arXiv subjects

Tian Xie

Publications and source records attributed to Tian Xie.

At least 37 records · Page 2Linked to original sources

arXiv2026

MatterSim-MT: A multi-task foundation model for in silico materials characterization

Accurate property characterization is a major bottleneck in materials design. While first-principles methods and task-specific machine-learning models have driven important progress, they remain fundamentally limited in scalability and generalizability across the vast space of structures and properties relevant to real-world materials design. We present MatterSim-MT, a multi-task foundation model for in silico materials simulation and property characterization. The model is pretrained on over 35 million first-principles-labeled structures covering 89 elements, temperatures up to 5000 K and pressures up to 1000 GPa, and is fine-tuned on various properties including Bader charges, magnetic moments, Born effective charges, and dielectric matrices. Out of the box, MatterSim-MT not only serves as a foundation model for predicting material structure, dynamics and thermodynamics, its multi-task architecture also enables a wide range of complex simulations that cannot be captured by potential energy surfaces alone. For example, we demonstrate pressure-dependent LO-TO phonon splitting in SiC with close agreement with experiment, electric hysteresis in ferroelectric BaTiO3, and the cationic-to-anionic redox transition during delithiation of a Li-rich cathode material. Finally, we show that MatterSim-MT scales well with more data and parameters, can be efficiently fine-tuned to higher levels of theory, and can be efficiently extended to new systems via active learning. Overall, we believe this approach provides a scalable route to accurate in silico materials characterization.

cond-mat.mtrl-sci↗

arXiv2026

GeRM: A Generative Rendering Model From Physically Realistic to Photorealistic

While physically-based rendering (PBR) simulates light transport that guarantees physical realism, achieving true photorealistic rendering (PRR) demands prohibitive time and labor, and still struggles to capture the intractable richness of the real world. We propose GeRM, the first multimodal generative rendering model to bridge the gap from PBR to PRR (P2P). We formulate this P2P transition by learning a distribution transfer vector (DTV) field to direct the generative process. To achieve this, we introduce a multi-condition ControlNet that synthesizes PBR images and progressively transitions them into PRR images, guided by G-buffers, text prompts, and cues for enhanced regions. To improve the model's grasp of the image distribution shift driven by text prompts, we propose a residual perceptual transfer mechanism to associate text prompts with corresponding targeted modification regions, which more clearly defines the incremental component updates. To supervise this transfer process, we introduce a multi-agent visual language model framework to construct an expert-guided pairwise transfer dataset, named P2P-50K, where each paired sample corresponds to a specific transfer vector in the DTV field. Extensive experiments demonstrate that GeRM synthesizes high-quality controllable images and outperforms state-of-the-art baselines across diverse applications, including PBR and PRR image synthesis and editing.

cs.CV↗

arXiv2026

Observation of Tunable Superradiant Frequency Combs

Cavity quantum electrodynamics (QED) with quantum emitters coupled to resonators provides a powerful platform for engineering light-matter interactions and exploring collective phenomena. In particular, superradiance, arising from collective quantum interference among emitters, has been explored as a route to ultrastable continuous radiation. However, engineering superradiance in the time domain to realize periodic pulsed sources or frequency combs remains largely unexplored. Here, we investigate the non-equilibrium many-body dynamics of a driven spin ensemble coupled to an on-chip superconducting resonator and uncover a dynamical phase transition from continuous-wave to periodic pulsed superradiant emission. To quantitatively capture the observed dynamical phases, we introduce a driven-dissipative cavity-QED model that elucidates how the periodic pulsed superradiant phase emerges from collective, periodically repeating spin dynamics stabilized by the interplay of coherence growth, disorder, and dissipation. We also find that rare-earth ion spin systems exhibiting both optical and microwave transitions enable phase-synchronized, dual-rail superradiant frequency combs in both the microwave and optical domains. Our results not only open new avenues for dual-rail frequency-comb applications in quantum metrology and information processing, but also establish a fundamental connection between periodic pulsed superradiance and the emergence of a continuous time crystal as a novel nonequilibrium phase in driven open systems.

quant-ph↗

arXiv2026

Adaptive Depth-converted-Scale Convolution for Self-supervised Monocular Depth Estimation

Self-supervised monocular depth estimation (MDE) has received increasing interests in the last few years. The objects in the scene, including the object size and relationship among different objects, are the main clues to extract the scene structure. However, previous works lack the explicit handling of the changing sizes of the object due to the change of its depth. Especially in a monocular video, the size of the same object is continuously changed, resulting in size and depth ambiguity. To address this problem, we propose a Depth-converted-Scale Convolution (DcSConv) enhanced monocular depth estimation framework, by incorporating the prior relationship between the object depth and object scale to extract features from appropriate scales of the convolution receptive field. The proposed DcSConv focuses on the adaptive scale of the convolution filter instead of the local deformation of its shape. It establishes that the scale of the convolution filter matters no less (or even more in the evaluated task) than its local deformation. Moreover, a Depth-converted-Scale aware Fusion (DcS-F) is developed to adaptively fuse the DcSConv features and the conventional convolution features. Our DcSConv enhanced monocular depth estimation framework can be applied on top of existing CNN based methods as a plug-and-play module to enhance the conventional convolution block. Extensive experiments with different baselines have been conducted on the KITTI benchmark and our method achieves the best results with an improvement up to 11.6% in terms of SqRel reduction. Ablation study also validates the effectiveness of each proposed module.

cs.CV↗

arXiv2026

LiftFormer: Lifting and Frame Theory Based Monocular Depth Estimation Using Depth and Edge Oriented Subspace Representation

Monocular depth estimation (MDE) has attracted increasing interest in the past few years, owing to its important role in 3D vision. MDE is the estimation of a depth map from a monocular image/video to represent the 3D structure of a scene, which is a highly ill-posed problem. To solve this problem, in this paper, we propose a LiftFormer based on lifting theory topology, for constructing an intermediate subspace that bridges the image color features and depth values, and a subspace that enhances the depth prediction around edges. MDE is formulated by transforming the depth value prediction problem into depth-oriented geometric representation (DGR) subspace feature representation, thus bridging the learning from color values to geometric depth values. A DGR subspace is constructed based on frame theory by using linearly dependent vectors in accordance with depth bins to provide a redundant and robust representation. The image spatial features are transformed into the DGR subspace, where these features correspond directly to the depth values. Moreover, considering that edges usually present sharp changes in a depth map and tend to be erroneously predicted, an edge-aware representation (ER) subspace is constructed, where depth features are transformed and further used to enhance the local features around edges. The experimental results demonstrate that our LiftFormer achieves state-of-the-art performance on widely used datasets, and an ablation study validates the effectiveness of both proposed lifting modules in our LiftFormer.

cs.CV↗

arXiv2026

30-meter Land Surface Temperature from Landsat via Progressive Self-Training Downscaling

Land surface temperature (LST) is a critical parameter for characterizing surface energy balance and hydrothermal processes. While Landsat provides invaluable LST observations at medium spatial resolution for over 40 years, its native spatial resolution of thermal bands (e.g., 100 m) remains insufficient compared to its 30 m optical bands, failing to meet the demands of fine-scale studies. To address this issues, this study proposes a progressive self-training framework for downscaling Landsat LST to 30 m without relying on fine-scale ground truth, while maintaining minimal data dependence. The framework progressively optimizes a cross-modal fusion network to refine thermal details in a coarse-to-fine manner, characterized by one pre-training and two fine-tuning stages. Spatial validation against SDGSAT-1 30 m LST and temporal validation using in situ measurements confirm its reliability and accuracy, with both station-averaged MAE and RMSE outperforming the official cubic product by approximately 0.4 K. Further performance comparison experiments demonstrate that the proposed framework consistently reconstructs coherent fine-scale thermal patterns while preserving spatial heterogeneity. Multi spatial resolution evaluations and ablation studies verify the effectiveness of the proposed strategy and network design. Overall, the framework provides a stable pathway for enhancing the spatial resolution of Landsat LST, providing fine-resolution data support for fine-scale surface process studies and localized environmental monitoring.

physics.ao-ph↗

arXiv2026

Imaging the Meissner effect and local superfluid stiffness in a graphene superconductor

We report the observation of the Meissner effect in a rhombohedral graphene superconductor, realized via direct imaging of the static fringe magnetic field. In our few-micron sample, the onset of superconductivity manifests as a diamagnetic response that screens only $\sim 100$ ppm of the applied magnetic field. Tracking the evolution of the resulting nanotesla-scale fields in real space allows us to observe the entry of superconducting vortices and map the local superfluid stiffness, $ρ_s$. Correlating fringe field signals from both Meissner screening and magnetically ordered states, we show that superconductivity onsets in the midst of a continuous quantum phase transition to a canted spin ferromagnet. Within the superconducting state, we find the temperature dependence of $ρ_s$ to be incompatible with isotropic Bardeen-Cooper-Schrieffer theory and the zero-temperature stiffness $ρ_s^0$ to be linearly proportional to $T_c$, constraining future theoretical models of superconductivity in this system.

cond-mat.supr-con↗

arXiv2026

Shorten After You're Right: Lazy Length Penalties for Reasoning RL

Large reasoning models, such as OpenAI o1 or DeepSeek R1, have demonstrated remarkable performance on reasoning tasks but often incur a long reasoning path with significant memory and time costs. Existing methods primarily aim to shorten reasoning paths by introducing additional training data and stages. In this paper, we propose three critical reward designs integrated directly into the reinforcement learning process of large reasoning models, which reduce the response length without extra training stages. Experiments on four settings show that our method significantly decreases response length while maintaining or even improving performance. Specifically, in a logic reasoning setting, we achieve a 40% reduction in response length averaged by steps alongside a 14% gain in performance. For math problems, we reduce response length averaged by steps by 33% while preserving performance.

cs.AI↗

arXiv2026

Mixture of States: Routing Token-Level Dynamics for Multimodal Generation

We introduce MoS (Mixture of States), a novel fusion paradigm for multimodal diffusion models that merges modalities using flexible, state-based interactions. The core of MoS is a learnable, token-wise router that creates denoising timestep- and input-dependent interactions between modalities' hidden states, precisely aligning token-level features with the diffusion trajectory. This router sparsely selects the top-$k$ hidden states and is trained with an $ε$-greedy strategy, efficiently selecting contextual features with minimal learnable parameters and negligible computational overhead. We validate our design with text-to-image generation (MoS-Image) and editing (MoS-Editing), which achieve state-of-the-art results. With only 3B to 5B parameters, our models match or surpass counterparts up to $4\times$ larger. These findings establish MoS as a flexible and compute-efficient paradigm for scaling multimodal diffusion models.

cs.CV↗

arXiv2026

BiasCause: Evaluate Socially Biased Causal Reasoning of Large Language Models

While large language models (LLMs) play increasingly significant roles in society, research shows they continue to generate content that reflects social bias against sensitive groups. Existing benchmarks effectively identify these biases, but a critical gap remains in understanding the underlying reasoning processes that produce them. This paper addresses this gap by evaluating the causal reasoning of LLMs when answering socially biased questions. We propose a formal schema that categorizes causal reasoning into three types (mistaken, biased, and contextually-grounded). We then synthesize 1788 questions covering eight sensitive attributes, with each set of questions designed to probe a specific type of causal reasoning. All questions are then manually validated, and each of them prompts the LLM to generate a causal graph behind its answer. We evaluate four state-of-the-art LLMs and find that all models exhibit biased causal reasoning on most questions eliciting it. Moreover, we discover that LLMs are also prone to "mistaken-biased" reasoning, where they first confuse correlation with causality to infer sensitive group membership and subsequently apply biased causal reasoning. By examining the cases where LLMs produce unbiased causal reasoning, we also identify three strategies LLMs employ to avoid bias (i.e., explicitly refusing to answer, avoiding sensitive attributes, and adding contextual restrictions), which provide insights for future debiasing efforts.

cs.CL↗

arXiv2026

Controlled LLM Training on Spectral Sphere

Scaling large models requires optimization strategies that ensure rapid convergence grounded in stability. Maximal Update Parametrization ($\boldsymbolμ$P) provides a theoretical safeguard for width-invariant $Θ(1)$ activation control, whereas emerging optimizers like Muon are only ``half-aligned'' with these constraints: they control updates but allow weights to drift. To address this limitation, we introduce the \textbf{Spectral Sphere Optimizer (SSO)}, which enforces strict module-wise spectral constraints on both weights and their updates. By deriving the steepest descent direction on the spectral sphere, SSO realizes a fully $\boldsymbolμ$P-aligned optimization process. To enable large-scale training, we implement SSO as an efficient parallel algorithm within Megatron. Through extensive pretraining on diverse architectures, including Dense 1.7B, MoE 8B-A1B, and 200-layer DeepNet models, SSO consistently outperforms AdamW and Muon. Furthermore, we observe significant practical stability benefits, including improved MoE router load balancing, suppressed outliers, and strictly bounded activations.

cs.LG↗

arXiv2026

CellularSpecSec-Bench: A Staged Benchmark for Evidence-Grounded Interpretation and Security Reasoning over 3GPP Specifications

Cellular networks are critical infrastructure supporting billions of worldwide users and safety- and mission-critical services. Vulnerabilities in cellular networks can therefore cause service disruption, privacy breaches, and broad societal harm, motivating growing efforts to analyze 3GPP specifications that define required device and operator behavior. While large language models (LLMs) have demonstrated the capability for reading technical documents, cellular specifications impose unique challenges: faithful interpretation of normative language, reasoning across cross-referenced clauses, and verifiable conclusions grounded in multimodal evidence such as tables and figures. To address these challenges, we propose CellSpecSec-ARI, a unified Adapt-Retrieve-Integrate framework for systematic understanding and standard-driven security analysis of 3GPP specifications; CellularSpecSec-Bench, a staged benchmark, containing newly constructed high-quality datasets with expert-verified and corrected subsets from prior open-source resources. Together, they establish an accessible and reproducible foundation for quantifying progress in specification understanding and security reasoning in the cellular network security domain.

cs.CR↗

arXiv2025

Automatic Inference for Value-Added Regressions

A large empirical literature regresses outcomes on empirical Bayes shrinkage estimates of value-added, yet little is known about whether this approach leads to unbiased estimates and valid inference for the downstream regression coefficients. We study a general class of empirical Bayes estimators and the properties of the resulting regression coefficients. We show that estimators can be asymptotically biased and inference can be invalid if the shrinkage estimator does not account for heteroskedasticity in the noise when estimating value added. By contrast, shrinkage estimators properly constructed to model this heteroskedasticity perform an automatic bias correction: the associated regression estimator is asymptotically unbiased, asymptotically normal, and efficient in the sense that it is asymptotically equivalent to regressing on the true (latent) value-added. Further, OLS standard errors from regressing on shrinkage estimates are consistent in this case. As such, efficient inference is easy for practitioners to implement: simply regress outcomes on shrinkage estimates of value-added that account for noise heteroskedasticity.

econ.EM↗

arXiv2025

OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory

Storytelling in real-world videos often unfolds through multiple shots -- discontinuous yet semantically connected clips that together convey a coherent narrative. However, existing multi-shot video generation (MSV) methods struggle to effectively model long-range cross-shot context, as they rely on limited temporal windows or single keyframe conditioning, leading to degraded performance under complex narratives. In this work, we propose OneStory, enabling global yet compact cross-shot context modeling for consistent and scalable narrative generation. OneStory reformulates MSV as a next-shot generation task, enabling autoregressive shot synthesis while leveraging pretrained image-to-video (I2V) models for strong visual conditioning. We introduce two key modules: a Frame Selection module that constructs a semantically-relevant global memory based on informative frames from prior shots, and an Adaptive Conditioner that performs importance-guided patchification to generate compact context for direct conditioning. We further curate a high-quality multi-shot dataset with referential captions to mirror real-world storytelling patterns, and design effective training strategies under the next-shot paradigm. Finetuned from a pretrained I2V model on our curated 60K dataset, OneStory achieves state-of-the-art narrative coherence across diverse and complex scenes in both text- and image-conditioned settings, enabling controllable and immersive long-form video storytelling.

cs.CV↗

arXiv2025

Scaling Zero-Shot Reference-to-Video Generation

Reference-to-video (R2V) generation aims to synthesize videos that align with a text prompt while preserving the subject identity from reference images. However, current R2V methods are hindered by the reliance on explicit reference image-video-text triplets, whose construction is highly expensive and difficult to scale. We bypass this bottleneck by introducing Saber, a scalable zero-shot framework that requires no explicit R2V data. Trained exclusively on video-text pairs, Saber employs a masked training strategy and a tailored attention-based model design to learn identity-consistent and reference-aware representations. Mask augmentation techniques are further integrated to mitigate copy-paste artifacts common in reference-to-video generation. Moreover, Saber demonstrates remarkable generalization capabilities across a varying number of references and achieves superior performance on the OpenS2V-Eval benchmark compared to methods trained with R2V data.

cs.CV↗

arXiv2025

Addressing Polarization and Unfairness in Performative Prediction

In many real-world applications of machine learning such as recommendations, hiring, and lending, deployed models influence the data they are trained on, leading to feedback loops between predictions and data distribution. The performative prediction (PP) framework captures this phenomenon by modeling the data distribution as a function of the deployed model. While prior work has focused on finding performative stable (PS) solutions for robustness, their societal impacts, particularly regarding fairness, remain underexplored. We show that PS solutions can lead to severe polarization and prediction performance disparities, and that conventional fairness interventions in previous works often fail under model-dependent distribution shifts due to failing the PS criteria. To address these challenges in PP, we introduce novel fairness mechanisms that provably ensure both stability and fairness, validated by theoretical analysis and empirical results.

cs.LG↗

arXiv2025

ProFL: Performative Robust Optimal Federated Learning

Performative prediction is a framework that captures distribution shifts that occur during the training of machine learning models due to their deployment. As the trained model is used, data generation causes the model to evolve, leading to deviations from the original data distribution. The impact of such model-induced distribution shifts in federated learning is increasingly likely to transpire in real-life use cases. A recently proposed approach extends performative prediction to federated learning with the resulting model converging to a performative stable point, which may be far from the performative optimal point. Earlier research in centralized settings has shown that the performative optimal point can be achieved under model-induced distribution shifts, but these approaches require the performative risk to be convex and the training data to be noiseless, assumptions often violated in realistic federated learning systems. This paper overcomes all of these shortcomings and proposes Performative Robust Optimal Federated Learning, an algorithm that finds performative optimal points in federated learning from noisy and contaminated data. We present the convergence analysis under the Polyak-Lojasiewicz condition, which applies to non-convex objectives. Extensive experiments on multiple datasets demonstrate the advantage of Robust Optimal Federated Learning over the state-of-the-art.

cs.LG↗

arXiv2025

Exciton-based sensing of remote electron correlations in 2D heterostructures

Many monolayer transition metal dichalcogenides, including MoS$_2$, MoSe$_2$, WS$_2$, and WSe$_2$, are direct bandgap two-dimensional (2D) semiconductors with sharp optical resonances at excitonic bound state frequencies. Recent experiments have demonstrated that excitonic resonance frequencies in multilayer van der Waals stacks are altered by long-range Coulomb interactions with electrons in nearby but electrically isolated 2D materials. These modulations have been successfully used to detect transitions between distinct states of remote strongly correlated 2D electron fluids. In this Letter we provide a theory of these frequency shifts, enabling a more quantitative interpretation of excitonic-sensing experiments, and apply it as an example to WSe$_2$ that is proximate to graphene bilayers and multilayers.

cond-mat.mes-hall↗