Search arXiv⌕ Search

arXiv subjects

Wei Li

Publications and source records attributed to Wei Li.

At least 271 records · Page 15Linked to original sources
arXiv2026

Direct Visualization of Room-temperature Stair-stepped Quantum Spin Hall States in Bi4Br4

Topological insulators host exotic quantum phenomena such as the quantum spin Hall (QSH) effect, which enables dissipationless one-dimensional edge conduction. Realizing such states at room temperature and on a macroscopic scale is essential for energy-efficient electronics and quantum technologies, yet remains a fundamental challenge due to material limitations. Here, using microwave impedance microscopy, we directly visualize robust QSH states persisting up to 300 K in α-Bi4Br4 nanowires. This stability and scalability are enabled by a stair stepped stacking configuration, a multilayer geometry in which QSH edge states from individual layers remain spatially decoupled. This configuration circumvents the stringent alignment and layer number constraints of previous proposals, allowing robust stair-stepped QSH (SS-QSH) conduction in structures several micrometers long and hundreds of nanometers high. Magnetic field and temperature dependent measurements confirm their intrinsic topological nature. Crucially, the SS-QSH and bulk signals scale with nanowire height, verifying the stair stepped origin. Our results are also successfully reproduced by finite-element analysis simulations. This work establishes α Bi4Br4 as a practical platform for high temperature topological electronics and demonstrates a generalizable stacking strategy for designing scalable QSH systems.

cond-mat.mes-hall↗
arXiv2026

Diverse Skill Discovery for Quadruped Robots via Unsupervised Learning

Reinforcement learning necessitates meticulous reward shaping by specialists to elicit target behaviors, while imitation learning relies on costly task-specific data. In contrast, unsupervised skill discovery can potentially reduce these burdens by learning a diverse repertoire of useful skills driven by intrinsic motivation. However, existing methods exhibit two key limitations: they typically rely on a single policy to master a versatile repertoire of behaviors without modeling the shared structure or distinctions among them, which results in low learning efficiency; moreover, they are susceptible to reward hacking, where the reward signal increases and converges rapidly while the learned skills display insufficient actual diversity. In this work, we introduce an Orthogonal Mixture-of-Experts (OMoE) architecture that prevents diverse behaviors from collapsing into overlapping representations, enabling a single policy to master a wide spectrum of locomotion skills. In addition, we design a multi-discriminator framework in which different discriminators operate on distinct observation spaces, effectively mitigating reward hacking. We evaluated our method on the 12-DOF Unitree A1 quadruped robot, demonstrating a diverse set of locomotion skills. Our experiments demonstrate that the proposed framework boosts training efficiency and yields an 18.3\% expansion in state-space coverage compared to the baseline.

cs.RO↗
arXiv2026

PlugSI: Plug-and-Play Test-Time Graph Adaptation for Spatial Interpolation

With the rapid advancement of IoT and edge computing, sensor networks have become indispensable, driving the need for large-scale sensor deployment. However, the high deployment cost hinders their scalability. To tackle the issues, Spatial Interpolation (SI) introduces virtual sensors to infer readings from observed sensors, leveraging graph structure. However, current graph-based SI methods rely on pre-trained models, lack adaptation to larger and unseen graphs at test-time, and overlook test data utilization. To address these issues, we propose PlugSI, a plug-and-play framework that refines test-time graph through two key innovations. First, we design an Unknown Topology Adapter (UTA) that adapts to the new graph structure of each small-batch at test-time, enhancing the generalization of SI pre-trained models. Second, we introduce a Temporal Balance Adapter (TBA) that maintains a stable historical consensus to guide UTA adaptation and prevent drifting caused by noise in the current batch. Empirically, extensive experiments demonstrate PlugSI can be seamlessly integrated into existing graph-based SI methods and provide significant improvement (e.g., a 10.81% reduction in MAE).

cs.LG↗
arXiv2026

Hydra-Nav: Object Navigation via Adaptive Dual-Process Reasoning

While large vision-language models (VLMs) show promise for object goal navigation, current methods still struggle with low success rates and inefficient localization of unseen objects--failures primarily attributed to weak temporal-spatial reasoning. Meanwhile, recent attempts to inject reasoning into VLM-based agents improve success rates but incur substantial computational overhead. To address both the ineffectiveness and inefficiency of existing approaches, we introduce Hydra-Nav, a unified VLM architecture that adaptively switches between a deliberative slow system for analyzing exploration history and formulating high-level plans, and a reactive fast system for efficient execution. We train Hydra-Nav through a three-stage curriculum: (i) spatial-action alignment to strengthen trajectory planning, (ii) memory-reasoning integration to enhance temporal-spatial reasoning over long-horizon exploration, and (iii) iterative rejection fine-tuning to enable selective reasoning at critical decision points. Extensive experiments demonstrate that Hydra-Nav achieves state-of-the-art performance on the HM3D, MP3D, and OVON benchmarks, outperforming the second-best methods by 11.1%, 17.4%, and 21.2%, respectively. Furthermore, we introduce SOT (Success weighted by Operation Time), a new metric to measure search efficiency across VLMs with varying reasoning intensity. Results show that adaptive reasoning significantly enhances search efficiency over fixed-frequency baselines.

cs.RO↗
arXiv2026

Giant Magnetocaloric Effect in a High-Spin Shastry-Sutherland Dipolar Magnet

The Shastry-Sutherland lattice is a prototypical frustrated quantum magnet. It is notable for its exactly solvable dimer-singlet ground state and hosts a wealth of magnetic phenomena under external fields. Here, this work investigates the high-spin (S = 7/2) Eu-based magnet Eu2MgSi2O7 (EMSO) using low-temperature magnetothermal measurements and Monte Carlo simulations, revealing a giant magnetocaloric effect (MCE) in this Shastry-Sutherland compound. The entropy change peak value is found to be 55.0 J kg-1 K-1 under a field change of B = 0-4 T, approximately 1.5 times larger than the commercial Gd3Ga5O12 (GGG). Adiabatic demagnetization refrigeration achieves a lowest temperature of 151 mK, deeply into the sub-Kelvin regime. Furthermore, a distinctive cooling effect persists below about 1 T, a characteristic absent for conventional magnetic coolants. A dipolar Shastry-Sutherland model is introduced as a minimal model to describe this system; in particular, the experimentally revealed 1/3 magnetization pseudo-plateau can be ascribed to the presence of dipolar couplings between Eu2+ ions, further stabilized by the thermal fluctuations, explaining the persistent cooling effect. This work establishes EMSO as a novel platform for exploring the dipolar Shastry-Sutherland system and for sub-Kelvin adiabatic demagnetization refrigeration.

cond-mat.mtrl-sci↗
arXiv2026

Semiparametric Efficient Fusion of Individual Data and Summary Statistics

Suppose we have individual data from an internal study and various summary statistics from relevant external studies. External summary statistics have the potential to improve statistical inference for the internal population; however, it may lead to efficiency loss or bias if not used properly. We study the fusion of individual data and summary statistics in a semiparametric framework to investigate the efficient use of external summary statistics. Under a weak transportability assumption, we establish the semiparametric efficiency bound for estimating a general functional of the internal data distribution, which is no larger than that using only internal data and underpins the potential efficiency gain of integrating individual data and summary statistics. We propose a data-fused efficient estimator that achieves this efficiency bound. In addition, an adaptive fusion estimator is proposed to eliminate the bias of the original data-fused estimator when the transportability assumption fails. We establish the asymptotic oracle property of the adaptive fusion estimator. Simulations and application to a Helicobacter pylori infection dataset demonstrate the promising numerical performance of the proposed method.

stat.ME↗
arXiv2026

video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM

Long-duration streaming video understanding is fundamental for future AI agents, yet remains limited by ineffective long-term memory. We introduce video-SALMONN S, a memory-enhanced streaming audio-visual large language model that processes over 3-hour videos at 1 FPS and 360p resolution, outperforming strong non-streaming models under the same memory budget. In addition to token merging or downsampling, video-SALMONN S is the first to employ test-time training (TTT) as a streaming memory mechanism for video understanding. TTT continuously transforms short-term multimodal representations into long-term memory embedded in model parameters. To improve long-range dependency modeling and memory capacity, we propose (i) a TTT_MEM layer with an additional long-span prediction objective, (ii) a two-stage training scheme, and (iii) a modality-aware memory reader. We further introduce the Episodic Learning from Video Memory (ELViM) benchmark, simulating agent-like scenarios where models must learn from videos observed hours earlier. video-SALMONN S consistently outperforms both streaming and non-streaming baselines by 3-7% on long video benchmarks. Notably, video-SALMONN S achieves a 15% absolute accuracy improvement over strong non-streaming models on ELViM, demonstrating strong learning abilities from video memory.

cs.CV↗
arXiv2026

Categories of Line Defects and Cohomological Hall Algebras

Any four-dimensional Supersymmetric Quantum Field Theory with eight supercharges can be associated to a monoidal category of BPS line defects. Any Coulomb vacuum of such a theory can be conjecturally associated to an ``algebra of BPS particles'', exemplified by certain Cohomological Hall Algebras. We conjecture the existence of a monoidal functor from the category of line defects to a certain category of bimodules for the BPS Algebra in any Coulomb vacuum. We describe images of simple objects under the conjectural functor and study their monoidal structure in examples. We conjecture that the functor may be an equivalence of dg-categories and test the conjecture at the level of the equivariant Witten indices of the spaces of morphisms.

hep-th↗
arXiv2026

RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restoration

We present the RAW domain diffusion model (RDDM), an end-to-end diffusion model that restores photo-realistic images directly from the sensor RAW data. While recent sRGB-domain diffusion methods achieve impressive results, they are caught in a dilemma between high fidelity and image generation. These models process lossy sRGB inputs and neglect the accessibility of the sensor RAW images in many scenarios, e.g., in image and video capturing in edge devices, resulting in sub-optimal performance. RDDM obviates this limitation by directly restoring images in the RAW domain, replacing the conventional two-stage image signal processing (ISP)->Image Restoration (IR) pipeline. However, a simple adaptation of pre-trained diffusion models to the RAW domain confronts many challenges. To this end, we propose: (1) a RAW-domain VAE (RVAE), encoding sensor RAW and decoding it into an enhanced linear domain image, to solve the out-of-distribution (OOD) issues between the different domain distributions; (2) a configurable multi-bayer (CMB) LoRA module, adapting diverse RAW Bayer patterns such as RGGB, BGGR, etc. To compensate for the deficiency in the dataset, we develop a scalable data synthesis pipeline synthesizing RAW LQ-HQ pairs from existing sRGB datasets for large-scale training. Extensive experiments demonstrate RDDM's superiority over state-of-the-art sRGB diffusion methods, yielding higher fidelity results with fewer artifacts. Codes will be publicly available at https://github.com/YanCHEN-fr/RDDM.

eess.IV↗
arXiv2026

Fractional Chern Insulator and Quantum Anomalous Hall Crystal in Twisted MoTe$_2$

Recent experimental advances have uncovered fractional Chern insulator (FCI) states in twisted MoTe$_2$ (tMoTe$_2$) systems under zero magnetic field. Understanding the interaction effects on topological phases within realistic model presents a significant theoretical challenge. Here, we construct a moiré superlattice model tailored for tMoTe$_2$ and conduct investigations using state-of-the-art tensor-network methods. Our ground-state calculations reveal a rich variety of interaction-driven and filling-dependent topological phases, including FCIs, Chern insulators, and generalized Wigner crystals, which are revealed in recent experiments. For FCI state, dynamical simulations uncover a single-particle excitation continuum with a finite charge gap, reflecting the fractionalized charge excitations. Finite-temperature calculations further determine characteristic charge activation and ferromagnetic transition temperatures, reconciling existing experimental discrepancies. Furthermore, using this realistic lattice model, we predict the presence of quantum anomalous Hall crystals exhibiting integer Hall conductivity at fractional fillings in tMoTe$_2$. By integrating ground-state, finite-temperature, and dynamical analyses, our work establishes a comprehensive framework for understanding correlated topological phases in tMoTe$_2$ and related moiré systems.

cond-mat.str-el↗
arXiv2026

ScatterFusion: A Hierarchical Scattering Transform Framework for Enhanced Time Series Forecasting

Time series forecasting presents significant challenges due to the complex temporal dependencies at multiple time scales. This paper introduces ScatterFusion, a novel framework that synergistically integrates scattering transforms with hierarchical attention mechanisms for robust time series forecasting. Our approach comprises four key components: (1) a Hierarchical Scattering Transform Module (HSTM) that extracts multi-scale invariant features capturing both local and global patterns; (2) a Scale-Adaptive Feature Enhancement (SAFE) module that dynamically adjusts feature importance across different scales; (3) a Multi-Resolution Temporal Attention (MRTA) mechanism that learns dependencies at varying time horizons; and (4) a Trend-Seasonal-Residual (TSR) decomposition-guided structure-aware loss function. Extensive experiments on seven benchmark datasets demonstrate that ScatterFusion outperforms other common methods, achieving significant reductions in error metrics across various prediction horizons.

cs.LG↗
arXiv2026

AWGformer: Adaptive Wavelet-Guided Transformer for Multi-Resolution Time Series Forecasting

Time series forecasting requires capturing patterns across multiple temporal scales while maintaining computational efficiency. This paper introduces AWGformer, a novel architecture that integrates adaptive wavelet decomposition with cross-scale attention mechanisms for enhanced multi-variate time series prediction. Our approach comprises: (1) an Adaptive Wavelet Decomposition Module (AWDM) that dynamically selects optimal wavelet bases and decomposition levels based on signal characteristics; (2) a Cross-Scale Feature Fusion (CSFF) mechanism that captures interactions between different frequency bands through learnable coupling matrices; (3) a Frequency-Aware Multi-Head Attention (FAMA) module that weights attention heads according to their frequency selectivity; (4) a Hierarchical Prediction Network (HPN) that generates forecasts at multiple resolutions before reconstruction. Extensive experiments on benchmark datasets demonstrate that AWGformer achieves significant average improvements over state-of-the-art methods, with particular effectiveness on multi-scale and non-stationary time series. Theoretical analysis provides convergence guarantees and establishes the connection between our wavelet-guided attention and classical signal processing principles.

cs.LG↗
arXiv2026

Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM Reasoning

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical deduction. Traditional Reinforcement Learning (RL) attempts to mitigate this by introducing a ``think-before-speak'' paradigm. However, applying RL directly in high-dimensional, discrete token spaces faces three inherent challenges: sample-inefficient rollouts, high gradient estimation variance, and the risk of catastrophic forgetting. To fundamentally address these structural bottlenecks, we propose \textbf{DeepLatent Reasoning (DLR)}, a latent-space bidirectional contrastive reinforcement learning framework. This framework shifts the trial-and-error cost from expensive token-level full sequence generation to the continuous latent manifold. Specifically, we introduce a lightweight assistant model to efficiently sample $K$ reasoning chain encodings within the latent space. These encodings are filtered via a dual reward mechanism based on correctness and formatting; only high-value latent trajectories are fed into a \textbf{frozen main model} for single-pass decoding. To maximize reasoning diversity while maintaining coherence, we design a contrastive learning objective to enable directed exploration within the latent space. Since the main model parameters remain frozen during optimization, this method mathematically eliminates catastrophic forgetting. Experiments demonstrate that under comparable GPU computational budgets, DLR achieves more stable training convergence, supports longer-horizon reasoning chains, and facilitates the sustainable accumulation of reasoning capabilities, providing a viable path toward reliable and scalable reinforcement learning for LLMs.

cs.LG↗
arXiv2026

$d$-wave FFLO state and charge-2e supersolidity in the $t$-$t'$-$J$ model under Zeeman fields

Unconventional superconductivity under strong Zeeman fields--particularly beyond the Pauli paramagnetic limit--remains a central challenge in condensed matter physics. The exotic Fulde-Ferrell-Larkin-Ovchinnikov (FFLO) state, in particular, remains in need of definitive study within fundamental electronic models. Here we employ state-of-the-art finite-temperature and ground-state tensor network approaches to systematically explore the superconducting (SC) phase diagram of the $t$-$t'$-$J$ model subjected to Zeeman fields. We find that zero-momentum $d$-wave superconductivity persists until the spin gap closes, coexisting with charge density waves. A novel $d$-wave FFLO phase emerges under a higher Zeeman field even above the Pauli limit, concomitant with a field-enhanced spin density waves. We identify these phases, characterized by the simultaneous presence of pairing condensate and density wave orders, as charge-2e supersolids. Analysis of Matsubara Green's function reveals that the FFLO pairing momentum is locked to the underlying Fermi surface. Our results provide microscopic insights into field-induced unconventional pairing mechanisms and reveal the long-sought FFLO state in a fundamental correlated electron model, offering a promising route for its realization in ultracold atom optical lattice.

cond-mat.str-el↗
arXiv2026

Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Model

Recent advances in multimodal models have demonstrated impressive capabilities in unified image generation and editing. However, many prominent open-source models prioritize scaling model parameters over optimizing training strategies, limiting their efficiency and performance. In this work, we present UniPic2-SD3.5M-Kontext, a 2B-parameter DiT model based on SD3.5-Medium, which achieves state-of-the-art image generation and editing while extending seamlessly into a unified multimodal framework. Our approach begins with architectural modifications to SD3.5-Medium and large-scale pre-training on high-quality data, enabling joint text-to-image generation and editing capabilities. To enhance instruction following and editing consistency, we propose a novel Progressive Dual-Task Reinforcement strategy (PDTR), which effectively strengthens both tasks in a staged manner. We empirically validate that the reinforcement phases for different tasks are mutually beneficial and do not induce negative interference. After pre-training and reinforcement strategies, UniPic2-SD3.5M-Kontext demonstrates stronger image generation and editing capabilities than models with significantly larger generation parameters-including BAGEL (7B) and Flux-Kontext (12B). Furthermore, following the MetaQuery, we connect the UniPic2-SD3.5M-Kontext and Qwen2.5-VL-7B via a connector and perform joint training to launch a unified multimodal model UniPic2-Metaquery. UniPic2-Metaquery integrates understanding, generation, and editing, achieving top-tier performance across diverse tasks with a simple and scalable training paradigm. This consistently validates the effectiveness and generalizability of our proposed training paradigm, which we formalize as Skywork UniPic 2.0.

cs.CV↗
arXiv2026

IIR-VLM: In-Context Instance-level Recognition for Large Vision-Language Models

Instance-level recognition (ILR) concerns distinguishing individual instances from one another, with person re-identification as a prominent example. Despite the impressive visual perception capabilities of modern VLMs, we find their performance on ILR unsatisfactory, often dramatically underperforming domain-specific ILR models. This limitation hinders many practical application of VLMs, e.g. where recognizing familiar people and objects is crucial for effective visual understanding. Existing solutions typically learn to recognize instances one at a time using instance-specific datasets, which not only incur substantial data collection and training costs but also struggle with fine-grained discrimination. In this work, we propose IIR-VLM, a VLM enhanced for In-context Instance-level Recognition. We integrate pre-trained ILR expert models as auxiliary visual encoders to provide specialized features for learning diverse instances, which enables VLMs to learn new instances in-context in a one-shot manner. Further, IIR-VLM leverages this knowledge for instance-aware visual understanding. We validate IIR-VLM's efficacy on existing instance personalization benchmarks. Finally, we demonstrate its superior ILR performance on a challenging new benchmark, which assesses ILR capabilities across varying difficulty and diverse categories, with person, face, pet and general objects as the instances at task.

cs.CV↗
arXiv2026

Assessing Interactive Causes of an Occurred Outcome Due to Two Binary Exposures

In contrast to evaluating treatment effects, causal attribution analysis focuses on identifying the key factors responsible for an observed outcome. For two binary exposure variables and a binary outcome variable, researchers need to assess not only the likelihood that an observed outcome was caused by a particular exposure, but also the likelihood that it resulted from the interaction between the two exposures. For example, in the case of a male worker who smoked, was exposed to asbestos, and developed lung cancer, researchers aim to explore whether the cancer resulted from smoking, asbestos exposure, or their interaction. Even in randomized controlled trials, widely regarded as the gold standard for causal inference, identifying and evaluating retrospective causal interactions between two exposures remains challenging. In this paper, we define posterior probabilities to characterize the interactive causes of an observed outcome. We establish the identifiability of posterior probabilities by using a secondary outcome variable that may appear after the primary outcome. We apply the proposed method to the classic case of smoking and asbestos exposure. Our results indicate that for lung cancer patients who smoked and were exposed to asbestos, the disease is primarily attributable to the synergistic effect between smoking and asbestos exposure.

stat.AP↗
arXiv2026

ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding

Recent Omni-multimodal Large Language Models show promise in unified audio, vision, and text modeling. However, streaming audio-video understanding remains challenging, as existing approaches suffer from disjointed capabilities: they typically exhibit incomplete modality support or lack autonomous proactive monitoring. To address this, we present ROMA, a real-time omni-multimodal assistant for unified reactive and proactive interaction. ROMA processes continuous inputs as synchronized multimodal units, aligning dense audio with discrete video frames to handle granularity mismatches. For online decision-making, we introduce a lightweight speak head that decouples response initiation from generation to ensure precise triggering without task conflict. We train ROMA with a curated streaming dataset and a two-stage curriculum that progressively optimizes for streaming format adaptation and proactive responsiveness. To standardize the fragmented evaluation landscape, we reorganize diverse benchmarks into a unified suite covering both proactive (alert, narration) and reactive (QA) settings. Extensive experiments across 12 benchmarks demonstrate ROMA achieves state-of-the-art performance on proactive tasks while competitive in reactive settings, validating its robustness in unified real-time omni-multimodal understanding.

cs.CV↗