original motion. Existing diffusion-based approaches struggle to balance text-responsive "change" and inertial "invariance". They often rely on coarse spatial constraints and rigid uniform time assumptions, leading to spatial motion distortions and the destruction of intrinsic physical rhythms during variable-length editing. To handle these challenges, we propose Change and Invariance Motion Editing (CIME), a unified framework that comprehensively decouples change and invariance into spatial pose and temporal rhythm dimensions. For spatial poses, our method integrates an omni-supervised positive-negative learning mechanism comprising hierarchical retrospective feature supervision, subtle motion preservation, and triplet-based semantic alignment. For temporal rhythms, we introduce the Riemannian Non-uniform Integral Manifold Mapping (RNIMM) module, which achieves high-fidelity reproduction of physical beats in the edited text via kinematics-aware non-uniform timestamps. Extensive experiments on the MotionFix and STANCE Adjustment datasets demonstrate that CIME achieves state-of-the-art performance in editing alignment and structural fidelity, validating the effectiveness of our unified architecture. Our source codes and models have been released at: github.com/ZhenwuShi/CIME.git

cs.CV↗
arXiv2026

Tunable Extended Magnetic Non-Fermi Liquid in Graphene Moiré Heterostructures

Exploring exotic quantum metallic states beyond Landau's Fermi liquid theory remains a central focus in condensed matter physics. Such non-Fermi liquid behavior is mostly observed near quantum criticality, yet growing attention is directed toward extended NFL phases with intrinsic quantum fluctuations rooted in the extended ground state. While these extended NFL states have been previously reported only in a limited set of d- and f-electron systems, realizing a single, highly tunable platform capable of exhibiting multiple resistance exponent values is essential for uncovering the connection between the resistance exponent and the dominant quantum fluctuations coupled to quasiparticles. However, corresponding experimental progress remains elusive. Here, we report the observation of tunable extended non-Fermi liquid behavior in twisted double bilayer graphene encapsulated by aligned hBN layers. This NFL phase spans a broad range of carrier densities and exhibiting a carrier density dependent resistance exponent. Combined with temperature dependent resistance, magnetotransport and differential resistance measurements, these findings support a scenario where strong quantum fluctuations emerge from the interplay between localized and itinerant carriers. Our work establishes a highly tunable platform beyond conventional frameworks to investigate the organizing principles of non-Fermi liquid physics manifested in diverse behaviors.

cond-mat.mes-hall↗
arXiv2026

Orientation-tunable correlated Chern insulating states in chiral twisted double bilayer graphene proximitized by WSe2

Moire flat bands in graphene systems proximitized by transition-metal dichalcogenides (TMDCs) provide a setting where spin-orbit coupling (SOC) can reshape band topology. The crystallographic alignment angle twist angle between TMDC and graphene layers is predicted to tune the balance of Ising and Rashba SOC, but a combined theoretical and experimental understanding of how twist angle governs the topological character of correlated states has not been systematically established. Here we show that in chiral-stacked twisted double bilayer graphene in proximity to WSe2, twist angle between graphene and WSe2 determines the topological character of correlated Chern insulators. Continuum model calculations reveal that Ising spin-orbit coupling dominates at zero twist angle, giving rise to flat bands with finite valley Chern numbers, whereas Rashba coupling dominates at larger twist angle, resulting in topologically trivial bands. Transport measurements at quarter filling confirm this picture: twist angle = 0 deg devices exhibit C = +1 Chern insulators, consistent with spontaneous isospin polarization, whereas twist angle = 15 degree devices show C = 0 despite exhibiting similar correlated insulating behavior. The sharp contrast establishes crystallographic alignment as a new tuning knob, complementary to twist angle, displacement field, and carrier density, for engineering correlated topological states in van der Waals heterostructures.

cond-mat.mes-hall↗
arXiv2026

CSD: Content-aware Speculative Decoding for Efficient Image Generation

Speculative decoding (SD) has emerged as a key solution to accelerate the inference of autoregressive models. However, in the field of image generation, it faces the challenge of low acceptance rates, and directly relaxing its criteria leads to degradation in image quality. In this paper, we propose a novel content-aware speculative decoding algorithm, termed CSD, which integrates an entropy-based probability relaxation mechanism with an optimal resampling strategy to enhance the inference efficiency for autoregressive image generation. By leveraging the informational uncertainty inherent in different regions of an image, CSD dynamically adjusts the acceptance probability of candidate tokens, increasing the acceptance rate in low-detail areas to accelerate generation. Moreover, a distribution alignment filter is introduced to ensure the output distribution to be aligned with the target model, which significantly improves the generative quality. Experiments conducted on Lumina-mGPT and Janus-Pro demonstrate that the superiority of the proposed CSD. Our source code is available at https://github.com/aderfebr/CSD.

cs.CV↗
arXiv2026

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression

Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computational overhead for inference. Existing CoT compression methods often suffer from a critical loss of logical fidelity at high compression ratios, resulting in significant performance degradation. To achieve high-fidelity, fast reasoning, we propose a novel EXTreme-RAtio Chain-of-Thought Compression framework, termed Extra-CoT, which aggressively reduces the token budget while preserving answer accuracy. To generate reliable, high-fidelity supervision, we first train a dedicated semantically-preserved compressor on mathematical CoT data with fine-grained annotations. An LLM is then fine-tuned on these compressed pairs via a mixed-ratio supervised fine-tuning (SFT), teaching it to follow a spectrum of compression budgets and providing a stable initialization for reinforcement learning (RL). We further propose Constrained and Hierarchical Ratio Policy Optimization (CHRPO) to explicitly incentivize question-solving ability under lower budgets by a hierarchical reward. Experiments on three mathematical reasoning benchmarks show the superiority of Extra-CoT. For example, on MATH-500 using Qwen3-1.7B, Extra-CoT achieves over 73\% token reduction with an accuracy improvement of 0.6\%, significantly outperforming state-of-the-art (SOTA) methods. Our source codes have been released at https://github.com/Mwie1024/Extra-CoT.

cs.LG↗
arXiv2026

Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learning

Text-based human motion editing aims to modify existing motion sequences according to natural language instructions while maintaining the consistency of the original motion. Existing diffusion-based approaches often rely on heuristic similarity cues or coarse global conditioning, leading to motion distortion and suboptimal semantic alignment. The key challenge lies in balancing change (i.e. precisely editing target regions) and invariance (i.e. preserving unedited parts). To handle such challenge, we propose an Omni-Supervised Positive-Negative Learning framework, named OmniME. Our method integrates three complementary components: (1) retrospective feature supervision that enforces coarse-to-fine consistency across transformer layers,(2) motion preservation mechanism that focuses on subtle variations according to the source-target similarity, and (3) triplet-based semantic alignment that strengthens text-motion correspondence. Together, these components form a unified supervision paradigm that balances change and invariance. Extensive experiments on the MotionFix and STANCE Adjustment datasets demonstrate that OmniME achieves state-of-the-art performance in editing alignment, validating the effectiveness of our unified learning framework. Our source codes and models have been released at: https://github.com/rocket-ycyer/OmniME.git

cs.CV↗
arXiv2026

The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview

This paper provides a review of the NTIRE 2026 challenge on mobile real-world image super-resolution, highlighting the proposed solutions and the resulting outcomes. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through unknown degradations with a x4 scaling factor while ensuring the models remain executable on mobile devices. The objective is to develop effective and efficient network designs or solutions that achieve state-of-the-art real-world image super-resolution performance. The track of the challenge evaluates performance using a weighted combination of image quality assessment (IQA) score and speedup ratios. The competition attracted 108 registrants, with 16 teams achieving a valid score in the final ranking. This collaborative effort advances the performance of mobile real-world image super-resolution while offering an in-depth overview of the latest trends in the field.

cs.CV↗
arXiv2026

GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant

Recent advances in large language models (LLMs) have enabled increasingly capable chatbots. However, most existing systems focus on single-user settings and do not generalize well to multi-user group chat interactions, where agents require more proactive and accurate intervention under complex, evolving contexts. Existing approaches typically rely on LLMs for both intervention reasoning and response generation, leading to high token consumption, limited scalability, and potential privacy risks. To address these challenges, we propose GroupGPT, a token-efficient and privacy-preserving agentic framework for multi-user chat assistant. GroupGPT adopts an edge-cloud model collaboration architecture to decouple intervention timing from response generation, enabling efficient and accurate decision-making while preserving user privacy through on-device processing of sensitive information. The framework also supports multimodal inputs, including memes, images, videos, and voice messages.To support evaluation of timing accuracy and response quality, we further introduce MUIR, a benchmark dataset for multi-user chat assistant intervention reasoning. MUIR contains 2,500 annotated group chat segments with intervention labels and rationales. We evaluate a range of models on MUIR, spanning from open-source to proprietary variants, including both LLMs and their smaller counterparts. Extensive experiments demonstrate that GroupGPT generates accurate and well-timed responses, achieving an average score of 4.72/5.0 in LLM-based evaluation, and is well-received by users across diverse group chat scenarios. Moreover, GroupGPT reduces the token usage by up to 3 times compared to baselines, while providing privacy sanitization of user messages before cloud transmission. Code is available at: https://github.com/Eliot-Shen/GroupGPT .

cs.CL↗
arXiv2026

MASA: Rethinking the Representational Bottleneck in LoRA with Multi-A Shared Adaptation

Low-Rank Adaptation (LoRA) has emerged as a dominant method in Parameter-Efficient Fine-Tuning (PEFT) for large language models, which augments the transformer layer with one down-projection $A$ and one up-projection $B$. However, LoRA's reliance on a single down-projection matrix ($A$) creates a representational bottleneck, as this solitary feature extractor is inherently insufficient for capturing the diverse signals required by complex tasks. This motivates our architectural shift to focus on enriching the feature adaptation to improve the downstream task adaptation ability. We propose MASA (Multi-$A$ Shared Adaptation), an architecture that implements a multi-$A$, single-$B$ structure where the multi-$A$ expert ensemble is asymmetrically shared across layers to ensure parameter efficiency. In MASA, these specialized experts capture diverse features, which are then integrated by a single, layer-specific $B$-matrix. The effectiveness and versatility of our method are validated through a comprehensive suite of experiments spanning multi-domain generalization, single-domain specialization, and multi-task reasoning. For example, on the MMLU benchmark, MASA achieves an average accuracy of 59.62%, outperforming the standard LoRA by 1.08 points (a relative improvement of 1.84%) with comparable learnable parameters of 0.52%.

cs.CL↗
arXiv2024

Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration

Knowledge distillation (KD) is a valuable yet challenging approach that enhances a compact student network by learning from a high-performance but cumbersome teacher model. However, previous KD methods for image restoration overlook the state of the student during the distillation, adopting a fixed solution space that limits the capability of KD. Additionally, relying solely on L1-type loss struggles to leverage the distribution information of images. In this work, we propose a novel dynamic contrastive knowledge distillation (DCKD) framework for image restoration. Specifically, we introduce dynamic contrastive regularization to perceive the student's learning state and dynamically adjust the distilled solution space using contrastive learning. Additionally, we also propose a distribution mapping module to extract and align the pixel-level category distribution of the teacher and student models. Note that the proposed DCKD is a structure-agnostic distillation framework, which can adapt to different backbones and can be combined with methods that optimize upper-bound constraints to further enhance model performance. Extensive experiments demonstrate that DCKD significantly outperforms the state-of-the-art KD methods across various image restoration tasks and backbones.

cs.CV↗
arXiv2024

Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution

State Space Models (SSM), such as Mamba, have shown strong representation ability in modeling long-range dependency with linear complexity, achieving successful applications from high-level to low-level vision tasks. However, SSM's sequential nature necessitates multiple scans in different directions to compensate for the loss of spatial dependency when unfolding the image into a 1D sequence. This multi-direction scanning strategy significantly increases the computation overhead and is unbearable for high-resolution image processing. To address this problem, we propose a novel Hierarchical Mamba network, namely, Hi-Mamba, for image super-resolution (SR). Hi-Mamba consists of two key designs: (1) The Hierarchical Mamba Block (HMB) assembled by a Local SSM (L-SSM) and a Region SSM (R-SSM) both with the single-direction scanning, aggregates multi-scale representations to enhance the context modeling ability. (2) The Direction Alternation Hierarchical Mamba Group (DA-HMG) allocates the isomeric single-direction scanning into cascading HMBs to enrich the spatial relationship modeling. Extensive experiments demonstrate the superiority of Hi-Mamba across five benchmark datasets for efficient SR. For example, Hi-Mamba achieves a significant PSNR improvement of 0.29 dB on Manga109 for $\times3$ SR, compared to the strong lightweight MambaIR.

cs.CV↗
arXiv2024

Selective and Quasi-continuous Switching of Ferroelectric Chern Insulator Device for Neuromorphic Computing

Topologically protected edge state transport in quantum materials is dissipationless and features quantized Hall conductance, and shows great potential in highly fault-tolerant computing technologies. However, it remains elusive about how to develop topological edge state-based computing devices. Recently, exploration and understanding of interfacial ferroelectricity in various van der Waals heterostructure material systems have received widespread attention among the community of materials science and condensed matter physics3-11. Such ferroelectric polarization emergent at the vdW interface can coexist with other quantum states and thus provides an unprecedented opportunity to electrically switch the topological edge states of interest, which is of crucial significance to the fault-tolerant electronic device applications based on the topological edge states. Here, we report the selective and quasi-continuous ferroelectric switching of topological Chern insulator devices and demonstrate its promising application in noise-immune neuromorphic computing. We fabricate this ferroelectric Chern insulator device by encapsulating magic-angle twisted bilayer graphene with doubly-aligned h-BN layers, and observe the coexistence of the interfacial ferroelectricity and the topological Chern insulating states. This ferroelectricity exhibits an anisotropic dependence on the in-plane magnetic field. By using a VBG pulse with delicately controlled amplitude, we realize the nonvolatile switching between any pair of Chern insulating states and achieve 1280 distinguishable nonvolatile resistance levels on a single device. Furthermore, we demonstrate deterministic switching between two arbitrary levels among the record-high number of nonvolatile resistance levels.

cond-mat.mes-hall↗
arXiv2024

Electrical switching of Ising-superconducting nonreciprocity for quantum neuronal transistor

Nonreciprocal quantum transport effect is mainly governed by the symmetry breaking of the material systems and is gaining extensive attention in condensed matter physics. Realizing electrical switching of the polarity of the nonreciprocal transport without external magnetic field is essential to the development of nonreciprocal quantum devices. However, electrical switching of superconducting nonreciprocity remains yet to be achieved. Here, we report the observation of field-free electrical switching of nonreciprocal Ising superconductivity in Fe3GeTe2/NbSe2 van der Waals (vdW) heterostructure. By taking advantage of this electrically switchable superconducting nonreciprocity, we demonstrate a proof-of-concept nonreciprocal quantum neuronal transistor, which allows for implementing the XOR logic gate and faithfully emulating biological functionality of a cortical neuron in the brain. Our work provides a promising pathway to realize field-free and electrically switchable nonreciprocity of quantum transport and demonstrate its potential in exploring neuromorphic quantum devices with both functionality and performance beyond the traditional devices.

cond-mat.mes-hall↗
arXiv2024

A General and Efficient Training for Transformer via Token Expansion

The remarkable performance of Vision Transformers (ViTs) typically requires an extremely large training cost. Existing methods have attempted to accelerate the training of ViTs, yet typically disregard method universality with accuracy dropping. Meanwhile, they break the training consistency of the original transformers, including the consistency of hyper-parameters, architecture, and strategy, which prevents them from being widely applied to different Transformer networks. In this paper, we propose a novel token growth scheme Token Expansion (termed ToE) to achieve consistent training acceleration for ViTs. We introduce an "initialization-expansion-merging" pipeline to maintain the integrity of the intermediate feature distribution of original transformers, preventing the loss of crucial learnable information in the training process. ToE can not only be seamlessly integrated into the training and fine-tuning process of transformers (e.g., DeiT and LV-ViT), but also effective for efficient training frameworks (e.g., EfficientTrain), without twisting the original training hyper-parameters, architecture, and introducing additional training strategies. Extensive experiments demonstrate that ToE achieves about 1.3x faster for the training of ViTs in a lossless manner, or even with performance gains over the full-token training baselines. Code is available at https://github.com/Osilly/TokenExpansion .

cs.LG↗
arXiv2023

Quantum Transport on the Surfaces of Topological Nodal-line Semimetals

Topological nodal-line semimetals are always characterized by the drumhead surface states at the open boundaries. In this paper we first derive an analytical expression for the surface Green's function of a nodal-line semimetal. By making use of this result, we explore the charge and spin transport properties of a metallic chain on the surface of a nodal-line semimetal, as functions of the gate voltage applied on the top of the material. According to the size of the nodal loop, due to the coupling to the surface modes, the charge conductance in the chain is found to show a robust plateau at $e^{2}/h$, or to exhibit multiple valleys at $e^{2}/h$. Correspondingly, the spin polarization of the transmitted current is $100\%$ at the plateau region, or exhibits multiple peaks at nearly $100\%$. This feature can be viewed as a transport signature of the topological nodal-line semimetals.

cond-mat.mes-hall↗
arXiv2023

Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler

Filter pruning simultaneously accelerates the computation and reduces the memory overhead of CNNs, which can be effectively applied to edge devices and cloud services. In this paper, we propose a novel Knowledge-driven Differential Filter Sampler~(KDFS) with Masked Filter Modeling~(MFM) framework for filter pruning, which globally prunes the redundant filters based on the prior knowledge of a pre-trained model in a differential and non-alternative optimization. Specifically, we design a differential sampler with learnable sampling parameters to build a binary mask vector for each layer, determining whether the corresponding filters are redundant. To learn the mask, we introduce masked filter modeling to construct PCA-like knowledge by aligning the intermediate features from the pre-trained teacher model and the outputs of the student decoder taking sampling features as the input. The mask and sampler are directly optimized by the Gumbel-Softmax Straight-Through Gradient Estimator in an end-to-end manner in combination with global pruning constraint, MFM reconstruction error, and dark knowledge. Extensive experiments demonstrate the proposed KDFS's effectiveness in compressing the base models on various datasets. For instance, the pruned ResNet-50 on ImageNet achieves $55.36\%$ computation reduction, and $42.86\%$ parameter reduction, while only dropping $0.35\%$ Top-1 accuracy, significantly outperforming the state-of-the-art methods. The code is available at \url{https://github.com/Osilly/KDFS}.

cs.CV↗
arXiv2021

Connections between the Open-boundary Spectrum and Generalized Brillouin Zone in Non-Hermitian Systems

Periodic-boundary spectrum, open-boundary spectrum, as well as the generalized Brillouin zone (GBZ) are three essential properties of a one-dimensional non-Hermitian system. In this paper we illustrate that the deep connections between them can be revealed by a series of special similar transformations. This viewpoint closely connects the topological geometry of the open-boundary spectrum with the GBZ and provides a new efficient numerical method of calculating them accurately. We further extend these connections to non-Hermitian systems in the symplectic symmetry class. We show that if just the open-boundary features of a non-Hermitian system such as the spectrum and the GBZ, are concerned, the relevant symmetry we should consider is not that of the original system itself, but that of one which has higher symmetry and is related to the original system by a similarity transformation.

cond-mat.other↗
arXiv2021

Rapid COVID-19 Risk Screening by Eye-region Manifestations

It is still nontrivial to develop a new fast COVID-19 screening method with the easier access and lower cost, due to the technical and cost limitations of the current testing methods in the medical resource-poor districts. On the other hand, there are more and more ocular manifestations that have been reported in the COVID-19 patients as growing clinical evidence[1]. This inspired this project. We have conducted the joint clinical research since January 2021 at the ShiJiaZhuang City, Heibei province, China, which approved by the ethics committee of The fifth hospital of ShiJiaZhuang of Hebei Medical University. We undertake several blind tests of COVID-19 patients by Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China. Meantime as an important part of the ongoing globally COVID-19 eye test program by AIMOMICS since February 2020, we propose a new fast screening method of analyzing the eye-region images, captured by common CCD and CMOS cameras. This could reliably make a rapid risk screening of COVID-19 with the sustainable stable high performance in different countries and races. Our model for COVID-19 rapid prescreening have the merits of the lower cost, fully self-performed, non-invasive, importantly real-time, and thus enables the continuous health surveillance. We further implement it as the open accessible APIs, and provide public service to the world. Our pilot experiments show that our model is ready to be usable to all kinds of surveillance scenarios, such as infrared temperature measurement device at airports and stations, or directly pushing to the target people groups smartphones as a packaged application.

eess.IV↗