Search arXiv⌕ Search

arXiv subjects

Shuai Zhang

Publications and source records attributed to Shuai Zhang.

At least 19 recordsLinked to original sources
arXiv2026

HoloRecon: Incremental Reconstruction of Long-Range Panoramas with Global Consistency

Long-sequence panoramic reconstruction requires detailed scene geometry and globally consistent camera poses across distant revisits. Panoramic SLAM and incremental SfM rely on feature correspondences, but repeated, similar structures and small partial overlap make reliable long-range connections difficult to establish, leaving accumulated drift unresolved. Feed-forward models offer detailed local geometry, but their high computational costs limit inference window size, necessitating additional constraints for global consistency. This motivates combining continuous feature-based tracking and sparse mapping with rapid, high-quality local reconstruction from feed-forward models to achieve accurate localization and globally consistent dense mapping over long sequences. We therefore propose a panoramic reconstruction framework that couples an ORB-based sparse panoramic mapping frontend with a fine-tuned feed-forward model. Our key insight is that predicted local geometry enables 3D verification of feature matches across distant revisits, yielding long-range camera constraints even between regions. We calibrate predicted depths with sparse landmarks and use verified connections to optimize the global pose graph, updating dense geometry with the corrected camera poses. We also introduce PanoRecon, a seven-scene benchmark with repetitive architecture, large and small loops, and reference camera poses and LiDAR geometry for evaluating global consistency. Our method achieves the lowest mean absolute trajectory error and high F-1 Score among the evaluated methods. Project Page:https://zhuoxiaoli.github.io/HoloRecon_page/

cs.CV↗
arXiv2026

Intrinsic Raman Modes and Crystal Symmetry of Altermagnetic $α$-MnTe

Crystal symmetry governs the physical properties of materials and provides the framework for interpreting their microscopic excitations and macroscopic responses. In altermagnets, the crystal symmetries that relate opposite-spin sublattices give rise to momentum-dependent spin splitting despite compensated magnetization. Determining the real crystal symmetry is therefore essential for understanding the intrinsic electronic and magnetic properties. For the altermagnetic semiconductor $α$-MnTe, conflicting Raman assignments have left both its intrinsic lattice excitations and its crystal symmetry unresolved. Here we combine high-resolution Raman and second-harmonic generation (SHG) spectroscopy with first-principles calculations to distinguish intrinsic lattice excitations from Te-derived spectral contributions and to examine bulk inversion symmetry of $α$-MnTe. We show that several prominent Raman features previously assigned to $α$-MnTe instead originate from segregated Te clusters or precipitates. The remaining intrinsic Raman response consists of a single Raman-active mode assigned to the calculated $E_{2g}$ phonon, consistent with the centrosymmetric $D_{6h}$ symmetry. The SHG response agrees with surface electric-dipole and bulk electric-quadrupole contributions expected for a centrosymmetric $D_{6h}$ crystal, supporting the preservation of bulk inversion symmetry in $α$-MnTe. Our findings revise the Raman assignments in $α$-MnTe and provide a basis for interpreting its altermagnetic properties within the appropriate crystal-symmetry framework.

cond-mat.mtrl-sci↗
arXiv2026

Learning Domain Trajectories with Flow Matching for Gradual Domain Adaptation

Large distribution shifts remain a primary obstacle for domain generalization and unsupervised adaptation. Although gradual domain adaptation alleviates this difficulty by introducing ordered intermediate domains, most existing approaches still operate in a discrete, step-wise manner, which can accumulate errors and often relies on unstable Min--Max optimization. We propose \textbf{FlowGDA}, a flow-matching framework that models gradual adaptation as \emph{continuous} transport on a statistical manifold in a representation space. FlowGDA learns time-dependent velocity fields that induce smooth domain trajectories, using a simulation-free regression objective rather than adversarial training. To prevent semantic drift, we couple left-to-right transport between consecutive domains with a source-anchored transport and a semantic consistency loss, and we further stabilize learning via a two-stage sequential optimization scheme. Extensive experiments demonstrate that our method outperforms state-of-the-art techniques, validating flow matching as an effective alternative for domain adaptation.

cs.LG↗
arXiv2026

Robust Anomalous Hall Effect in Epitaxial Cubic D0$_3$-Fe$_3$Ge Nanoplates Grown by Chemical Vapor Deposition

The iron-based ferromagnetic materials have emerged as a promising system for spintronics due to their high Curie temperatures and significant anomalous Hall effect (AHE) driven by Berry curvature. While there have been investigations into the epitaxial growth of non-layered iron-based ferromagnetic materials, the realization of high-quality single crystal thin films continues to be a formidable obstacle. Meanwhile, the issues such as grain boundary scattering further hinder their characterization and application. Here, we report the first chemical vapor deposition (CVD) synthesis of single-crystalline cubic D0$_3$-Fe$_3$Ge nanoplates. This compound represents a substantial departure from the conventional hexagonal phases typically observed in the Fe-Ge system. Structural characterizations confirm the cubic lattice and stoichiometric purity of the crystals. Structural analysis identifies a strong epitaxial effect, resulting in a giant compressive strain of ~4.16% at the interface that relaxes gradually toward the surface. The second-harmonic generation (SHG) signals might further reveal that such interfacial strain disrupted the inherent centro-symmetry of the cubic phase. SQUID magnetometry shows robust room-temperature ferromagnetism and clear magnetic anisotropy. Magneto-transport measurements reveal a robust AHE that remains stable at temperatures far exceeding room temperature. The scaling observed between the anomalous Hall resistance and longitudinal resistance strongly suggests that this effect is dominated by the intrinsic Berry curvature mechanism. Furthermore, density functional theory (DFT) calculations reveal that the huge epitaxial strain induces band reconstructions and creates dense spin-orbit coupling gaps near the Fermi level, effectively doubling the anomalous Hall conductivity to match our experimental observations.

cond-mat.mtrl-sci↗
arXiv2026

Latent Bridge: From Video Latents to 3D Geometry via Feature Alignment

Video generation and feed-forward 3D reconstruction typically use separate representations, requiring RGB decoding and visual re-encoding to recover geometry from generated latents. We propose Latent Bridge, which connects video generative latent spaces with geometric feature spaces to directly predict 3D geometry from video latents. We develop representation-specific bridges for Wan2.1 and V-RAE, enabling feed-forward prediction of cameras, depth, and 3D point clouds without the intermediate RGB pathway. Each bridge is trained on RGB videos through feature distillation, while the video encoder and geometry model remain frozen. Training requires neither ground-truth geometry nor execution of the downstream geometric aggregator or prediction heads. At inference, the same video latents support both RGB decoding and geometry prediction. The same trained bridge can be reused for image-to-video and text-to-video generation within the same video latent space, without bridge retraining. Experiments on Co3Dv2 and WildRGB-D demonstrate competitive geometric reconstruction quality, efficient end-to-end generation and reconstruction, and faster latent-to-geometry decoding, highlighting latent alignment as a practical and reusable interface between video generation and 3D reconstruction. Our code is available at: https://github.com/hustvl/Latent-Bridge.

cs.CV↗
arXiv2026

On the origin of nonreciprocal charge transport in topological insulator BiSbTeSe2

Nonreciprocal charge transport provides an effective approach for probing direction dependent charge dynamics and spin-momentum-locked electronic states. Here, we report highly gate-tunable nonreciprocal charge transport in dual-gated BiSbTeSe2 topological insulator device. The second-harmonic longitudinal resistance is linear in both current and magnetic field. The nonreciprocal response reaches its maximum near the charge neutrality point, exhibits sign reversals on either side, and is strongly suppressed once the Fermi level enters the bulk states. We suggest that the nonreciprocal response is attributed to the inhomogeneity of spin-momentum locking in the topological surface states. The nonreciprocal signal near the charge neutrality point is about one order of magnitude larger than that without gate modulation and remains robust up to 300 K, highlighting BiSbTeSe2 as a promising platform for room-temperature nonlinear electronics.

cond-mat.mes-hall↗
arXiv2026

World Action Critic (WAC) Model: Joint Foresight and Criticism for Policy Learning

World models have shown considerable promise in sequential decision-making by anticipating the consequences of actions and providing predictive foresight for policy learning. However, learning to reason about counterfactual actions remains challenging, since predictive objectives may underemphasize information critical for action evaluation, while unexecuted actions lack observed futures for direct supervision. To address these challenges, we propose the World Action Critic (WAC) Model, which proposes multimodal action candidates and jointly learns candidate-conditioned future prediction and consequence evaluation. In our proposed framework, critic supervision directly shapes intermediate predictive representations during rollout, encouraging them to retain information needed to distinguish action quality. Observed futures supervise prediction for executed actions, while external task-quality targets provide evaluation signals for counterfactual candidates. Through joint optimization, critic signals from these candidates propagate into predictive representations without requiring their observed futures. Our theoretical analysis characterizes critic-guided feature retention and bounds candidate-selection regret. Applied to autonomous driving, WAC achieves 93.4 PDMS on NAVSIM-v1, demonstrating the effectiveness of jointly learning predictive foresight and consequence evaluation.

cs.AI↗
arXiv2026

LonGaussian: Tracking Foundation Priors for Long-Context Feedforward Gaussian Reconstruction

Reconstructing high-quality, renderable 3D scenes from long videos is essential for robotic perception and embodied intelligence. Many feed-forward Gaussian reconstruction methods rapidly predict 3D scenes from a small set of images, but extending them to longer sequences presents two bottlenecks: jointly processing all views increases GPU memory requirements, while accumulating pixel-aligned predictions redundantly represents the same surfaces and increases storage and rendering costs. We present LonGaussian, a streaming feed-forward framework that reconstructs compact, globally renderable Gaussian scenes from long image sequences with known intrinsics and unknown camera poses. Built on a pretrained streaming 3D reconstruction backbone, LonGaussian decodes long-context geometric features into dense Gaussians. Within each chunk, multi-frame point tracks link repeated observations of the same surface and guide a learned merger to consolidate the corresponding Gaussian predictions. Rendered-depth consistency filtering further suppresses Gaussians from other chunks that incorrectly occlude locally reconstructed surfaces. On DL3DV and RealEstate10K benchmarks, LonGaussian improves novel-view rendering quality while using substantially fewer Gaussians than the evaluated feed-forward baselines.

cs.CV↗
arXiv2026

GeoPano: Towards Geometrically Accurate 3D Reconstruction from a Single Panorama

Panoramic 3D reconstruction enables the holistic recovery of complete 360 $^\circ$ scene geometry, offering significant benefits for robotics and AR/VR applications. However, directly estimating geometry from ERP images is inherently challenged by spherical distortions. To reduce spherical projection distortions, a common strategy is to decompose panoramas into distortion-free perspective views, but independently processing these views often introduces cross-view geometric inconsistencies. To address these challenges, we introduce GeoPano, a feed-forward framework for single-view panoramic 3D reconstruction that recovers a geometrically accurate and consistent point cloud from a single panorama. Our approach is driven by two key innovations: First, we propose a panoramic-aware attention aggregator, featuring a streamlined attention architecture equipped with a novel Pano-Attention mechanism, which explicitly exploits the intrinsic spherical geometry of the panorama to guide cross-view interactions, thereby suppressing geometric inconsistencies. Furthermore, we formulate a hybrid supervision strategy to jointly enforce fine-grained local details in perspective space and global structural coherence in spherical space. Experiments demonstrate that our method significantly outperforms previous SOTA approaches in reconstruction accuracy, geometric consistency, and visual fidelity.

cs.CV↗
arXiv2026

PathFM: Fast Generative Forecasting of Multivariate Trajectories

Time series foundation models are becoming increasingly popular for general-purpose forecasting. However, most leading models predict marginal quantiles, leaving the dependence structure of future trajectories unspecified. This distinction matters for trajectory-dependent quantities such as cumulative demand, peak load, and event timing, yet point and marginal scores do not reveal it. To model this dependence, we introduce PathFM, a trajectory-based forecasting model that uses flow matching to generate complete future paths. We further distill the model to one or two steps and share history attention cache across draws. Together, these enable PathFM to generate multiple paths for a single series in roughly the time needed for one query to a quantile model. The distilled sampler also makes it practical to optimize a calibration loss directly. PathFM achieves competitive marginal accuracy on the established forecasting benchmarks fev-bench and TIME. To complement these evaluations, we introduce Forecast Path Score Bench (fps-bench), which augments fev-bench tasks with energy and variogram scores and downstream metrics. PathFM achieves a higher aggregate path score on fps-bench than all evaluated external baselines. Experiments on chaotic systems further show that our flow model sustains long-run variability, while strong baselines rapidly collapse. PathFM makes generative time series forecasting both competitive and practical, enabling diverse downstream applications.

cs.LG↗
arXiv2026

Batch-Paced: Fixed-Budget Batch Decoding in Discrete Diffusion Language Models

As generative language models become more capable and widely used, inference demand grows, making efficient serving increasingly important. Discrete diffusion language models (dLLMs) offer a promising path to more efficient inference through parallel token generation. Prior dLLM decoding methods, however, focus on improving inference efficiency for individual sequences. We formulate fixed-budget dLLM batch decoding and introduce Batch-Paced, a training-free method that jointly optimizes the allocation of decoding compute across requests to improve overall batch quality. Across two dLLM backbones, five benchmarks and their representative mixtures, Batch-Paced improves batch performance under matched budgets; gains generally grow with batch size and largely persist across decoding configurations. Analysis of requests' decoding trajectories suggests that these gains arise largely by raising the committed-token confidence of lower-confidence requests. We further show that Batch-Paced's batch decode time remains competitive and that adding a decoding-depth allowance during Batch-Paced decoding can shorten it further at a modest performance cost.

cs.CL↗
arXiv2026

Conditional Multi-Event Temporal Grounding in Long-Form Video

Multimodal large language models have made rapid progress in video temporal grounding, yet real-world applications routinely require localizing every event that satisfies compositional temporal and spatial conditions. Existing benchmarks fall short: they localize only a single moment per query, count without temporal conditions, or treat grounding and counting as disjoint tasks. We introduce CoMET-Bench for Conditional Multi-Event Temporal Grounding in long-form video, comprising 2789 queries over 600 videos averaging 33.8 minutes across five real-world domains, with each query composed from 4 temporal conditions, 3 spatial conditions, and a dedicated negative-query subset. We further propose a unified evaluation protocol jointly measuring counting, grounding, and negative-query recognition, including a new Rejection-F1 metric that prevents trivial gaming by lazy "always-empty" models. Benchmarking a broad suite of MLLMs, agent-based, and grounding-specialized methods reveals that existing approaches remain far from solving this task. Building on these findings, we propose CoMET-Agent, a training-free agentic framework that reformulates the task as structured search-and-aggregate, improving F1@0.5 by 6.1% over GPT-5 purely through structural reasoning. Failure analysis further surfaces three open directions: fine-grained entity tracking, position-uniform retrieval, and causal event pairing.

cs.CV↗
arXiv2026

Photometric Identification and Dynamical Purification of Blue Horizontal Branch Stars in DESI MWS DR1

Blue horizontal-branch (BHB) stars are ideal tracers for mapping the structure of the Galactic stellar halo. However, traditional spectroscopic identification is limited by data quality and sample size, while broad-band photometric methods often achieve only moderate completeness and purity. Building upon the color-space BHB identification method of \citet{2025ApJS..278...62H}, we synthesize SkyMapper $(u,v,g,z)$ photometry from DESI MWS DR1 spectroscopy and identify 9,237 BHB candidates in the $(g-z)_0$--$(u-v)_0$ color space using the HDBSCAN clustering algorithm. We then construct a Kernel Density Estimation (KDE) Bayesian probability model with capture-recapture (C-R) prior to assign posterior membership probabilities, achieving a probability-weighted purity of 88.9\% and completeness of 94.2\%. Applying an escape-velocity cut based on the Galactic gravitational potential, we remove 1,461 contaminants with unphysical kinematic parameters, yielding a clean photometric BHB sample $\mathcal{S}_c$ of 7,776 stars (retention rate $R_{\rm keep} = 84.2\%$). Systematic analysis of the contaminants reveals that they are predominantly faint sources ($g\sim20$~mag) with very low signal-to-noise ratios (median SNR~$<$~5). When the BHB color--luminosity relation is incorrectly applied to these objects, their space velocities are amplified beyond the Galactic escape limit, confirming that the escape-velocity filter essentially acts as a physical detector of low-SNR--driven distance inflation.

astro-ph.GA↗
arXiv2026

TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning

Low-precision execution can substantially accelerate reinforcement learning (RL) for large language models, but discrepancies between learner and sampler execution can destabilize policy optimization. In this paper, we characterize the interaction between mismatch and the policy-gradient direction, distinguishing locally amplifying from contracting update contributions that mismatch magnitude alone cannot identify. In native NVFP4 runs, we observe an early imbalance between the two amplifying regions, favoring negative-advantage, negative-gap updates. Their tail tokens become concentrated in a small fraction of response segments before mismatch spreads globally. Motivated by these findings, we introduce TRIAGE, a direction-aware stabilization method that uses segment-level diagnosis to selectively rebalance policy-gradient updates and applies bounded repair to residual severe mismatch. TRIAGE modifies the optimization objective while retaining native NVFP4 weight-and activation 4-bit (W4A4) forward execution on both the sampler and learner. Experiments on Qwen3-4B and Qwen3-30B-A3B show stable optimization throughout the evaluated training horizon and achieve full precision level performance across five mathematical reasoning benchmarks, while native NVFP4 with TRIAGE provides up to 2.3x higher rollout throughput than BF16.

cs.LG↗
arXiv2026

Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation

Prompt learning is a popular method for adapting foundation models, but learned prompts are typically task-specific and fail to generalize to new classes, domains, or compositions of tasks. In this paper, we introduce a Diffusion Meta-Prompt (DMP) model , a framework that models the distribution of learned prompts using diffusion models. Given a repository of previously learned prompts, DMP is trained and sampled without access to the original task examples or task losses, and synthesizes new prompts conditioned on natural language task descriptions. To improve the sampling stability, we introduce a test-time steering strategy for DMP, which uses the best training-selected prompt in the repository as a latent anchor during diffusion sampling, without retraining the DMP or accessing test classes. DMP improves generalization across classification, retrieval and text-to-image generation tasks, supports concept composition and negative prompting without explicit training. It reduces storage and inference costs by over 90% compared to prompt retrieval methods. For composite classification, DMP achieves upto 2.0% average gain over prior meta-learning methods across 55 pairs of datasets with gains as high as 8.5% on specific pairs such as Eurosat and Flowers. DMP also enhances cross-task generalization with ~2-9% improvement for hierarchical classification task. We further provide a theoretical guarantee bounding the expected task loss of prompts sampled from a DMP. Code is available: https://github.com/DeepakSridhar/dmp

cs.CV↗
arXiv2026

Cooperative STT and SOT switching in perpendicular magnetic tunnel junctions: Role of the pulse-end magnetization state

Spin--orbit torque MRAM (SOT-MRAM) is a leading candidate for next-generation nonvolatile memory, offering high speed, endurance, and architectural compatibility. However, in conventional SOT switching, the magnetization remains near the in-plane region at pulse termination, making the final state highly sensitive to post-pulse relaxation dynamics and prone to back-switching. To overcome this, we propose a field-free scheme in which the transverse SOT drives large-angle precessional excitation while the perpendicular spin-transfer torque (STT) biases the trajectory toward the reversed $-z$ state. Micromagnetic simulations reveal a nonlinear switching boundary in the $J_{\mathrm{STT}}$--$J_{\mathrm{SOT}}$ parameter space, originating from the distinct dynamical roles of the two torques: SOT primarily governs the excitation and crossing of the dynamical separatrix, whereas STT controls the terminal trajectory and final-state selection. An analytical macrospin model, based on the stability analysis of the current-induced equilibrium, reproduces the critical-boundary trends as functions of current density, Gilbert damping $α$, and uniaxial anisotropy $K_\mathrm{u}$, and distinguishes dynamic anti-damping and static instability branches. Systematic analyses of pulse duration, damping, anisotropy, and the STT--SOT balance further demonstrate that reliable ultrafast switching requires not only sufficient excitation to cross the separatrix before pulse termination, but also precise control of the pulse-end magnetization state to minimize post-pulse relaxation. These results establish that the pulse-end state, rather than the instantaneous torque amplitude, is the decisive factor governing switching speed and reliability in coupled STT--SOT systems.

cond-mat.mes-hall↗
arXiv2026

Tunable Ultrastrong Magnon-Magnon Coupling and Squeezed States in a Triaxial Van der Waals Antiferromagnet

Achieving and quantifying ultrastrong magnon-magnon coupling (USC) remains a key challenge for quantum magnonics. Here, we demonstrate widely tunable USC between chiral (right- and left-handed) and acoustic or optical magnon modes in the van der Waals antiferromagnet $CrPS_4$. Using a full quantum model, we decompose the interaction into three microscopic interaction channels: the co-rotating term $g_1$ (mode hybridization), the counter-rotating term $g_2$ (two-mode squeezing), and, uniquely in the chiral regime, the self-squared term $g_3$ that mediates single-mode squeezing. The normalized coupling ratio reaches $g/f_g$ $\sim$ 0.41, entering the USC regime. Most significantly, we establish a complete protocol linking these USC parameters to a measurable quantum phenomenon: a squeezed magnon vacuum state. Our simulations not only visualize the chirality and polarization evolution of the hybrid modes but also demonstrate how to directly extract quadrature fluctuations and a substantial squeezing factor (up to $\sim$ 9.7 dB) from thermal noise-driven magnetization dynamics. This work provides a material-specific quantum framework for USC and a practical pathway to detect and exploit non-classical magnon states in low-damping two-dimensional magnets, opening a route toward quantum-enhanced spintronics and hybrid quantum information platforms.

cond-mat.mes-hall↗
arXiv2026

Gamma: Grounded Multi-Agent Memory with Mechanical Audit for Memory-Intensive Manipulation

Pretrained vision-language-action (VLA) policies fail on memory tasks, behaviour that depends on events observed long before the current frame, because their training data is overwhelmingly Markov and mapping episodic memory directly to action chunks is hard. Yet the same policy, finetuned once to follow a privileged oracle's grounded-subgoal text, nearly solves these tasks: the difficulty lies entirely in mapping memory to a grounded symbolic subgoal. Existing work entrusts this stage to a single VLM that selects keyframes and reasons over raw frames, and falls far short of the oracle: key identities and dynamics are buried in noisy pixels, the reasoning spans hundreds of frames in an unbounded context, and hallucination corrupts the memory itself. We instead present GAMMA (Grounded multi-Agent Memory with Mechanical Audit), which builds the stage as a collaborating two-agent memory system: a detector tool (SAM-3) for spatial grounding, a VLM writer that distils each replan window into one grounded text line, an append-only text memory bank, and a VLM reasoner that reads the bank and emits the next grounded subgoal at the oracle's cadence, wrapped in a propose-verify harness that admits, defers, corrects, or rejects every agent claim against mechanical visual evidence, at training-corpus construction and at deployment alike. On a sixteen-task memory-manipulation suite GAMMA recovers a large fraction of the oracle ceiling with the policy held fixed, reaching the ceiling on several tasks, and transfers with unchanged contracts to a second benchmark.

cs.RO↗