Search arXiv⌕ Search

arXiv subjects

Xin Lu

Publications and source records attributed to Xin Lu.

At least 37 records · Page 2Linked to original sources
arXiv2026

Beyond Spatial Benchmarks: From Spatial Reasoning to Navigation

Does progress on spatial reasoning benchmarks translate into better navigation? Existing benchmarks test isolated inferences from images or videos, with little connection to downstream navigation. Our analysis reveals a gap between benchmark-oriented spatial specialization and navigation performance, and shows how aligning spatial supervision with navigation goals, phases, and decision learning improves navigation. Guided by these findings, we build \textsc{Spatial-Nav-100K} and fine-tune in two stages, \textit{i.e.} first learning a shared spatial-navigation foundation, and then specializing each phase with the abilities it relies on. We further introduce Spatial-NPD, where a teacher conditioned on spatial priors produces grounded action preferences and distills them into a student policy, so no explicit spatial reasoning is needed at inference. With 45 A100 GPU-hours of policy training, our 8B model reaches SR/SPL of 77.4/35.4 on HM3D-v0.2, 60.2/30.5 on HM3D-v0.1, and 47.9/20.6 on train-unseen MP3D. It outperforms several systems that rely on closed-source models or thousands of GPU-hours of training, at 148 ms per action step. All code and datasets will be publicly available at https://github.com/ylwhxht/Spatial-Nav.

cs.CV↗
arXiv2026

Unraveling the Kagome Antiferromagnetic $3J$ Model and Its Materials: An Integrated Approach

We investigate the ground-state and finite-temperature properties of the kagome antiferromagnetic Heisenberg model with three inequivalent couplings, dubbed the $3J$ model, which is designed for the candidate Dirac quantum spin liquid (QSL) material YCu$_3$(OH)$_6$Br$_2$[Br$_{1-x}$(OH)$_x$] (see, e.g., Zeng et al., 2024). Employing large-scale density-matrix renormalization group (DMRG) supplemented by neural quantum states (NQS) simulations, we identify an intermediate QSL phase between two magnetically ordered phases. We also find that this QSL is separated from the kagome spin liquid ground state at the isotropic limit. To establish a direct comparison with experiments, we compute the specific heat of the model by means of advanced exponential (XTRG) and tangent-space (tanTRG) thermal tensor-network methods. In the magnetically ordered phase, the specific heat over temperature exhibits a shoulder at a temperature that is a fraction of the coupling strength $J_{h}$, which disappears in the QSL phase. These universal behaviors are consistent with the experimentally observed specific heat in $3J$ materials for both ordered and QSL candidate samples. Our work thus connects microscopic models with experimentally measurable signatures, exemplifying an integrated approach to understanding QSL phenomena in frustrated quantum magnets~ (see Meng et al., 2026), with $3J$ materials serving as a representative case and providing a foundation for future studies.

cond-mat.str-el↗
arXiv2026

When Cognitive Graphs Meet LLMs: BDEI Cognitive Pathways for Panic Emotional Arousal Prediction

Predicting the timing of individual and collective panic emotional arousal before manifestation is essential for timely emergency intervention. Existing methods incorporate cognitive elements but none of them model emotion in the generative direction of the arousal process, leaving arousal timing undetermined. We argue that grounding prediction in appraisal emotion theory is necessary because it models this process explicitly in its natural generative direction, but three problems must be solved. (1) Appraisal theory posits that emotion arises from simultaneous evaluation across multiple threat dimensions, yet no prior work fuses these inputs into risk perception; (2) Existing models are trained in the opposite, behavior-bridged direction, recovering emotion merely as a post-hoc correlate of behavior; (3) Approaches that adopt LLMs as the primary decision-maker yet overlook the fragility and hallucination-proneness of their outputs. We introduce PanicCognitivePath (PCP) to address all three. A Psychological Safety Distance (PSD) model, grounded in psychological distance theory, maps four-domain signals (physical, social, cognitive, and informational) into a unified risk metric that gates entry to cognitive reasoning. An explicit Emotion node grounded in appraisal emotion theory is introduced into BDI, forming a novel Belief-Desire-Emotion-Intention (BDEI) pathway that couples threat appraisal directly to emotional arousal. Inverting the conventional LLM-as-decision-maker paradigm, PCP confines the LLM to parameter estimation for the Belief-to-Desire transition, restricting hallucinations to a single step and curbing their accumulation across steps. Experiments on Hurricane Sandy show PCP improves individual prediction accuracy by 10.68% over baselines, reduces peak count error to 7.07%.

cs.CL↗
arXiv2026

Multiscale Reconstruction of Multiplex Networks with Higher-Order Interactions

Inferring network structure from dynamical observations is a fundamental inverse problem in complex systems. Existing approaches have largely focused on single-layer or pairwise interaction networks, leaving the reconstructability of multiplex systems with higher-order interactions poorly understood. Here, we show that structural identifiability in such systems is jointly governed by cross-layer spreading couplings and network heterogeneity. Building on coupled awareness-behavior dynamics, we develop a multiscale inference framework that disentangles interacting spreading processes and enables the simultaneous reconstruction of microscopic simplicial interactions and macroscopic metapopulation organization. Numerical experiments on synthetic and empirical networks demonstrate high reconstruction performance, particularly in non-absorbing dynamical regimes sustained by weak inhibitory and strong facilitatory couplings. Results reveal the mechanisms governing structural identifiability in higher-order multiplex networks and provide a general route for inverse inference in multiscale complex systems.

physics.soc-ph↗
arXiv2026

ICEGR: An Intent-Coherent End-to-End Generative Retrieval Framework for E-commerce Search

Generative Retrieval (GR) is promising for e-commerce search, yet existing methods struggle to maintain query-intent consistency throughout the training pipeline. First, semantic ID (SID) construction based on static product information limits the ability of SIDs to encode product-intent associations. Second, although supervised fine-tuning (SFT) learns product-SID mappings across the catalog, low-exposure products still lack real query-intent supervision because query-to-SID training relies solely on online logs, resulting in poor retrieval performance for these products. Third, business-oriented preference optimization may favor popular or high-value products over those that best match the query intent, weakening query-product relevance. To address these issues, we propose ICEGR, an Intent-Coherent End-to-End Generative Retrieval Framework for E-commerce Search that integrates query intent consistently throughout the GR training pipeline. ICEGR comprises three components: (1) Intent-Aware SID Construction incorporates query-intent signals into SID construction, enabling SIDs to capture search intent beyond static product information; (2) Synthetic Query-Enhanced Unified SFT unifies multiple SFT tasks under the query-to-SID objective and augments sparse supervision from online logs with synthetic queries, providing complementary query-intent supervision for low-exposure products; and (3) Relevance-Calibrated Preference Optimization integrates query-product relevance and business signals into a margin-adaptive preference objective, preserving query intent while enabling business preference learning. Offline results show that ICEGR improves Recall@20 by 21.7% and NDCG@20 by 26.6% over the baseline. Deployed as an end-to-end generative retrieval pathway in Baidu E-commerce Search, ICEGR achieves relative improvements of 3.52% in CTR, 15.96% in order volume, and 7.53% in GMV in an A/B test.

cs.IR↗
arXiv2026

NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning

Named Entity Recognition (NER) has achieved substantial progress since the advent of large language models (LLMs). Nevertheless, the recognition of long-tail and domain-specific entities remains challenging due to the deficiency in parametric knowledge. Retrieval-augmented generation (RAG) offers a promising remedy by injecting external knowledge, but it also introduces noise and unnecessary cost when dealing with familiar cases. In this paper, we propose NE-R1, a novel framework for adaptive retrieval-augmented NER. We design a "retrieval-on-demand" mechanism for NER. Then we integrate it into models by a two-stage training method: (1) multi-task instruction tuning initialization; (2) end-to-end RL optimization with CoT. To achieve reasonable selection between parameterized and external knowledge, we design a multi-dimensional reward considering both accuracy and retrieval benefit. NE-R1 achieves state-of-the-art performance on various benchmarks, with an average F1 score gain of 2.52% in in-domain evaluation and 1.18% in zero-shot cross-domain evaluation.

cs.CL↗
arXiv2026

Gradient-based optimization of non-Abelian fractional quantum states in patterned superlattices

The realization of fractional Chern insulator (FCI) states in moiré heterostructures has attracted intense interest in the study of correlated topological states. So far, most experimentally realized FCI states may be interpreted as lattice analogues of Abelian fractional quantum Hall (FQH) states. Realizing non-Abelian FCI states is an important challenge in the field. Patterned dielectric superlattices provide a versatile platform for engineering topological flat bands. Such systems offer substantial structural flexibility and tunability, because their lattice patterns, periods, and other structural parameters can all be designed and fabricated. Here, we provide a gradient-based optimization workflow to design non-Abelian fractional states in patterned bilayer graphene superlattices. The experimentally relevant structural parameters of the superlattice devices are gradient-optimized to favor a flat Chern band with quantum-geometric properties reminiscent of those of the first excited Landau level. Exact diagonalization calculations at 1/2 filling of the optimized Chern band naturally yield non-Abelian FCIs. We apply this workflow to triangular, honeycomb, and kagome patterned superlattices and find robust non-Abelian FCIs over a large region of the parameter space spanned by superlattice constant and vertical potential drop. Our work thus establishes an experimentally feasible framework for exploring non-Abelian FCIs in realistic patterned-superlattice devices.

cond-mat.mes-hall↗
arXiv2026

Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds

Video generation is progressing beyond isolated clips toward long-form narratives and interactive worlds, requiring models to preserve identities, follow user controls, and remain stable over extended rollouts. We present JoyAI-Echo-1.5, a unified audio-visual generation system with two purpose-built variants. The long-video variant introduces composable cross-shot memory that aggregates visual evidence across multiple prior shots and speaker cues derived from speech-filtered full-shot audio, enabling persistent character appearance and voice identity across flexible combinations of text, image, and memory conditioning. The world-model variant converts heterogeneous navigation inputs into calibrated metric 6-DoF camera trajectories and injects them through a geometry-aware conditioning pathway, enabling controller-agnostic interaction across flexible viewpoints. To support efficient long-horizon generation, we transform a bidirectional audio-visual backbone into a causal few-step generator using progressive teacher forcing and short- and long-horizon Self-Gradient Forcing on self-generated rollouts. Experiments demonstrate strong performance in both settings. JoyAI-Echo-1.5 achieves improvements over existing long-video baselines in cross-shot consistency, visual quality, text alignment, and speech fidelity. Its world-model variant ranks first on WBench, with an average score of 81.7, and achieves leading visual quality and long-horizon persistence on SANA-WM-Bench. Together, these results indicate that memory, geometric control, and rollout-aware training provide a practical foundation for generating coherent stories and continuously evolving interactive worlds. Project page: https://echo-team-joy-future-academy-jd.github.io/Echo-1.5-Page/.

cs.CV↗
arXiv2026

EchoWM: Open and Enterable Omnimodal World Models

We present EchoWM, an omnimodal world model for enterable generative media that responds to continuous navigation while jointly generating 720p video, environmental sound, music and speech. We organize interaction around camera intent: in first-person scenes, it specifies observer motion, while in third-person scenes, camera--character dynamics are learned from data without view-specific controllers. Discrete commands and continuous poses are mapped to a shared metric-scale relative 6-DoF trajectory, with dataset-level calibration preserving motion magnitude across heterogeneous data. To jointly learn audio-visual generation and trajectory control, we construct a complementary data engine and adopt progressive training followed by autoregressive post-training for long-horizon generation. Extensive evaluations show that \model achieves strong trajectory following and high visual quality on public world-model benchmarks, supporting both first- and third-person interaction across varied subjects, and maintaining synchronized environmental sound and speech over long-horizon generation.

cs.CV↗
arXiv2026

Multiple superconducting phases and order-parameter evolution in pressurized UTe$_2$

The recently discovered heavy-fermion spin-triplet superconductor candidate UTe$_2$ provides a rich platform for unconventional pairing and topological phenomena. However, limited has been known about its superconducting order parameters and their evolution with control parameters, largely due to the lack of appropriate symmetry-sensitive detections. Here, we report comprehensive point-contact spectroscopy measurements of pressurized UTe$_2$ on the (0~0~1) surface. The observation of Andreev bound states strongly suggests the presence of a $p_z$ component in the superconducting order parameters. Quantitative analysis based on an extended Blonder-Tinkham-Klapwijk model unveils the superconducting order parameters with a finite odd-$k_z$ component (e.g. $B_{2u}$ or $B_{3u}$) for both ambient and pressurized UTe$_2$. Remarkably, the multiple superconducting phases can be distinguished by a single parameter $\langle Δ_{z}\rangle/\langleΔ_{x(y)}\rangle$, the relative weight between the $p_z$-wave and $p_{x(y)}$-wave pairings. These findings place stringent constraints on the pairing symmetry and provide essential spectroscopic signatures for distinguishing pressure-induced multiple superconducting phases in UTe$_2$.

cond-mat.str-el↗
arXiv2026

Charge imprinting biases topology of correlated insulator in hBN-aligned rhombohedral multilayer graphene

Rhombohedral multilayer graphene aligned with hexagonal boron nitride (RMG-hBN) hosts correlated Chern phases, but the microscopic role of hBN stacking remains unclear, especially when the active carriers are displaced away from the moiré interface. Using Hartree-Fock calculations over layer numbers, twist angles, displacement fields, fillings, and hBN alignments, we show that correlated insulators are most robust at small twist angles and intermediate layer number ($N\simeq 6$), where bandwidth suppression is balanced by layer delocalization of the wavefunctions of the active carriers. Under moiré-distant conditions at filling $ν=1$, the topology of the insulating state is strongly biased by charge imprinting: the hBN alignment shapes the occupied valence-band charge texture near the interface via moiré potential, which acts through long-range Coulomb interactions as a remote electrostatic template for doped conduction electrons. Depending on the alignment, this template favors either triangular charge localization associated with trivial insulators or honeycomb-like charge networks compatible with Chern insulators. Our results identify valence-band charge textures as a microscopic route by which a remote moiré interface controls correlated topology in multilayer graphene.

cond-mat.mes-hall↗
arXiv2026

VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs

Multimodal Large Language Models (MLLMs) encounter significant computational and memory bottlenecks from the massive number of visual tokens generated by high-resolution images or multi-image inputs. Previous token compression techniques are often constrained by heuristic rules that risk discarding critical information. They may suffer from biases, such as attention sinks, that lead to sharp performance drops under aggressive compression ratios. To address these limitations, we reformulate token compression as a lightweight plug-and-play framework and turn it into an end-to-end learnable decision process. Specifically, we propose VisionSelector, a scorer module decoupled from the MLLM backbone that incorporates a differentiable Top-K mechanism and a curriculum annealing strategy to bridge the training-inference gap, enabling efficient and adaptive token selection across various compression rates. Remarkably lightweight with only 12.85M trainable parameters, VisionSelector demonstrates generalization across various compression rates and adaptively identifies critical tokens. This leads to superior performance across the evaluated compression budgets, evidenced by preserving 100% performance on MME with a 30% retention budget, outperforming representative heuristic baselines by 12.14 percentage points at a 10% retention budget, and doubling prefill speed. Our code is available at https://github.com/JulietChoo/VisionSelector .

cs.CV↗
arXiv2026

Rerandomization for covariate balance mitigates $p$-hacking caused by strategically selecting covariates in regression adjustment

Rerandomization enforces covariate balance across treatment groups in the design stage of experiments. Despite its intuitive appeal, its theoretical justification remains unsatisfying because its benefits of improving efficiency for estimating the average treatment effect diminish if we use regression adjustment in the analysis stage. To strengthen the theory of rerandomization, we show that it mitigates false discoveries resulting from $p$-hacking caused by strategically selecting covariates in regression adjustment to get more significant $p$-values. Moreover, we show that rerandomization with a sufficiently stringent threshold can resolve such $p$-hacking. As a byproduct, our theory offers guidance for choosing the threshold in rerandomization in practice.

math.ST↗
arXiv2026

Poverty Mapping: Data, Models and Applications

Poverty mapping is increasingly important for monitoring Sustainable Development Goal 1 (SDG 1) of the United Nations 2030 Agenda, which aims to end poverty in all its forms everywhere. Yet timely and fine-resolution poverty estimation remains difficult because conventional census- and survey-based approaches are costly, infrequent, and often sparse precisely where deprivation is most severe. As poverty emerges from complex socioeconomic systems shaped by human mobility, social interactions, infrastructure, and economic activities, emerging computational methods and nontraditional data sources have created new opportunities for poverty estimation and mapping. At the intersection of statistical physics, complex systems science, and data science, these approaches enable poverty estimation at finer spatial and temporal resolutions. This review summarizes the main concepts of poverty and the principal frameworks used to measure it, and examines recent advances on poverty estimation and mapping using satellite imagery, mobile phone data, social media data, and multisource data fusion. The review also discusses persistent challenges related to representativeness, transferability across regions, interpretability, and uncertainty quantification. Finally, the review clarifies both the analytical promise and the practical limits of contemporary poverty mapping.

physics.soc-ph↗
arXiv2026

Correlated states in charge-transfer heterostructures based on rhombohedral multilayer graphene

Charge transfer is a common phenomenon in van der Waals heterostructures with proper work function mismatch, which enables electrostatic gating to control band alignment and interlayer charge distributions. This provides a tunable platform for studying coupled bilayer correlated electronic systems. Here, we theoretically investigate heterostructures of rhombohedral multilayer graphene (RMG) and an insulating substrate with gate-tunable band alignment. We first develop a self-consistent electrostatic theory for layer charge densities incorporating charge transfer, which reproduces the experimentally observed broadened and bent charge neutrality region. When the substrate's band edge has a much larger effective mass than RMG, its carriers may form a Wigner crystal at low densities. This generates a quantum superlattice that induces topological flat bands in the RMG layer through interlayer Coulomb interactions, which may further lead to Chern insulators driven by Coulomb interactions within the RMG layers. Conversely, with comparable effective masses, we find an interlayer excitonic insulator state at charge neutrality stabilized by interlayer Coulomb coupling. Our work establishes these charge-transfer heterostructures as a rich platform for topological and excitonic correlated states.

cond-mat.str-el↗
arXiv2026

Soft point-contact Andreev reflection spectroscopy in a palm-type cubic anvil-pressure cell

We have implemented soft point-contact Andreev reflection spectroscopy (PCARS) in a palm-type cubic anvil pressure cell by combining a substrate anchoring strategy with an external wire-splitting technique. This design enables the stable formation of multiple point contact junctions under hydrostatic pressures up to 15 GPa. Benchmark measurements on the elemental superconductor Nb demonstrate high reproducibility and yield a zero-temperature superconducting gap with a gap ratio of 3.3. We further apply this technique to the Kagome metal superconductor CsCr3Sb5 and the bilayer nickelate superconductor La2PrNi2O7. Pronounced zero-bias conductance peaks are observed, and their evolution with temperature, magnetic field and applied pressure is investigated, together with the superconducting gap magnitude and possible pairing symmetries. These measurements provide spectroscopic evidence consistent with unconventional superconductivity in these materials. Our work establishes a robust experimental platform that bridges macroscopic electrical transport and microscopic spectroscopic probes, opening a new avenue for investigating pairing symmetry in a wide range of pressure-induced unconventional superconductors.

cond-mat.supr-con↗
arXiv2026

SocialPersona: Benchmarking Personalized Profiling and Response with Multimodal Social-Media Context

Personalized language-model assistants are often evaluated through a memory lens: can a model recall preferences users have explicitly stated in dialogue? More comprehensive personalization demands a harder capability -- inferring what users care about from the multimodal traces they naturally leave behind. We introduce SocialPersona, a benchmark for evaluating whether multimodal large language models (MLLMs) can recover revealed preferences from longitudinal social-media timelines and use them in dialogue. Built from longitudinal timelines of 171 everyday, non-promotional social-media users, SocialPersona contains text, images, timestamps, and 2,597 human-verified preference tags across seven interest domains, separating stable interests from recent interests. It supports two tasks: constructing structured user profiles from multimodal context and generating responses aligned with inferred profiles. Experiments with proprietary and open-weight MLLMs show that models can identify broad interest domains, yet their performance drops on fine-grained and recent interests and degrades further when inferred profiles must be used to personalize dialogue. Together with evidence that text and images provide complementary preference signals, these results indicate that robust cross-modal, long-horizon user modeling remains a key challenge, and that SocialPersona can help measure and advance progress toward assistants that infer and act on revealed preferences.

cs.CL↗
arXiv2026

ActWorld: From Explorable to Interactive World Model via Action-Aware Memory

Interactive world models aim to simulate environment dynamics under real-time user actions. However, their action vocabulary is largely confined to navigation: most actions correspond to motion (e.g., walk, turn, look around), while interaction with objects in the scene (e.g., pick up plates, open doors, or trigger physical responses) is either absent, restricted to game domains, or relegated to prompt-to-full-video scenarios. The resulting worlds are visually explorable but not truly actionable. In this work, we present ActWorld, an interactive world model that extends prior navigation-centric generators to support mid-rollout object interaction within a chunk-autoregressive framework. We argue that the navigation-interaction gap stems from two bottlenecks. First, a data bottleneck: the lack of human-object interaction data with accurate, dense labels. Second, a memory bottleneck: recency-biased history compression in existing world models discards the event-transition frames that causally determine subsequent object states, leading to an action-forgetting pathology. On the data side, we construct a 100K interaction video dataset, each annotated with per-chunk captions via chain-of-thought reasoning. On the model side, we introduce a hierarchical action-aware memory design that routes history compression by interaction importance, complemented by a persistent memory bank that maintains event-update and object-identity tokens across long rollouts. Experiments show that ActWorld supports both flexible navigation and rich object interaction within a single model, substantially improving interaction fidelity over navigation-only baselines without sacrificing viewpoint control. Project page is available at https://interactwm.github.io/ActWorld.

cs.CV↗