arXiv subjects

Wei Ji

Publications and source records attributed to Wei Ji.

At least 55 records · Page 3Linked to original sources

arXiv2026

SAM3-I: Segment Anything with Instructions

Segment Anything Model 3 (SAM3) advances open-vocabulary segmentation through promptable concept segmentation, enabling users to segment all instances associated with a given concept using short noun-phrase (NP) prompts. While effective for concept-level grounding, real-world interactions often involve far richer natural-language instructions that combine attributes, relations, actions, states, or implicit reasoning. Currently, SAM3 relies on external multi-modal agents to convert complex instructions into NPs and conducts iterative mask filtering, leading to coarse representations and limited instance specificity. In this work, we present SAM3-I, an instruction-following extension of the SAM family that unifies concept-level grounding and instruction-level reasoning within a single segmentation framework. Built upon SAM3, SAM3-I introduces an instruction-aware cascaded adaptation mechanism with dedicated alignment losses that progressively aligns expressive instruction semantics with SAM3's vision-language representations, enabling direct interpretation of natural-language instructions while preserving its strong concept recall ability. To enable instruction-following learning, we introduce HMPL-Instruct, a large-scale instruction-centric dataset that systematically covers hierarchical instruction semantics and diverse target granularities. Experiments demonstrate that SAM3-I achieves appealing performance across referring and reasoning-based segmentation, showing that SAM3 can be effectively extended to follow complex natural-language instructions without sacrificing its original concept-driven strengths. Code and dataset are available at https://github.com/debby-0527/SAM3-I.

cs.CV↗

arXiv2026

Potential of constraining the Fifth Force Using the Earth as a Spin and Mass Source from space

We explore the potential of conducting an experiment in a low Earth orbit spacecraft and using the Earth as a spin and mass source to constrain beyond-the-standard-model (BSM) long-range spin- and velocity-dependent interactions, which are mediated by the exchange of an ultralight $\left(m_{Z^{\prime}}<10^{-10}\text{eV}\right)$ or massless intermediate vector boson. The high speed of the low Earth orbit spacecraft can enhance the sensitivity to velocity-dependent interactions. The periodicity enables efficient extraction of signals from background noise, thereby improving the experiment's accuracy. Combining these advantages, we demonstrate theoretically that the novel Spacecraft-Earth model can improve existing bounds on these exotic interactions by up to three orders of magnitude, using the China Space Station (CSS) as a representative low-Earth-orbit carrier. Such a model, if successfully implemented, may provide an innovative strategy for detecting ultralight dark matter and yield tighter constraints on certain coupling constants of exotic interactions.

hep-ph↗

arXiv2026

Selective Noise Suppression and Discriminative Mutual Interaction for Robust Audio-Visual Segmentation

The ability to capture and segment sounding objects in dynamic visual scenes is crucial for the development of Audio-Visual Segmentation (AVS) tasks. While significant progress has been made in this area, the interaction between audio and visual modalities still requires further exploration. In this work, we aim to answer the following questions: How can a model effectively suppress audio noise while enhancing relevant audio information? How can we achieve discriminative interaction between the audio and visual modalities? To this end, we propose SDAVS, equipped with the Selective Noise-Resilient Processor (SNRP) module and the Discriminative Audio-Visual Mutual Fusion (DAMF) strategy. The proposed SNRP mitigates audio noise interference by selectively emphasizing relevant auditory cues, while DAMF ensures more consistent audio-visual representations. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on benchmark AVS datasets, especially in multi-source and complex scenes. \textit{The code and model are available at https://github.com/happylife-pk/SDAVS}.

cs.CV↗

arXiv2026

Toward Real-Time Surgical Scene Segmentation via a Spike-Driven Video Transformer with Spike-Informed Pretraining

Modern surgical systems increasingly rely on intelligent scene understanding to improve intra-operative safety and situational awareness, with surgical scene segmentation playing a fundamental role in fine-grained surgical perception. Although recent ANN models, especially large foundation models, have achieved impressive accuracy, their high computational and energy demands often hinder deployment in resource-constrained operative environments. To address this challenge, we explore SNN as a highly efficient paradigm. However, its performance in surgical scene segmentation remains constrained by sparse spike representations and limited annotated surgical data. We therefore propose SpikeSurgSeg, the first spike-driven video Transformer for surgical scene segmentation. It preserves the real-time and energy-efficient advantages of SNN, while achieving competitive performance against most ANN models in data-scarce surgical scenarios. Specifically, we introudce a spike-informed pretraining strategy based on MAE, where mask generation is guided by spike firing activity to better align with sparse spike representations, together with a layer-wise tube masking scheme that reduces information leakage and encourages contextual reasoning. To further strengthen semantic representation, we introduce multi-spectral knowledge distillation, which aligns teacher ANN and student SNN features in the frequency domain, where the mismatch between continuous activation patterns and spike-driven temporal representations can be effectively mitigated. Built on the pretrained SNN encoder, we further design a lightweight spike-driven segmentation head. Extensive experiments on EndoVis18 and our in-house SurgBleed dataset show that SpikeSurgSeg achieves mIoU comparable to SOTA ANN models while reducing inference latency by at least 8x. Notably, it delivers over 20x speedup relative to most foundation models.

cs.CV↗

arXiv2026

TexEditor: Structure-Preserving Text-Driven Texture Editing

Text-guided texture editing aims to modify object appearance while preserving the underlying geometric structure. However, our empirical analysis reveals that even SOTA editing models frequently struggle to maintain structural consistency during texture editing, despite the intended changes being purely appearance-related. Motivated by this observation, we jointly enhance structure preservation from both data and training perspectives, and build TexEditor, a dedicated texture editing model based on Qwen-Image-Edit-2509. Firstly, we construct TexBlender, a high-quality SFT dataset generated with Blender, which provides strong structural priors for a cold start. Sec- ondly, we introduce StructureNFT, a RL-based approach that integrates structure-preserving losses to transfer the structural priors learned during SFT to real-world scenes. Moreover, due to the limited realism and evaluation coverage of existing benchmarks, we introduce TexBench, a general-purpose real-world benchmark for text-guided texture editing. Extensive experiments on existing Blender-based texture benchmarks and our TexBench show that TexEditor consistently outperforms strong baselines such as Nano Banana Pro. In addition, we assess TexEditor on the general purpose benchmark ImgEdit to validate its generalization. Our code and data are available at https://github.com/KlingAIResearch/TexEditor.

cs.CV↗

arXiv2026

UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark

In real-world multimodal applications, systems usually need to comprehend arbitrarily combined and interleaved multimodal inputs from users, while also generating outputs in any interleaved multimedia form. This capability defines the goal of any-to-any interleaved multimodal learning under a unified paradigm of understanding and generation, posing new challenges and opportunities for advancing Multimodal Large Language Models (MLLMs). To foster and benchmark this capability, this paper introduces the UniM benchmark, the first Unified Any-to-Any Interleaved Multimodal dataset. UniM contains 31K high-quality instances across 30 domains and 7 representative modalities: text, image, audio, video, document, code, and 3D, each requiring multiple intertwined reasoning and generation capabilities. We further introduce the UniM Evaluation Suite, which assesses models along three dimensions: Semantic Correctness & Generation Quality, Response Structure Integrity, and Interleaved Coherence. In addition, we propose UniMA, an agentic baseline model equipped with traceable reasoning for structured interleaved generation. Comprehensive experiments demonstrate the difficulty of UniM and highlight key challenges and directions for advancing unified any-to-any multimodal intelligence. The project page is https://any2any-mllm.github.io/unim.

cs.CV↗

arXiv2026

Surrogate Modeling for Neutron Transport: A Neural Operator Approach

This work introduces a neural operator based surrogate modeling framework for neutron transport computation. Two architectures, the Deep Operator Network (DeepONet) and the Fourier Neural Operator (FNO), were trained for fixed source problems to learn the mapping from anisotropic neutron sources, Q(x,μ), to the corresponding angular fluxes, ψ(x,μ), in a one-dimensional slab geometry. Three distinct models were trained for each neural operator, corresponding to different scattering ratios (c = 0.1, 0.5, & 1.0), providing insight into their performance across distinct transport regimes (absorption-dominated, moderate, and scattering-dominated). The models were subsequently evaluated on a wide range of previously unseen source configurations, demonstrating that FNO generally achieves higher predictive accuracy, while DeepONet offers greater computational efficiency. Both models offered significant speedups that become increasingly pronounced as the scattering ratio increases, requiring <0.3% of the runtime of a conventional S_N solver. The surrogate models were further incorporated into the S_N k-eigenvalue solver, replacing the computationally intensive transport sweep loop with a single forward pass. Across varying fission cross sections and spatial-angular grids, both neural operator solvers reproduced reference eigenvalues with deviations up to 135 pcm for DeepONet and 112 pcm for FNO, while reducing runtime to <0.1% of that of the S_N solver on relatively fine grids. These results demonstrate the strong potential of neural operator frameworks as accurate, efficient, and generalizable surrogates for neutron transport, paving the way for real-time digital twin applications and repeated evaluations, such as in design optimization.

physics.comp-ph↗

arXiv2026

Cavity, lumped-circuit, and spin-based detection of axion dark matter: differences and similarities

Axions and axion-like particles are compelling candidates for ultralight bosonic dark matter, forming coherent oscillating fields that can be probed by experiments known as haloscopes. A broad range of haloscope concepts has been developed, including resonant cavity haloscopes, lumped-element circuit detectors, and spin-based experiments, each sensitive to different axion couplings and mass ranges. Rather than attempting an exhaustive survey of all existing approaches, this comparative review provides a unified framework for the major haloscope classes, establishing a common language for the descriptions of signal generation, noise properties, data analysis, and scanning strategies. Key properties of ultralight bosonic dark matter relevant for detection are summarized first, including coherence time, spectral linewidth, and stochasticity under the standard halo model. The discussion then compares cavity, Earth-scale, lumped-element, and spin haloscopes, focusing on expected signal shapes, dominant noise sources, and statistical frameworks for axion searches. Particular emphasis is placed on consistent definitions of signal-to-noise ratio and on how detector bandwidth, axion coherence, and noise characteristics determine optimal scan strategies. By systematically comparing operating principles and performance metrics across these detector families, this framework clarifies shared concepts as well as the essential differences that govern sensitivity in different mass and coupling regimes. The resulting perspective synthesizes current search methodologies and offers guidance for optimizing future haloscope experiments.

hep-ph↗

arXiv2026

Interp3D: Correspondence-aware Interpolation for Generative Textured 3D Morphing

Textured 3D morphing seeks to generate smooth and plausible transitions between two 3D assets, preserving both structural coherence and fine-grained appearance. This ability is crucial not only for advancing 3D generation research but also for practical applications in animation, editing, and digital content creation. Existing approaches either operate directly on geometry, limiting them to shape-only morphing while neglecting textures, or extend 2D interpolation strategies into 3D, which often causes semantic ambiguity, structural misalignment, and texture blurring. These challenges underscore the necessity to jointly preserve geometric consistency, texture alignment, and robustness throughout the transition process. To address this, we propose Interp3D, a novel training-free framework for textured 3D morphing. It harnesses generative priors and adopts a progressive alignment principle to ensure both geometric fidelity and texture coherence. Starting from semantically aligned interpolation in condition space, Interp3D enforces structural consistency via SLAT (Structured Latent)-guided structure interpolation, and finally transfers appearance details through fine-grained texture fusion. For comprehensive evaluations, we construct a dedicated dataset, Interp3DData, with graded difficulty levels and assess generation results from fidelity, transition smoothness, and plausibility. Both quantitative metrics and human studies demonstrate the significant advantages of our proposed approach over previous methods. Source code is available at https://github.com/xiaolul2/Interp3D.

cs.CV↗

arXiv2026

STEP3-VL-10B Technical Report

We present STEP3-VL-10B, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. STEP3-VL-10B is realized through two strategic shifts: first, a unified, fully unfrozen pre-training strategy on 1.2T multimodal tokens that integrates a language-aligned Perception Encoder with a Qwen3-8B decoder to establish intrinsic vision-language synergy; and second, a scaled post-training pipeline featuring over 1k iterations of reinforcement learning. Crucially, we implement Parallel Coordinated Reasoning (PaCoRe) to scale test-time compute, allocating resources to scalable perceptual reasoning that explores and synthesizes diverse visual hypotheses. Consequently, despite its compact 10B footprint, STEP3-VL-10B rivals or surpasses models 10$\times$-20$\times$ larger (e.g., GLM-4.6V-106B, Qwen3-VL-235B) and top-tier proprietary flagships like Gemini 2.5 Pro and Seed-1.5-VL. Delivering best-in-class performance, it records 92.2% on MMBench and 80.11% on MMMU, while excelling in complex reasoning with 94.43% on AIME2025 and 75.95% on MathVision. We release the full model suite to provide the community with a powerful, efficient, and reproducible baseline.

cs.CV↗

arXiv2026

Intertwined atomic-nanoscale-microscale structures via intralayer anisotropic Fe-chains in the layered ferromagnet FePd2Te2

Controlling mesoscale and nanoscale material structures and properties through self-organized atomic behavior is essential for atomic-scale manufacturing. However, direct and visual studies on the cross-scale effects of such atomic self-organization on mesoscopic structures remain scarce. Here, we report the intertwined atomic-nanoscale-mesoscale structures via the intralayer Fe-chains in the sandwich-like layered FePd2Te2 crystal by scanning tunneling microscopy (STM) and atomic force microscopy (AFM). The hierarchical orthogonal corrugated morphologies are directly revealed and attributed to its chain-orientation-determined twinning-domain effect. Both Fe-chains of middle-sublayer and two kinds of Te atoms of top-sublayer are further atomically resolved at the sub-Å level, indicating the critical effects of Pd-atoms/voids on the intra-layer anisotropic Fe-chains and the interlayer structural alignment. The thermal-induced and strain-related structural transitions of surface layer are further investigated and discussed based on the proposed filling model of Pd-voids by the intralayer Pd-atoms. Our work not only provides deep understanding of this exotic layered magnetic material, and will inspire more perspectives for tailoring its anisotropic atomic-to-mesoscale structures and properties.

cond-mat.mtrl-sci↗

arXiv2025

Kinetically accessible 1D magnetic chains of transition-metal chalcogenides and halides on van der Waals surfaces

One-dimensional (1D) chains offer unique opportunities for nanoelectronics and spintronics, yet their experimental realization remains challenging because 1D motifs are often thermodynamically disfavored relative to higher-dimensional phases. Here we present a high-throughput first-principles exploration of 1D single-atomic transition-metal chalcogenide and halide chains, screening 6,832 candidates constructed from binary combinations of 28 metals and 8 non-metals. To assess kinetic accessibility, we compare the formation energetics of 1D chains with competing two-dimensional polymorphs at the nucleation stage across relevant chemical-potential windows, using nucleation-stage thermodynamic selectivity as a proxy. This workflow identifies 183 kinetically accessible 1D chains. Interpretable machine-learning analysis reveals two simple stability descriptors as key drivers of 1D stabilization. The accessible chains exhibit diverse magnetic configurations with different magnetic characters. We further uncover their pronounced magnetoelastic couplings, exemplified by CrTe with giant magnetostriction reaching 5.93%. Finally, we show that selected metallic ferromagnetic chains retain robust edge magnetism on superconducting substrates, laying the groundwork for proximity-induced topological superconductivity and Majorana zero modes.

cond-mat.mtrl-sci↗

arXiv2025

Step-DeepResearch Technical Report

As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands for open-ended research, which requires robust skills in intent recognition, long-horizon decision-making, and cross-source verification. To address this, we introduce Step-DeepResearch, a cost-effective, end-to-end agent. We propose a Data Synthesis Strategy Based on Atomic Capabilities to reinforce planning and report writing, combined with a progressive training path from agentic mid-training to SFT and RL. Enhanced by a Checklist-style Judger, this approach significantly improves robustness. Furthermore, to bridge the evaluation gap in the Chinese domain, we establish ADR-Bench for realistic deep research scenarios. Experimental results show that Step-DeepResearch (32B) scores 61.4% on Scale AI Research Rubrics. On ADR-Bench, it significantly outperforms comparable models and rivals SOTA closed-source models like OpenAI and Gemini DeepResearch. These findings prove that refined training enables medium-sized models to achieve expert-level capabilities at industry-leading cost-efficiency.

cs.CL↗

arXiv2025

Learning Multi-Modal Mobility Dynamics for Generalized Next Location Recommendation

The precise prediction of human mobility has produced significant socioeconomic impacts, such as location recommendations and evacuation suggestions. However, existing methods suffer from limited generalization capability: unimodal approaches are constrained by data sparsity and inherent biases, while multi-modal methods struggle to effectively capture mobility dynamics caused by the semantic gap between static multi-modal representation and spatial-temporal dynamics. Therefore, we leverage multi-modal spatial-temporal knowledge to characterize mobility dynamics for the location recommendation task, dubbed as \textbf{M}ulti-\textbf{M}odal \textbf{Mob}ility (\textbf{M}$^3$\textbf{ob}). First, we construct a unified spatial-temporal relational graph (STRG) for multi-modal representation, by leveraging the functional semantics and spatial-temporal knowledge captured by the large language models (LLMs)-enhanced spatial-temporal knowledge graph (STKG). Second, we design a gating mechanism to fuse spatial-temporal graph representations of different modalities, and propose an STKG-guided cross-modal alignment to inject spatial-temporal dynamic knowledge into the static image modality. Extensive experiments on six public datasets show that our proposed method not only achieves consistent improvements in normal scenarios but also exhibits significant generalization ability in abnormal scenarios.

cs.AI↗

arXiv2025

AI Deception: Risks, Dynamics, and Controls

As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved from a speculative concern to an empirically demonstrated risk across language models, AI agents, and emerging frontier systems. This project provides a comprehensive and up-to-date overview of the AI deception field, covering its core concepts, methodologies, genesis, and potential mitigations. First, we identify a formal definition of AI deception, grounded in signaling theory from studies of animal deception. We then review existing empirical studies and associated risks, highlighting deception as a sociotechnical safety challenge. We organize the landscape of AI deception research as a deception cycle, consisting of two key components: deception emergence and deception treatment. Deception emergence reveals the mechanisms underlying AI deception: systems with sufficient capability and incentive potential inevitably engage in deceptive behaviors when triggered by external conditions. Deception treatment, in turn, focuses on detecting and addressing such behaviors. On deception emergence, we analyze incentive foundations across three hierarchical levels and identify three essential capability preconditions required for deception. We further examine contextual triggers, including supervision gaps, distributional shifts, and environmental pressures. On deception treatment, we conclude detection methods covering benchmarks and evaluation protocols in static and interactive settings. Building on the three core factors of deception emergence, we outline potential mitigation strategies and propose auditing approaches that integrate technical, community, and governance efforts to address sociotechnical challenges and future AI risks. To support ongoing work in this area, we release a living resource at www.deceptionsurvey.com.

cs.AI↗

arXiv2025

Realization of polytype heterostructures via delicate structural transitions from a doped-Mott insulator

Transition metal dichalcogenides (TMDs) host multiple competing structural and electronic phases, making them an ideal platform for constructing polytype heterostructures with emergent quantum properties. However, controlling phase transitions to form diverse heterostructures inside a single crystal remains challenging. Here, we realize vertical/lateral polytype heterostructures in a hole-doped Mott insulator via thermal-annealing-induced structural transitions. Raman spectroscopy, atomic force microscopy (AFM) and scanning Kelvin probe force microscopy (SKPM) confirm the coexistence of T-H polytype heterostructures. Atomic-scale scanning tunneling microscopy/spectroscopy (STM/STS) measurements reveal the transparent effect in 1H/1T vertical heterostructures, where the charge density wave (CDW) of the underlying 1T-layer superposes on the top 1H-layer under positive bias. By systematically comparing 1T/1H and 1T/1T interfaces, we demonstrate that the metallic 1H-layer imposes a Coulomb screening effect on the 1T-layer, suppressing the formation of CDW domain walls and forming more ordered electronic states. These results clarify the interfacial coupling between distinct quantum many-body phases and establish a controllable pathway for constructing two-dimensional polytype heterostructures with tunable electronic properties.

cond-mat.mtrl-sci↗

arXiv2025

Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learning

We contend that embodied learning is fundamentally a lifecycle problem rather than a single-stage optimization. Systems that optimize only one link (data collection, simulation, learning, or deployment) rarely sustain improvement or generalize beyond narrow settings. We introduce Arcadia, a closed-loop framework that operationalizes embodied lifelong learning by tightly coupling four stages: (1) Self-evolving exploration and grounding for autonomous data acquisition in physical environments, (2) Generative scene reconstruction and augmentation for realistic and extensible scene creation, (3) a Shared embodied representation architecture that unifies navigation and manipulation within a single multimodal backbone, and (4) Sim-from-real evaluation and evolution that closes the feedback loop through simulation-based adaptation. This coupling is non-decomposable: removing any stage breaks the improvement loop and reverts to one-shot training. Arcadia delivers consistent gains on navigation and manipulation benchmarks and transfers robustly to physical robots, indicating that a tightly coupled lifecycle: continuous real-world data acquisition, generative simulation update, and shared-representation learning, supports lifelong improvement and end-to-end generalization. We release standardized interfaces enabling reproducible evaluation and cross-model comparison in reusable environments, positioning Arcadia as a scalable foundation for general-purpose embodied agents.

cs.RO↗

arXiv2025

Mechanically and electrically switchable triferroic altermagnet in a pentagonal FeO2 monolayer

Two-dimensional multiferroics promise low-power, multifunctional devices, yet the intrinsic coexistence and mutual control of three coupled ferroic orders in a single layer remains elusive. Here, we identify pentagonal monolayer FeO$_2$ as an intrinsic triferroic altermagnet where ferroelectric (FE), ferroelastic (FA), and altermagnetic (AM) orders coexist and are tightly coupled, accompanied by a competing antiferroelectric (AFE) phase using first-principles calculations. The sole presence of glide mirror $M_x$ symmetry in a FeO$_2$ sublayer, with the breaking of four-fold rotation $C_{4z}$ symmetry, induces in-plane vector ferroelectricity and twin-related ferroelastic strains. Both FE and AFE phases break combined parity - time symmetry and display sizable altermagnetic spin splitting with Néel temperatures over 200~K. Electric-field-induced rotation of the FE polarization reverses the sign of the spin splitting, while in-plane uniaxial strain triggers ferroelastic switching that simultaneously rotates the FE polarization vector by $90^\circ$ and reverses the AM state. These electric-field- and strain-mediated pathways interlink six distinct polarization states that can be selected purely by electric fields and/or mechanical strain. This work extends intrinsic triferroicity to pentagonal monolayers and outlines a symmetry-based route toward mechanically and electrically configurable altermagnetic spintronics.

cond-mat.mtrl-sci↗