arXiv subjects

Xin Lu

Publications and source records attributed to Xin Lu.

At least 55 records · Page 3Linked to original sources

arXiv2026

LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results

This paper presents a review for the LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aimed to advance research on real-world all-in-one image restoration under diverse real-world degradation conditions, including blur, low-light, haze, rain, and snow. It provided a unified benchmark to evaluate the robustness and generalization ability of restoration models across multiple degradation categories within a common framework. The competition attracted 124 registered participants and received 9 valid final submissions with corresponding fact sheets, significantly contributing to the progress of real-world all-in-one image restoration. This report provides a detailed analysis of the submitted methods and corresponding results, emphasizing recent progress in unified real-world image restoration. The analysis highlights effective approaches and establishes a benchmark for future research in real-world low-level vision.

cs.CV↗

arXiv2026

IR-Flow: Bridging Discriminative and Generative Image Restoration via Rectified Flow

In image restoration, single-step discriminative mappings often lack fine details via expectation learning, whereas generative paradigms suffer from inefficient multi-step sampling and noise-residual coupling. To address this dilemma, we propose IR-Flow, a novel image restoration method based on Rectified Flow that serves as a unified framework bridging the gap between discriminative and generative paradigms. Specifically, we first construct multilevel data distribution flows, which expand the ability of models to learn from and adapt to various levels of degradation. Subsequently, cumulative velocity fields are proposed to learn transport trajectories across varying degradation levels, guiding intermediate states toward the clean target, while a multi-step consistency constraint is presented to enforce trajectory coherence and boost few-step restoration performance. We show that directly establishing a linear transport flow between degraded and clean image domains not only enables fast inference but also improves adaptability to out-of-distribution degradations. Extensive evaluations on deraining, denoising and raindrop removal tasks demonstrate that IR-Flow achieves competitive quantitative results with only a few sampling steps, offering an efficient and flexible framework that maintains an excellent distortion-perception balance. Our code is available at https://github.com/fanzh03/IR-Flow.

cs.CV↗

arXiv2026

Bird-SR: Bidirectional Reward-Guided Diffusion for Real-World Image Super-Resolution

Powered by multimodal text-to-image priors, diffusion-based super-resolution excels at synthesizing intricate details; however, models trained on synthetic low-resolution (LR) and high-resolution (HR) image pairs often degrade when applied to real-world LR images due to significant distribution shifts. We propose Bird-SR, a bidirectional reward-guided diffusion framework that formulates super-resolution as trajectory-level preference optimization via reward feedback learning (ReFL), jointly leveraging synthetic LR-HR pairs and real-world LR images. For structural fidelity easily affected in ReFL, the model is directly optimized on synthetic pairs at early diffusion steps, which also facilitates structure preservation for real-world inputs under smaller distribution gap in structure levels. For perceptual enhancement, quality-guided rewards are applied to both synthetic and real LR images at the later trajectory phase. To mitigate reward hacking, the rewards for synthetic results are formulated in a relative advantage space bounded by their ground-truth counterparts, while real-world optimization is regularized via a semantic alignment constraint. Furthermore, to balance structural and perceptual learning, we introduce a dynamic fidelity-perception weighting strategy that emphasizes structure preservation at early stages and progressively shifts focus toward perceptual optimization at later diffusion steps. Extensive experiments on real-world SR benchmarks demonstrate that Bird-SR consistently outperforms state-of-the-art methods in perceptual quality while preserving structural consistency, validating its effectiveness for real-world super-resolution. Our code can be obtained at https://github.com/fanzh03/Bird-SR.

cs.CV↗

arXiv2026

General Many-Body Perturbation Framework for Moiré Systems

Moiré superlattices host a rich variety of correlated topological states, including interaction-driven integer and fractional Chern insulators. A common approach to study interacting ground states at integer fillings is the Hartree-Fock mean-field method. However, this method neglects dynamical correlations, which often leads to an overestimation of spontaneous symmetry breaking and fails to provide quantitative descriptions of single-particle excitations. This work introduces a general many-body perturbation framework for moiré systems, combining all-band Hartree-Fock calculations with $GW$ quasiparticle corrections and random phase approximation (RPA) correlation energies. We apply this framework to hexagonal boron nitride aligned rhombohedral pentalayer graphene and magic-angle twisted bilayer graphene (MATBG). We show that incorporating RPA correlation energy and $GW$ self-energy corrections yields phase diagrams and single-particle spectra that quantitatively align with experimental measurements for both systems. Particularly, the ground state at charge neutrality of MATBG is predicted to be a nematic metal, which is stabilized over Kramers intervalley coherent insulator due to lower correlation energy. Our versatile framework provides a systematic beyond-mean-field approach applicable to generic moiré systems.

cond-mat.str-el↗

arXiv2026

Animated Public Furniture as an Interaction Mediator: Engaging Passersby In-the-Wild with Robotic Benches

Urban HCI investigates how digital technologies shape human behaviour within the social, spatial, temporal dynamics of public space. Meanwhile, robotic furniture research demonstrates how the purposeful animation of mundane utilitarian elements can influence human behaviour in everyday contexts. Taken together, these strands highlight an untapped opportunity to investigate how animated public furniture could mediate social interaction in urban environments. In this paper, we present the design process and in-the-wild study of mobile robotic benches that reconfigure with a semi-outdoor public space. Our findings show that the gestural performance of the benches manifested three affordances perceived by passersby, they activated engagement as robots, redistributed engagement as spatial elements, and settled engagement as infrastructure. We proposed an Affordance Transition Model (ATM) describing how robotic furniture could proactively facilitate transition between these affordances to engage passersby. Our study bridges robotic furniture and urban HCI to activate human experience with the built environment purposefully.

cs.HC↗

arXiv2026

Tracking by Detection and Query: An Efficient End-to-End Framework for Multi-Object Tracking

Multi-object tracking (MOT) is primarily dominated by two paradigms: tracking-by-detection (TBD) and tracking-by-query (TBQ). While TBD offers modular efficiency, its fragmented association pipeline often limits robustness in complex scenarios. Conversely, TBQ enhances semantic modeling end-to-end but suffers from high training costs and slow inference due to the tight coupling of detection and association. In this work, we propose the tracking-by-detection-and-query framework, TBDQ-Net, to advance the synergy between TBD and TBQ paradigms. By integrating a frozen detector with a lightweight associator, this architecture ensures intrinsic efficiency. Within this streamlined framework, we introduce tailored designs to address MOT-specific challenges. Concretely, we alleviate task conflicts and occlusions through the dual-stream update of the Basic Information Interaction (BII) module. The Content-Position Alignment (CPA) module further refines both content and positional components, providing well-aligned representations for association decoding. Extensive evaluations on DanceTrack, SportsMOT, and MOT20 benchmarks demonstrate that TBDQ-Net achieves a favorable efficiency-accuracy trade-off in challenging scenarios. Specifically, TBDQ-Net outperforms leading TBD methods by 6.0 IDF1 points on DanceTrack and achieves the best performance among TBQ methods in the crowded MOT20 benchmark. Relative to MOTRv2, TBDQ-Net reduces trainable parameters by approximately 80% while accelerating practical inference by 37.5%. These results highlight TBDQ-Net as an efficient alternative to heavy architectures, showcasing the efficacy of lightweight design. Source code is publicly available at https://github.com/FaithFlow/TBDQ-Net.

cs.CV↗

arXiv2026

Pose-Free Omnidirectional Gaussian Splatting for 360-Degree Videos with Consistent Depth Priors

Omnidirectional 3D Gaussian Splatting with panoramas is a key technique for 3D scene representation, and existing methods typically rely on slow SfM to provide camera poses and sparse points priors. In this work, we propose a pose-free omnidirectional 3DGS method, named PFGS360, that reconstructs 3D Gaussians from unposed omnidirectional videos. To achieve accurate camera pose estimation, we first construct a spherical consistency-aware pose estimation module, which recovers poses by establishing consistent 2D-3D correspondences between the reconstructed Gaussians and the unposed images using Gaussians' internal depth priors. Besides, to enhance the fidelity of novel view synthesis, we introduce a depth-inlier-aware densification module to extract depth inliers and Gaussian outliers with consistent monocular depth priors, enabling efficient Gaussian densification and achieving photorealistic novel view synthesis. The experiments show significant outperformance over existing pose-free and pose-aware 3DGS methods on both real-world and synthetic 360-degree videos. Code is available at https://github.com/zcq15/PFGS360.

cs.CV↗

arXiv2026

MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation

Embodied navigation is a fundamental capability for robotic agents operating. Real-world deployment requires open vocabulary generalization and low training overhead, motivating zero-shot methods rather than task-specific RL training. However, existing zero-shot methods that build explicit 3D scene graphs often compress rich visual observations into text-only relations, leading to high construction cost, irreversible loss of visual evidence, and constrained vocabularies. To address these limitations, we introduce the Multi-modal 3D Scene Graph (M3DSG), which preserves visual cues by replacing textual relational edges with dynamically assigned images. Built on M3DSG, we propose MSGNav, a zero-shot navigation system that includes a Key Subgraph Selection module for efficient reasoning, an Adaptive Vocabulary Update module for open vocabulary support, and a Closed-Loop Reasoning module for accurate exploration reasoning. Additionally, we further identify the last mile problem in zero-shot navigation determining the feasible target location with a suitable final viewpoint, and propose a Visibility-based Viewpoint Decision module to explicitly resolve it. Comprehensive experimental results demonstrate that MSGNav achieves state-of-the-art performance on the challenging GOAT-Bench and HM3D-ObjNav benchmark. The code will be publicly available at https://github.com/ylwhxht/MSGNav.

cs.CV↗

arXiv2026

Experimental Determination of Gamma-Ray Polarization in Strong-Field Nonlinear Compton Scattering

The polarization of gamma rays produced in strong-field quantum electrodynamics (SFQED) is a fundamental and long-standing prediction, the verification of which has remained elusive, limiting both foundational tests and applications. Here, we report the first experimental measurement of gamma-ray polarization generated via all-optical nonlinear Compton scattering. Colliding a laser-wakefield-accelerated electron beam with an intense counter-propagating laser pulse reflected from a plasma mirror, we produce bright gamma rays in the strong-field regime ($a_0 > 1$). For gamma rays with $a_0 \approx 3$, a linear polarization degree of $\sim 50\%$ is measured via the azimuthal asymmetry of photoneutrons from a deuterium target, and independently verified by a Compton polarimeter.The results show excellent agreement with SFQED calculations employing the locally monochromatic approximation, while diverging from predictions based on the locally constant field approximation, highlighting the importance of quantum interference effects in this regime. Our work provides experimental evidence for polarization dynamics in SFQED, supports a key prediction of nonperturbative QED, and paves the way for compact, laser-driven sources of polarized gamma rays.}

physics.plasm-ph↗

arXiv2026

Magnetic field and pressure tuning of the heavy fermion antiferromagnet CePdIn

Frustrated Kondo lattices are ideal platforms for studying how both the Kondo effect and quantum fluctuations compete with the magnetic exchange interactions that drive magnetic ordering. Here, we investigate the effect of tuning the heavy-fermion compound CePdIn, which crystallizes in the geometrically frustrated ZrNiAl-type structure, using applied magnetic fields and hydrostatic pressure. At ambient pressure, CePdIn exhibits two magnetic transitions, one at $T_{\rm{N}} \approx 1.65$ K and another at $T_{\rm{M}} \approx 1.15$ K, which are both suppressed by applied $c$-axis fields. Upon applying pressure in zero magnetic field, there is a non-monotonic evolution of $T_{\rm{N}}$, which decreases to 0.8 K at 2.3 GPa, before abruptly increasing to 1.5 K at 2.6 GPa. At higher pressures, $T_{\rm{N}}$ has a weak pressure dependence, and vanishes near 5 GPa. Together with the high-pressure phase being more robust to applied fields, these results suggest two distinct antiferromagnetic phases in CePdIn, which are separated near 2.6 GPa, and this change may be driven by the evolution of the underlying electronic structure due to enhanced Kondo hybridization under pressure.

cond-mat.str-el↗

arXiv2026

Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings

Leveraging Multimodal Large Language Models (MLLMs) has become pivotal for advancing Universal Multimodal Embeddings (UME) in addressing diverse cross-modal tasks. Recent studies demonstrate that incorporating generative Chain-of-Thought (CoT) reasoning can substantially enhance task-specific representations compared to discriminative methods. However, the generated reasoning CoTs of existing generative embedding methods are limited to the textual analysis of queries and are irrelevant to the retrieval of the targets. To address these limitations, we propose a reasoning-driven UME framework that integrates Embedder-Guided Reinforcement Learning (EG-RL) to optimize the Reasoner to produce evidential Traceability CoT (T-CoT). Our key contributions are threefold: (1) We design an EG-RL framework where the Embedder provides explicit supervision to the Reasoner, ensuring the generated CoT traces are aligned with embedding tasks. (2) We introduce T-CoT, which extracts critical multimodal cues to focus on retrieval-relevant elements and provides multimodal inputs for the Embedder. (3) With limited computational resources, our framework outperforms the pioneering embedding model on both MMEB-V2 and UVRB benchmarks. The integration of multimodal evidence in structured reasoning, paired with retrieval-oriented alignment, effectively strengthens cross-modal semantic consistency and boosts the fine-grained matching capability of the model as well as the generalization across complex scenarios. Our work demonstrates that targeted reasoning optimization can significantly improve multimodal embedding quality, providing a practical and efficient solution for reasoning-driven UME development.

cs.CV↗

arXiv2026

FC-4DFS: Frequency-controlled Flexible 4D Facial Expression Synthesizing

4D facial expression synthesizing is a critical problem in the fields of computer vision and graphics. Current methods lack flexibility and smoothness when simulating the inter-frame motion of expression sequences. In this paper, we propose a frequency-controlled 4D facial expression synthesizing method, FC-4DFS. Specifically, we introduce a frequency-controlled LSTM network to generate 4D facial expression sequences frame by frame from a given neutral landmark with a given length. Meanwhile, we propose a temporal coherence loss to enhance the perception of temporal sequence motion and improve the accuracy of relative displacements. Furthermore, we designed a Multi-level Identity-Aware Displacement Network based on a cross-attention mechanism to reconstruct the 4D facial expression sequences from landmark sequences. Finally, our FC-4DFS achieves flexible and SOTA generation results of 4D facial expression sequences with different lengths on CoMA and Florence4D datasets. The code will be available on GitHub.

cs.GR↗

arXiv2026

Landmark Guided 4D Facial Expression Generation

In this paper, we proposed a generative model that learns to synthesize the 4D facial expression with the neutral landmark. Existing works mainly focus on the generation of sequences guided by expression labels, speech, etc, while they are not robust to the change of different identities. Our LM-4DGAN utilizes neutral landmarks to guide the facial expression generation while adding an identity discriminator and a landmark autoencoder to the basic WGAN for achieving better identity robustness. Furthermore, we add a cross-attention mechanism to the existing displacement decoder which is suitable for the given identity.

cs.GR↗

arXiv2026

Memory-Guided View Refinement for Dynamic Human-in-the-loop EQA

Embodied Question Answering (EQA) has traditionally been evaluated in temporally stable environments where visual evidence can be accumulated reliably. However, in dynamic, human-populated scenes, human activities and occlusions introduce significant perceptual non-stationarity: task-relevant cues are transient and view-dependent, while a store-then-retrieve strategy over-accumulates redundant evidence and increases inference cost. This setting exposes two practical challenges for EQA agents: resolving ambiguity caused by viewpoint-dependent occlusions, and maintaining compact yet up-to-date evidence for efficient inference. To enable systematic study of this setting, we introduce DynHiL-EQA, a human-in-the-loop EQA dataset with two subsets: a Dynamic subset featuring human activities and temporal changes, and a Static subset with temporally stable observations. To address the above challenges, we present DIVRR (Dynamic-Informed View Refinement and Relevance-guided Adaptive Memory Selection), a training-free framework that couples relevance-guided view refinement with selective memory admission. By verifying ambiguous observations before committing them and retaining only informative evidence, DIVRR improves robustness under occlusions while preserving fast inference with compact memory. Extensive experiments on DynHiL-EQA and the established HM-EQA dataset demonstrate that DIVRR consistently improves over existing baselines in both dynamic and static settings while maintaining high inference efficiency.

cs.CV↗

arXiv2026

Offer of a reward does not always promote trust in spatial games

Trust is one of the cornerstones of human society. One of the evolutionary pressure mechanisms that may have led to its emergence is the presence of incentives for trustworthy behavior. However, this type of reward has received relatively little attention in the context of spatial trust games, which are often used to build models in evolutionary game theory. To fill this gap, we introduce an inter-role reward mechanism in the spatial trust game, so that an investing trustor can choose to pay an extra cost to reward a trustworthy trustee. With extensive numerical simulations, we find that this type of reward does not always promote trust. Rather, while moderate rewards break the dominance of mistrust, thereby favoring investment, excessive rewards eventually stimulate a nonreturn strategy, ultimately suppressing the evolution of trust. Additionally, lower reward costs do not necessarily promote trust. Instead, more costly, but not excessive, rewards enhance the advantage of the original investment, consolidating the clusters of rewarders and improving trust. Our model thus provides evidence about the counterintuitive nature of the relationship between trust and rewards in a complex society.

cond-mat.stat-mech↗

arXiv2026

Competing and Intertwined Orders in Boson-Doped Mott Antiferromagnets

Inspired by the recent experimental advances in cold atom quantum simulators, we explore the experimentally implemented bosonic $t$-$t'$-$J$ model on the square lattice using large-scale density matrix renormalization group simulations. By tuning the doping level $δ$ and hopping ratio $t'/t$, we uncover six distinct quantum phases, several of which go far beyond the conventional paradigm of phase-coherent superfluidity (SF) expected for bosonic systems. In particular, in the presence of antiferromagnetic (AFM) order, doped holes are tightly bound into pairs, giving rise to a pair density wave (PDW) phase at low doping and small $|t'/t|$, which is suppressed on the $t'<0$ side, resulting in a disordered PDW state that lacks coherence of either individual bosons or pairs. Upon further doping, bosons can regain phase coherence and form a SF* state, characterized by condensation at emergent incommensurate momenta concurrent with an incommensurate magnetic order. On the $t'>0$ side, the sign-induced kinetic frustration inherently disfavors local AFM correlations, leading to a phase separation in which doped holes cluster into ferromagnetic (FM) domains spatially separated by undoped AFM regions. Upon further doping, this inhomogeneous state evolves into a uniform SF + $xy$-FM phase. Finally, we propose a concrete experimental scheme to realize both signs of $t'/t$ in Rydberg tweezer arrays, with an explicit mapping between model parameters and experimentally accessible regimes. Our results reveal competing and intertwined orders in doped antiferromagnets, which are relevant to central issues in high-$T_c$ superconductivity, reflecting the frustrated interplay between doped holes and spin background.

cond-mat.str-el↗

arXiv2026

ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing

Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning (RL) has been investigated for improving the quality of image editing, but it faces three key challenges: (1) limited reasoning exploration confined to denoising stochasticity, (2) biased reward fusion, and (3) unstable VLM-based instruction rewards. In this work, we propose ThinkRL-Edit, a reasoning-centric RL framework that decouples visual reasoning from image synthesis and expands reasoning exploration beyond denoising. To the end, we introduce Chain-of-Thought (CoT)-based reasoning sampling with planning and reflection stages prior to generation in online sampling, compelling the model to explore multiple semantic hypotheses and validate their plausibility before committing to a visual outcome. To avoid the failures of weighted aggregation, we propose an unbiased chain preference grouping strategy across multiple reward dimensions. Moreover, we replace interval-based VLM scores with a binary checklist, yielding more precise, lower-variance, and interpretable rewards for complex reasoning. Experiments show our method significantly outperforms prior work on reasoning-centric image editing, producing instruction-faithful, visually coherent, and semantically grounded edits.

cs.CV↗

arXiv2026

GGBall: Graph Generative Model on Poincaré Ball

Generating graphs with hierarchical structures remains a fundamental challenge due to the limitations of Euclidean geometry in capturing exponential complexity. Here we introduce \textbf{GGBall}, a novel hyperbolic framework for graph generation that integrates geometric inductive biases with modern generative paradigms. GGBall combines a Hyperbolic Vector-Quantized Autoencoder (HVQVAE) with a Riemannian flow matching prior defined via closed-form geodesics. This design enables flow-based priors to model complex latent distributions, while vector quantization helps preserve the curvature-aware structure of the hyperbolic space. We further develop a suite of hyperbolic GNN and Transformer layers that operate entirely within the manifold, ensuring stability and scalability. Empirically, our model reduces degree MMD by over 75\% on Community-Small and over 40\% on Ego-Small compared to state-of-the-art baselines, demonstrating an improved ability to preserve topological hierarchies. These results highlight the potential of hyperbolic geometry as a powerful foundation for the generative modeling of complex, structured, and hierarchical data domains. Our code is available at \href{https://github.com/AI4Science-WestlakeU/GGBall}{here}.

cs.LG↗