arXiv subjects

Haoran Wang

Publications and source records attributed to Haoran Wang.

At least 19 recordsLinked to original sources

arXiv2026

Long-Time Dispersion and Threshold Resonances for the Landau Hamiltonian on the Hyperbolic Plane

A uniform magnetic field completely suppresses long-time dispersion for the Euclidean Landau Hamiltonian. We show that negative curvature fundamentally changes this behavior. For the Landau Hamiltonian with arbitrary field strength $B\in\mathbb R$ on the hyperbolic plane $\mathbb H$, we establish sharp dispersive estimates for the Schrödinger evolution on the absolutely continuous spectral subspace. The decay is $|t|^{-1}$ at short times and, strikingly, improves to $|t|^{-3/2}$ at large times whenever $B\notin\frac12+\mathbb Z$. At half-integer fields, we identify a threshold resonance and isolate its leading contribution, which yields the slower but sharp rate $|t|^{-1/2}$. Thus the long-time dynamics exhibit a resonance-driven dichotomy with no analogue in the flat constant-field problem. Our analysis is based on an explicit representation of the magnetic Schrödinger kernel together with a precise separation of the Landau levels and threshold profile. As a further consequence, for every nonthreshold field we obtain global-in-time Strichartz estimates on the absolutely continuous spectral subspace throughout the full hyperbolic admissible region.

math.AP↗

arXiv2026

GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data

Dialectal Arabic speech recognition remains constrained by the scarcity of dialect-resolved transcribed speech despite the abundance of web audio. We introduce GigaSpeech 3, a corpus of 39,000 hours and 10 million weakly transcribed speech segments covering Algerian, Egyptian, Iraqi, Saudi, and Syrian Arabic. Starting from 60 hours of manual transcription per dialect, we train labeling models using speech-recognition-biased self-supervised learning and apply them to dialect-matched web audio. Data selection and four rounds of noisy-student refinement for Saudi and Syrian Arabic yield the final corpus. We validate its utility through dialect-specific and multi-dialect speech recognition training and cross-domain evaluation. On GigaSpeechBench, the final dialect-specific models outperform their labeling models across all five dialects and achieve a macro-average word error rate of 23.86%, a 16.6% relative reduction from the strongest third-party system covering all five dialects, while outperforming the best third-party result on three dialects. A multi-dialect model using self-predicted dialect identities achieves a macro-average word error rate of 25.51% while also supporting Modern Standard Arabic. Across eight conditions from three external corpora, a GigaSpeech 3-trained Zipformer achieves the lowest word error rate among six evaluated models in every condition, while adapting the Qwen3 speech recognizer on GigaSpeech 3 improves performance across all eight conditions. We release the corpus and recipes as a foundation for dialect-aware Arabic speech processing.

cs.CL↗

arXiv2026

Beyond Trial-and-Error: A Geospatial-Guided Active Reasoning Framework for Robust Aerial Vision-and-Language Navigation

Aerial Vision-and-Language Navigation (VLN) requires UAVs to locate language-specified goals in large-scale urban environments, where objects often appear small and visually ambiguous from high-altitude viewpoints. Existing methods largely follow a reactive paradigm common in indoor VLN, repeatedly updating navigation states from local observations while underutilizing the geospatial structure that remains stable during navigation. As a result, visually similar distractors can cause a reactive goal search to repeatedly reinforce locally plausible goal hypotheses based on passively accumulated evidence, leading to unreliable localization. To address this, we propose GeoReasoner, a robust framework that shifts the paradigm of Aerial VLN from reactive trial-and-error to geospatial-guided active reasoning. Specifically, GeoReasoner first performs pre-search geospatial reasoning to derive region-level priors and constrain the goal hypothesis space. Building on these, it further conducts hypothesis-driven exploration to actively acquire discriminative evidence and refine competing goal hypotheses. Finally, consistency-aware goal verification adversarially assesses complementary evidence sources before stopping, hence reducing premature or erroneous goal confirmations. Experiments on the real-world CityNav benchmark demonstrate that GeoReasoner sets a new SOTA among zero-shot Aerial VLN methods while competing favorably with supervised approaches.

cs.CV↗

arXiv2026

Homological branching laws for $p$-adic and mod $p$ representations of ${\rm GL}_2$ over a $p$-adic field

Let $F$ be a finite extension of $\mathbb Q_p$ and $p\geq 5$. In this paper, we establish homological branching laws for mod $p$ representations of $\mathrm{GL}_2(F)$ restricted to split and nonsplit maximal tori, treating principal and special series and, when $F=\mathbb Q_p$, supersingular representations. We determine the derived Hom-complexes in both orders for nonexceptional characters. At exceptional characters, we calculate their Euler--Poincaré characteristics under a $p$-torsion-freeness hypothesis. We also establish corresponding results for a class of unitary Banach space representations.

math.RT↗

arXiv2026

On multilinear forms for mod $p$ representations of $\operatorname{GL}_2$ over a $p$-adic field

Let $F$ be a finite extension of $\mathbb Q_p$, for any prime $p$, and let $L/F$ be a ramified quadratic extension. We compute the spaces of $\mathcal O_L^\times$-equivariant linear forms on the representation $\operatorname{ind}^G_{KZ}σ/(Φ-λ)$. The only nonzero cases arise from one-dimensional quotients. Consequently, the restriction of an infinite-dimensional irreducible smooth mod $p$ representation of $\operatorname{GL}_2(F)$ with a central character to $\mathcal O_L^\times$ has no character quotient. We apply this vanishing result to show that a finite tensor product of smooth mod $p$ representations of $\operatorname{GL}_2(F)$ admits no nonzero invariant linear form whenever at least one factor is infinite-dimensional and irreducible with a central character.

math.NT↗

arXiv2026

World2HOSI: A Multi-Expert Harness for Long-Horizon Human-Object-Scene Interaction Generation

Long-horizon human-object-scene interaction (HOSI) is central to embodied AI, animation, and game development. Existing human-object interaction (HOI) and human-scene interaction (HSI) models excel in their respective domains, but none alone covers tasks requiring multiple interaction skills. Training unified HOSI models is hindered by scarce and costly data. We introduce World2HOSI, a multi-expert orchestration harness that generates continuous HOSI data from 3D Gaussian Splatting (3DGS) scenes and natural language instructions. Our key insight is that long-horizon HOSI hinges not on a stronger single model but on orchestration. Given a shared, structured scene state and an orchestration harness grounded in it, existing experts can jointly accomplish tasks beyond the reach of any of them alone. World2HOSI realizes this insight as a closed loop around a persistent scene state built from decoupled background and object assets. A harness plans action stages over this state, invokes experts via their native conditioning interfaces, and writes each action's effects back, so that every invocation is grounded in the evolving world. To reduce physical artifacts, bounded residual optimization and contact-driven physics simulation further ensure the physical plausibility of human motion and object manipulation, respectively, while preserving interaction intent. Experiments and a perceptual user study show that World2HOSI achieves the best task completion and interaction quality on the evaluated HOSI tasks, while generating more diverse data.

cs.CV↗

arXiv2026

RUSplatting: Robust 3D Gaussian Splatting for Sparse-View Underwater Scene Reconstruction

Reconstructing high-fidelity underwater scenes remains a challenging task due to light absorption, scattering, and limited visibility inherent in aquatic environments. This paper presents an enhanced Gaussian Splatting-based framework that improves both the visual quality and geometric accuracy of deep underwater rendering. We propose decoupled learning for RGB channels, guided by the physics of underwater attenuation, to enable more accurate colour restoration. To address sparse-view limitations and improve view consistency, we introduce a frame interpolation strategy with a novel adaptive weighting scheme. Additionally, we introduce a new loss function aimed at reducing noise while preserving edges, which is essential for deep-sea content. We also release a newly collected dataset, Submerged3D, captured specifically in deep-sea environments. Experimental results demonstrate that our framework consistently outperforms state-of-the-art methods with PSNR gains up to 1.90dB, delivering superior perceptual quality and robustness, and offering promising directions for marine robotics and underwater visual analytics. The code of RUSplatting is available at https://github.com/theflash987/RUSplatting and the dataset Submerged3D can be downloaded at https://zenodo.org/records/15482420.

cs.CV↗

arXiv2026

HelpMeOut: A Neuropsychology-Grounded Benchmark for Error-Aware Monitoring of Household Task Execution

We introduce HelpMeOut, an embodied AI benchmark for error-aware monitoring of household task execution. Existing embodied household benchmarks typically assume that humans execute tasks correctly, but this assumption does not hold for cognitively impaired persons or older adults whose everyday activities produce structured execution errors. To address this gap, HelpMeOut operationalizes research on everyday action errors into 20000 paired activity episodes, covering nine neuropsychologically motivated error categories. In each episode, agents observe a streaming human activity trajectory and must monitor whether the execution is unfolding correctly, diagnosing any structured errors as early as possible. We evaluate learned-monitor, symbolic, change-point, and frontier LLM prompting baselines. Results show that these methods perform poorly as error monitors, often missing when execution goes wrong. These results suggest a gap left by standard goal-inference and task-completion benchmarks, making HelpMeOut a testbed for error-aware assistive agents.

cs.RO↗

arXiv2026

Preliminary Exploration of Large Models Based on Self-Supervised Learning for Health Monitoring of Power Electronic Converters

Current artificial intelligence (AI) methods for power electronics converters make limited use of the abundant unlabeled data generated during real-world operation. This underexplored resource holds significant potential for advancing model performance. To address this gap, this paper presents PE-TSFM, a time-series foundation model tailored for power module health monitoring. The model adopts the PatchTST architecture combined with self-supervised learning and is trained on more than 143 million timestamps, where over 98\% of this training data is unlabeled and collected directly from an operating traction converter. In degradation classification tasks, PE-TSFM achieves an accuracy of 87\%, considerably surpassing five conventional time-series AI models whose performance ranges from 27\% to 45\%. These results demonstrate the model's strong few-shot learning capability and generalization across different operating conditions. This work promotes a shift from narrowly focused models in power electronics toward unified, scalable foundation models that can unlock value from large-scale unlabeled operational data.

eess.SY↗

arXiv2026

I2O2I-Nav: A Benchmark with a Modular Agent for Long-Horizon Indoor-to-Outdoor-to-Indoor Navigation

Service and delivery robots often need to complete long-horizon navigation missions spanning indoor and outdoor environments. Existing embodied navigation benchmarks primarily evaluate isolated stages or partial cross-domain journeys, providing limited support for assessing how heterogeneous navigation capabilities compose under continuous execution. We introduce I2O2I-Nav, a physics-enabled benchmark of 20 real-world composite scenes spanning over 115,000 square meters across multiple buildings and floors, with aligned 3DGS rendering and collision geometry. Its three-level evaluation progresses from independent primitives to two-stage compositions and complete four-stage I2O2I missions. Each stage starts from its predecessor's actual endpoint, while stage-conditional metrics track completion and localize failures along the mission. We further propose the MODULAR-Agent that coordinates frozen navigation policies through completion verification, stage handoffs, and bounded recovery. Evaluation across 1,374 episodes highlights the difficulty of continuous composition. The MODULAR-Agent achieves 40.5-76% success on individual primitives, but full I2O2I success remains low. Compared with a fixed policy chain using the same underlying policies, it more than doubles success on both Indoor-to-Outdoor (I2O) and Outdoor-to-Indoor (O2I), while improving full-mission success from 1.15% to 4.02%. Stage-wise analysis shows that the MODULAR-Agent enables more missions to reach the final object-navigation stage, where conditional success remains low, revealing challenges in both long-horizon stage execution and completion decisions.

cs.RO↗

arXiv2026

Constant-Loss Round-Preserving Direct Sums for Information Complexity

Strong direct-sum theorems relate the information needed to solve many independent instances of a communication problem to the information needed for one instance. For Gap-Majority composition, an optimal information bound was previously known, but preserving the number of communication rounds incurred an additional logarithmic loss. We prove a round-preserving Gap-Majority lemma with constant additive information loss, independent of both the number of instances and the number of rounds. More generally, we establish a variance direct-sum theorem for additive square-integrable observables over product distributions. For protocols with a bounded number of terminal answer values, the extracted single-coordinate protocols preserve the round budget, and their average information cost is at most the original information cost divided by the number of coordinates, plus a term depending only on the answer alphabet and the allowed variance loss. The proof uses centered counterfactual conditional means and a global variance amortization argument. Rather than encoding absolute conditional means for every possible terminal answer, we encode the information not already determined by the common view. The total squared innovation is controlled by a telescoping variance potential, yielding an information loss independent of the number of coordinates. We also derive same-round mean-square estimation bounds for arbitrary terminal outputs.

cs.CC↗

arXiv2026

Geometry beneath the Waves: Dense Priors for Sparse-View Underwater 3D Gaussian Splatting

Underwater 3D reconstruction remains challenging under sparse views, where scattering, absorption, and suspended particles degrade feature correspondences and geometric estimation. Although feed-forward geometry foundation models offer an alternative to conventional Structure-from-Motion, their direct application underwater produces noisy and fragmented geometry that limits subsequent 3D Gaussian Splatting (3DGS). We propose a sparse-view underwater reconstruction framework that adapts feed-forward geometry to underwater degradation and exploits its dense geometric priors for view synthesis. First, we adapt VGGT using LoRA and teacher--student distillation, training on synthetically degraded underwater images while preserving clean geometric supervision. This improves robustness to underwater appearance distortions without modifying the pretrained prediction heads. Second, the predicted dense geometry initialises an intermediate 3DGS representation that generates geometry-guided pseudo-views, increasing view overlap and strengthening feature tracks for subsequent RUSplatting optimisation. Experiments on SeaThru-NeRF and Submerged3D demonstrate improved reconstruction quality under sparse-view conditions. On SeaThru-NeRF, our method improves RUSplatting from 24.37 to 27.11 dB PSNR and increases SSIM from 0.7611 to 0.8634, while achieving the best average PSNR and LPIPS on Submerged3D. These results demonstrate the potential of domain-adapted geometric priors for robust sparse-view underwater 3D reconstruction.

cs.CV↗

arXiv2026

DA-GRD: Decision-Aware Grasp-Relevant Disambiguation for tactile recovery under perception-to-execution mismatches

Grasping is a fundamental robotic capability that bridges perception and physical task execution. This paper studies grasp pose recovery under a perception-to-execution mismatch, where a grasp generated from visual perception may become spatially stale if the object moves before execution, using only sparse tactile interactions and no further visual observations. We propose DA-GRD, Decision-Aware Grasp-Relevant Disambiguation, which maintains a weighted planar belief over possible object configurations and selects tactile probes according to their ability to eliminate hypotheses and improve agreement among candidate task grasps. Rather than fully relocalizing the object, DA-GRD stops when the remaining hypotheses support a common executable grasp. In MuJoCo experiments on ten rigid objects with translations up to 5~cm and yaw perturbations up to $\pm45^\circ$, DA-GRD achieves an 84.7% physical lift success rate, compared with 9.1% for stale AnyGrasp, 21.2% for the original fix-scan baseline, and 63.7% for fix-scan method adapted with an SE(2) belief. DA-GRD also achieves a 57.3% Task conditioned Success rate. Across objects, it uses a success-average of 4.13 tactile probes over the ten per-object means, corresponding to a 72.5% reduction relative to the fixed 15-probe baselines. Real-world experiments on six objects achieve 71.7% physical lift success and 38.3% task-conditioned success with 4.20 probes on average. These results show that tactile sensing can recover task-relevant grasps under vision-off conditions with limited physical interaction, without requiring complete object localization.

cs.RO↗

arXiv2026

OceanXL: Large-scale Underwater 3D Gaussian Splatting via Block Partitioning and Adaptive Pruning

Underwater 3D reconstruction is critical for marine exploration, ecological monitoring, and subsea infrastructure inspection, yet remains challenging at large scale due to light attenuation, scattering, and limited capture coverage. While 3D Gaussian Splatting (3DGS) enables high-quality real-time rendering, its application to large underwater scenes is constrained by high memory consumption and inefficient optimization over extensive areas. We propose OceanXL, a fast and scalable 3DGS-based framework for large-scale underwater reconstruction. OceanXL adopts a divide-and-conquer strategy, partitioning scenes into spatially coherent blocks to enable efficient optimization while preserving global geometric consistency. We further introduce an adaptive pruning scheme tailored to underwater conditions that removes redundant primitives, producing compact representations without sacrificing visual fidelity. Together, these components improve training efficiency and rendering performance for large scenes. We also introduce a large-scale underwater dataset covering diverse marine environments. Experiments on five large-scale scenes demonstrate favorable scalability, compactness, and efficiency--quality trade-offs over large-scene baselines. Controlled comparisons on the small-scale SeaThru-NeRF dataset further show competitive reconstruction quality with substantially smaller model sizes than underwater-specific methods.

cs.CV↗

arXiv2026

The Sharp Rényi and Tsallis Threshold in the Shepp--Olkin Concavity Problem

Let $B_1,\ldots,B_n$ be independent Bernoulli random variables with parameters $p_1,\ldots,p_n$, and let $S=\sum_i B_i$. Hillion and Johnson proved that the Shannon entropy of $S$ is jointly concave in the parameter vector and proposed corresponding critical-order conjectures for R'enyi and Tsallis entropies, with predicted thresholds $2$ and approximately $3.65986$, respectively. We determine both thresholds exactly. For every $0 1$, joint concavity fails already for the sum of two Bernoulli variables: a transverse interpolation in which the two parameters move in opposite directions gives strict local convexity for both entropies. Hence the universal joint-concavity range for both families is exactly $0<q\leq 1$. Below order one, the proof combines the Hillion--Johnson transport inequality with an explicit nonlinear telescoping correction. The corrected local curvature reduces to a two-dimensional quadratic form. An exact Riccati identity, together with a one-sided zero-crossing argument, proves positivity of its determinant throughout the full range $0<q<1$.

cs.IT↗

arXiv2026

A Majorana Formulation of Time-Dependent Two-Particle Reduced-Density-Matrix Dynamics

We introduce a time-dependent two-particle (TP) reduced-density-matrix algorithm for systems of interacting Majorana fermions. We close the BBGKY hierarchy at the two-particle level by reconstructing the three-particle reduced density matrix from lower-order correlations. To stabilize the evolution, we impose a positivity projection on the two-particle density matrix while preserving chosen conserved quantities such as the energy. We benchmark the approach on quenches in the one-dimensional Hubbard model and on flux dynamics in the Kitaev honeycomb model. For the Hubbard quench, TP captures strong-coupling dynamics missed by Hartree--Fock (HF). For the Kitaev quenches, TP accurately reproduces the early-time flux dynamics in several regimes and provides a substantial improvement over HF when two-particle correlations are important. We further show that gauge coherence is essential for flux dynamics. The projection procedure however introduces an effective irreversibility, which affects the long-time dynamics.

cond-mat.str-el↗

arXiv2026

When Label Noise Meets Class Imbalance: A Robust Framework for Android Malware Family Classification

Machine learning methods for Android malware family classification have achieved high accuracy, but their application is hindered by two major challenges. First, the widely used code obfuscation severely disrupts the automated labeling process and introduces substantial label noise into training datasets. Second, training datasets often exhibit severe class imbalance, leading to poor performance of family classification models. Although existing studies have proposed various solutions to either label noise or class imbalance, they often overlook the interplay between these two factors. Under class imbalance, the presence of hard-to-learn minority-class samples can significantly impair the effectiveness of existing countermeasures for noisy samples. To jointly address label noise and class imbalance, we propose a robust Android malware family classification framework, RoMaC. It employs a self-training strategy to correct noisy labels and, more importantly, discriminately treats head-family and tail-family samples. This design effectively mitigates the adverse impact of class imbalance on noise-robust learning. Moreover, RoMaC integrates a class reweighting mechanism with multi-model ensemble learning, thereby enhancing both classification accuracy and noise robustness. We evaluate RoMaC on a combined dataset constructed from two public datasets. When 30% of the samples are obfuscated, RoMaC achieves an overall Macro-F1 score of 0.803 and an accuracy of 0.871, as well as a tail-class Macro-F1 score of 0.672 and an accuracy of 0.784. Compared with existing methods, RoMaC demonstrates performance improvements of 6%-20% across various obfuscation scenarios and noise levels.

cs.CR↗

arXiv2026

Sharp High-Entropy Bounds for Sums of Independent Discrete Random Variables

Sharp high-entropy lower bounds for the entropy of a sum were known for identically distributed summands in torsion-free abelian groups and in prime cyclic groups. For arbitrary independent summands, Gavalakis, Goh and Kontoyiannis obtained an additive constant of $1/8$ and conjectured that the sharp constant is $1/2$. We prove that independent discrete random variables $X,Y$ with finite Shannon entropies satisfy $H(X+Y)\ge (H(X)+H(Y))/2+1/2-o(1)$ in every torsion-free abelian group as $\max{H(X),H(Y)}\to\infty$. The same conclusion holds in the prime cyclic group $\mathbb F_p$ when both $\max{H(X),H(Y)}$ and $\log_2 p-\max{H(X),H(Y)}$ tend to infinity. We give explicit error bounds in both settings. The proof extracts a component with paired point probabilities while controlling the entropy of the remainder independently of its support. Discrete rearrangement and uniform perturbation then transfer the continuous entropy power inequality to this component. In prime cyclic groups, an additional estimate controls the entropy lost under modular reduction. Binomial distributions show that the constant $1/2$ is optimal.

cs.IT↗