Searcharxiv⌕ Search

arXiv subjects

Sheng Yang

Publications and source records attributed to Sheng Yang.

At least 19 recordsLinked to original sources
arXiv2026

A temporally clustered gravitational wave pair and a Type IIb supernova

Compact object mergers are generally expected long after the stellar collapse that forms their remnants. Here we report two marginal gravitational wave (GW) candidates, S190910d and S190910h, separated by 7.1 hr, whose three-dimensional localizations overlap at the position and distance of the Type IIb supernova SN 2019rsq. The GW pair lies in the extreme tail of the joint distribution of temporal separation and localization overlap, with a pairwise null probability of $7.6 \times 10^{-5}$ under our Monte Carlo null test. Independent re-analyses recover both as signal-like candidates. Under a common-origin hypothesis, S190910h remains consistent with a low-mass compact binary with source-frame masses near $2.5 + 1.3\,M_\odot$, whereas S190910d favours a strongly asymmetric $\sim 34 + 3\,M_\odot$ system whose observed amplitude is compatible with the supernova distance. SN 2019rsq is a rapidly evolving stripped-envelope Type IIb explosion whose light curve is consistent with stellar collapse occurring near the GW activity. Although the supernova coincidence alone is not statistically rare, its timing and physical properties provide a stellar collapse anchor for the unusual GW pair. A fragmenting collapsar disk provides a plausible framework that can accommodate the component masses, hour-scale delays and supernova properties, raising the possibility that multiple compact object mergers can accompany a single stellar collapse episode.

astro-ph.HE↗
arXiv2026

Evaluating the Robustness of Proof Autoformalization in Lean 4

Proof autoformalization aims to translate a mathematical informal proof in natural language into a formal proof in a formal language such as Lean 4. Existing LLM-based models for proof autoformalization are typically evaluated only on well-formed informal proofs from curated datasets. We argue that a robust proof autoformalizer must remain faithful even for informal proofs that diverge from these idealized ones, and we present the first study on the robustness of proof autoformalization models. We formulate two categories of perturbations: a global perturbation paraphrases the informal theorem-proof pair in a different style, under which the formalization should remain consistent; a local perturbation alters a value, symbol, or proof step, possibly in a counterfactual way, and a robust formalization should faithfully reflect the perturbation rather than reverting to the original or inferring a different one on its own. We build a benchmark with both perturbations on miniF2F and MATH-500, and automatically measure how stable a proof autoformalization's correctness is under global perturbations and how faithfully its output reflects local perturbations. We evaluate seven recent models: their correctness varies under global perturbations, and they mostly fail to remain faithful under local perturbations.

cs.CL↗
arXiv2026

Topological Quantum Criticality in Quasiperiodic Cluster Ising Chain

Topological classifications of quantum critical systems have recently attracted growing interest, as they go beyond the traditional paradigms of condensed matter and statistical physics. However, such classifications remain largely unexplored in aperiodic environments, particularly under quasiperiodic modulations. In this Letter, we uncover a family of topological quasiperiodic fixed points with critical scalings intermediate between the clean and infinite-randomness limits. By exactly solving the quasiperiodic cluster-Ising chain, we demonstrate that all phase boundaries separating quasiperiodically modulated phases are governed by topological Ising-like fixed points unique to strongly modulated quasiperiodic systems. Although their local bulk critical properties match those of conventional quasiperiodic Ising critical points reported before, these fixed points host robust topological edge degeneracies and exhibit a distinct symmetry-enriched realization of the quasiperiodic Ising criticality, as further supported by complementary lattice simulations.

cond-mat.stat-mech↗
arXiv2026

Topological Superradiant Universality Classes in Cavity-Mediated Spin Chains

Superradiant phase transitions are fundamental phenomena in light-matter coupled systems. Here, we uncover a novel class of superradiant criticality that is topologically distinct from previously known superradiant transitions. Using cavity-mediated cluster-Ising chains as an illustrative example, we numerically demonstrate that the critical line separating the superradiant phase from the cavity topological phase hosts robust symmetry-protected edge degeneracies, a feature absent in conventional superradiant transitions. Remarkably, although its local bulk critical properties are indistinguishable from those of the previously identified topologically trivial superradiant transition, the two criticalities cannot be smoothly connected without breaking the protecting symmetries or passing through a multicritical point. We further show that such topological superradiant criticality is generic, also occurring in cavity-mediated $\mathbb{Z}_{n}^{}$ cluster-qudit chains, as supported by complementary lattice simulations.

quant-ph↗
arXiv2026

Causal Spatiotemporal State Evolution for Monocular 4D Reconstruction

While feed-forward models excel in static 3D geometry estimation, extending them to dynamic 4D scenes requires modeling visual geometry as a causally evolving state. Current methods typically rely on unordered temporal aggregation, which lacks the directional structure of physical time. Furthermore, existing supervision often treats geometry and motion as disjoint objectives, failing to exploit their inherent physical coupling. Consequently, they lack a unified constraint to effectively supervise temporal state transitions, leading to inconsistent 4D scene representations. To address this, we propose a feed-forward framework for causal 4D visual geometry learning from monocular videos. At its core, Causal Spatiotemporal Mamba augments temporal aggregation with directional state propagation. Through complementary Temporal-Spatial and Spatial-Temporal Scans, CSM continuously propagates geometry-aware states across frames to model spatiotemporal evolution. To align this causal state evolution with observable dynamics, we introduce Unified Motion Supervision. Rather than treating motion as an independent objective, UMS leverages geometry-aware predictions from the camera and depth heads to construct a unified forward motion field that is consistent with the underlying 3D structure. This geometry-grounded supervision explicitly constrains inter-frame state transitions, enabling stable states propagation across frames. Extensive evaluations on dynamic benchmarks demonstrate state-of-the-art performance across video depth, camera pose, and optical flow estimation. These results validate that the synergy between the directional state propagation of Causal Spatiotemporal Mamba and Unified Motion Supervision effectively captures continuous scene evolution, significantly reducing temporal drift and reinforcing spatial-temporal consistency in 4D representation learning.

cs.CV↗
arXiv2026

Symmetry Enriched Criticality from Kennedy Tasaki Self-Duality

The interplay between topology and quantum criticality has established symmetry enriched criticality as a new paradigm beyond conventional frameworks in condensed matter and statistical physics. However, the conditions under which such criticality emerges remain poorly understood. In this work, we show that a broad class of symmetry enriched critical points separating symmetry protected topological (SPT) and spontaneous symmetry breaking (SSB) phases is governed by Kennedy Tasaki (KT) self duality. At these criticalities, the KT transformation that interchanges the SPT and SSB phases acts as a self-dual noninvertible symmetry, endowing the critical points with nontrivial topological characteristics. We numerically demonstrate this mechanism in $\mathbb{Z}_{n} \times \mathbb{Z}_{n}$ cluster qudit chains and further argue that it naturally extends to higher dimensions, providing a duality based criterion for identifying symmetry-enriched criticality across dimensions.

cond-mat.str-el↗
arXiv2026

SN 2025wiu: A Type Ib Supernova with Post-Peak Optical Rebrightening

We present optical photometric and optical/near-infrared spectroscopic observations of SN 2025wiu, a Type Ib supernova (SN) at z = 0.046927. The r-band light curve exhibits an initial maximum of approximately -18.2 mag, followed by a weaker optical rebrightening reaching approximately -17.8 mag at +38 days in the rest frame relative to the first maximum. However, the reconstructed bolometric light curve does not show a distinct second peak, but instead exhibits a reduced decline rate during the corresponding phase. The spectra consistently show Type Ib features without narrow emission components associated with circumstellar material. The late-time bolometric decline rate of 0.054 +/- 0.008 mag/day is faster than expected for complete trapping of 56Co decay. A radioactive-decay model for the first peak requires nickel mass = 0.47 solar masses, above the range typical of SNe Ib. A combined radioactive-decay and circumstellar-interaction model reproduces the full bolometric light curve with nickel mass ~ 0.38 solar masses, ejecta mass ~ 4.7 solar masses, and an effective circumstellar mass of ~ 0.10 solar masses, with the interaction contributing from the first peak onward. The lack of interaction signatures in the spectra favours an aspherical, disk-like circumstellar structure engulfed by the ejecta, in which the interaction energy is thermalized below the ejecta photosphere; the fitted circumstellar parameters are therefore effective values rather than direct measurements of the circumstellar geometry. SN 2025wiu demonstrates that optical rebrightening does not necessarily imply a genuine bolometric secondary maximum and highlights the importance of multi-band observations for identifying the powering mechanisms of double-peaked stripped-envelope supernovae.

astro-ph.HE↗
arXiv2026

FPD-Drive: Future Policy Distillation for End-to-End Autonomous Driving

End-to-end autonomous driving models are typically trained on real-world driving logs, which record only the trajectory actually executed in each scene. This provides limited supervision for learning alternative valid behaviors. Multi-target supervision can mitigate this limitation, but broader trajectory coverage makes safe candidate selection more challenging. We propose FPD-Drive, an end-to-end planner that distills privileged future knowledge into a visual driving policy to improve both multi-trajectory supervision and safety selection. Specifically, we introduce Future-Privileged Multi-Target Distillation to transfer diverse, high-quality trajectory targets from a teacher with access to recorded future observations to the student. These targets extend supervision beyond the single recorded human trajectory. For candidate selection, we further introduce Safety-Aware Score Correction to correct ranking errors between nearby safe and unsafe candidates and raise underestimated safety scores of safe candidates. At deployment, the student requires neither future observations nor teacher inference. Our base model achieves 94.9 PDMS on NAVSIM v1 navtest and 55.9 EPDMS on NAVSIM v2 navhard. The scaled FPD-Drive-Pro improves these scores to 95.5 PDMS and 58.1 EPDMS, respectively, achieving SOTA performance among the compared methods on both benchmarks. Zero-shot closed-loop evaluation on HUGSIM further yields an HD-Score of 45.1 and RC of 55.3.

cs.CV↗
arXiv2026

ABO-Med: Accelerated Bilevel Optimization for Few-Shot Medical Image Classification

In recent years, bilevel optimization has been widely used in a variety of machine learning tasks. However, prior bilevel optimization algorithms generally require the computation of second-order information, which limits their practical scalability. Only recently has a first-order paradigm for bilevel optimization been established, attaining near-optimal theoretical guarantees for solving bilevel optimization problems. In this paper, we propose ABO-Med, a scalable instantiation of this paradigm for few-shot learning, by incorporating it into the model-agnostic meta-learning (MAML) framework and tailoring it to medical image classification. We also introduce Medical Adaptive RandomAugment (MedRAug), a modality-aware augmentation strategy designed for medical images. Theoretically, ABO-Med establishes the optimality of MAML-type meta-learning approaches. Empirically, ABO-Med outperforms prior baselines on several public medical datasets, with gains of 1.99% to 18.76%, while MedRAug further improves the average accuracy by 2.20% to 6.34%. Additional cross-domain experiments, augmentation ablation studies, backbone ablation studies, and training efficiency analysis further validate the effectiveness and efficiency of the proposed method.

cs.CV↗
arXiv2026

DETECT: Real-Time Identification of Transients with DESI Spectroscopic Redshift

Wide-field surveys now report thousands of transients per month, while spectra are obtained for only a few per cent of them. We present DETECT (DESI--Transient Event Cross-matching Tool), a pipeline that turns each Transient Name Server (TNS) alert into a distance-informed candidate within an hour by placing it in the context of the Dark Energy Spectroscopic Instrument (DESI) archive. DETECT cross-matches every new report against the 22 million spectra of DESI EDR and DR1 through a HEALPix index, associates the transient with a host galaxy by a directional-light-radius rule whose morphology-dependent thresholds are calibrated on 4,474 supernovae with known redshifts (92.5% completeness, 0.4% wrong hosts), and passes ambiguous cases to a reviewer through a web interface. With a validated host redshift it derives the peak absolute magnitude, the projected offset and basic host properties of each event, and ranks it for spectroscopic follow-up. Applied retrospectively to ~1.2x10^5 TNS reports from 2020--2024, DETECT recovers a spectroscopic host for 15% of them, from these we build a Gold Sample of ~5,400 well-sampled light curves whose luminosity distributions by class reproduce those of untargeted surveys. Because the absolute magnitude is known at discovery, intrinsically overluminous events stand out immediately: in the prospective 2025 run this is how the lensed superluminous supernova SN~2025wny was flagged within hours of its report, and how faint, fast-declining kilonova candidates were screened against model grids and archival photometry. DETECT shows how an archival spectroscopic survey can make host redshifts a routine part of transient triage ahead of the Rubin Observatory's LSST.

astro-ph.HE↗
arXiv2026

Deterministic Smoothed MAP Detection for High-Dimensional MIMO Systems

We propose a deterministic smoothed maximum a posteriori (SMAP) framework for high-dimensional multiple-input multiple-output (MIMO) detection. The discrete constellation prior is approximated by an i.i.d. Gaussian mixture, yielding a differentiable MAP objective that retains the constellation structure while enabling continuous optimization. Unlike sampling-based approaches, SMAP formulates detection as a deterministic optimization problem and can be initialized by the output of an arbitrary detector, allowing it to operate either as a standalone detector or as a refinement stage. For hard detection, we introduce SMAP-KR, which complements the continuous solution with a local $K_R$-neighbor search evaluated according to the original maximum-likelihood metric. Annealed continuation improves robustness for higher-order constellations, while a two-neighbor approximation reduces the cost of evaluating the mixture prior. We further develop a soft-output SMAP method in which a local Gaussian approximation based on the curvature of the smoothed posterior provides symbol probabilities and bit log-likelihood ratios without posterior sampling or explicit counterhypothesis lists. Numerical results for critically loaded MU-MIMO systems show that SMAP-KR provides an increasingly favorable performance-complexity tradeoff as the system dimension grows and can also effectively refine the output of existing detectors. For coded transmission, soft SMAP provides substantial block-error-rate gains over both LMMSE- and K-best-based soft detection.

cs.IT↗
arXiv2026

A 32-day Quasi-periodic Modulation in the Post-peak Light Curve of the Superluminous Supernova SN 2018bsz

Recurrent structure in supernova (SN) light curves may reveal physical clocks associated with central-engine dynamics, binary orbital motion, or interaction with structured circumstellar material (CSM). We present a multiband photometric reanalysis of the nearby hydrogen-poor superluminous SN (SLSN-I) 2018bsz (z=0.0267), using Swift/UVOT and GROND observations spanning approximately 110 rest-frame days after maximum light. After independently modelling and subtracting the smooth decline in each band, Generalized Lomb-Scargle periodograms reveal recurrent residual variations at broadly consistent phases across ten bands from u to Ks. The strongest individual-band detections, in the g, r, i, z, and J bands, yield periods of 31.5-31.8 days, while the joint multiband analysis gives a rest-frame period of P=31.61 (+/-0.03) days. The modulation is traced over approximately three cycles and is therefore described as quasi-periodic. The signal is robust to the adopted detrending procedure, while comparison-star and lunar-cycle tests disfavour an observational systematic. The modulation is broadly phase-coherent from the optical to the near-infrared, but its amplitude increases towards shorter wavelengths; lower-significance bands also show possible wavelength-dependent shifts in the best-fitting period. The present observations do not uniquely determine the physical origin. Lense-Thirring precession, interaction with CSM structured before the explosion, and post-SN interaction with a surviving companion remain possible. SN 2018bsz provides one of the clearest examples of coherent, month-scale photometric modulation in an SLSN-I.

astro-ph.HE↗
arXiv2026

MM-Future: Multi-Mode Joint World-Action Modeling for Autonomous Driving

Autonomous driving involves coupled decision-making and scene evolution under multi-mode uncertainty. To capture this coupling and uncertainty, we introduce MM-Future, a world-action model that generates multiple paired scene-action hypotheses and models bidirectional interaction within each pair. Each hypothesis is initialized from a structured action prior and an independent future scene source, which are then co-evolved through a modality-aware diffusion Transformer. To support efficient multi-mode rollout, MM-Future compresses multi-view video into planning-oriented representations, dubbed MM-Tokens. Finally, a future-conditioned proposal scorer ranks trajectory candidates by shared history context and their paired predicted future. On NAVSIM navtest, MM-Future achieves 94.0 PDMS and 91.5 EPDMS, while attaining a 32.3 HD-Score in zero-shot closed-loop evaluation on HUGSIM. Ablations show consistent improvements over both single-mode and action-only variants, validating the benefit of multi-mode joint world-action modeling.

cs.CV↗
arXiv2026

Topological Tricritical Ising Universality Class in One Dimension

Quantum critical points can host symmetry-protected topological edge modes even when the bulk is gapless, giving rise to symmetry-enriched universality classes beyond the conventional Landau--Ginzburg--Wilson paradigm. Here we show that the tricritical Ising (TCI) critical point---described by a paradigmatic conformal field theory (CFT) with emergent supersymmetry---admits a topologically nontrivial, symmetry-enriched realization, which we term the topological TCI. We construct this critical point in the cluster O'Brien--Fendley spin chain by applying a symmetry-protected topological entangler to the original O'Brien--Fendley model. The two realizations therefore share the same bulk TCI CFT. Under open boundary conditions, however, the original model exhibits the free conformal boundary condition, whereas the cluster model exhibits a spontaneously fixed boundary condition: an infinitesimal boundary field can select one of the fixed boundary states, yielding spontaneous boundary magnetization. We further show that symmetry enrichment and boundary renormalization-group flow provide two physically distinct routes to the spontaneously fixed boundary condition. Whereas the free and spontaneously fixed boundary conditions of the original model can be interconverted by tuning a symmetry-preserving boundary term, no such conversion occurs for the cluster model along the boundary deformations studied here, even in the strong-deformation limit. Although they share the same conventional boundary CFT data, including the boundary operator content and boundary $g$-function, the two realizations of the spontaneously fixed boundary condition are distinguished by different time-reversal charges of the disorder field....

cond-mat.str-el↗
arXiv2026

Fast-BEV++: Fast by Algorithm, Deployable by Design

The advancement of vision-only BEV (Bird's-Eye-View) perception is hindered by the fundamental trade-off between perception accuracy and deployment efficiency. We introduce Fast-BEV++, resolving this tension through two principles: Fast by Algorithm and Deployable by Design. By decomposing view transformation into a hardware-oriented Index-Gather-Reshape pipeline, Fast-BEV++ eliminates custom kernels while achieving no less than 3 times speedup over baseline methods. Empirically, Fast-BEV++ establishes a new state-of-the-art accuracy-speed trade-off on nuScenes, achieving 0.488 NDS while sustaining real-time inference at over 134 FPS. In particular, depth supervision yields consistent and tangible performance gains, maintaining the highest accuracy among comparable methods. The decomposed architecture enables seamless real-time deployment on production-level platforms, eliminating hardware constraints without loss of efficiency. Code and models are released on the linked project page.

cs.CV↗
arXiv2026

Lightweight Soft X-ray Imager (LSXI) with glass-based coded mask

The coded mask technique has been widely used in X-ray and Gamma-ray imagers, especially in space astronomy. However, the traditional design of coded mask imagers usually has problems with large size and heavy weight. Here, we propose a novel design for a coded mask imager made of glass based on microchannel plate (MCP) technology, making it lightweight (within 1 kg), compact, and self-supporting, which is very suitable for space exploration satellites. The design is initially demonstrated by reconstructing encoded patterns from measurements at the X-ray beamline. Monte Carlo simulations of the module integrated into a 6U CubeSat are conducted to assess its in-orbit detector performance, including sensitivity and source localization.

astro-ph.IM↗
arXiv2026

Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning

Long-context LLMs and Retrieval-Augmented Generation defer state tracking and evidence consolidation to query time, which is brittle when facts evolve and answers depend on latent states. We introduce Unified Memory Agent (UMA) for a one-to-many setting: query-agnostic external memory is constructed once from a stream and reused across multiple future QA sessions. A single policy maintains a structured Memory Bank through CRUD operations and answers using both the Memory Bank and raw context. Task-Stratified GRPO uses the mean reward of QA trajectories branching from each sampled memory state to supervise memory maintenance, while normalizing memory and per-question QA groups separately. We also introduce Ledger-QA, a diagnostic benchmark for long-horizon state tracking over accumulated updates. At the 16k budget, UMA-Generalist achieves the highest average score among compared methods across the test-time-learning and accurate-retrieval benchmarks and transfers to Ledger-QA without task-specific training; UMA-Specialist further improves long-horizon tracking after task adaptation. These results support learned proactive memory management for long-context reasoning.

cs.LG↗
arXiv2026

USR-Drive: Unified Driving Scene Representation via Joint Denoising of 3D Gaussians and Boxes

Spatial representation learning for autonomous driving aims to map raw visual signals into structured 3D scene representations, where object-centric bounding boxes and rendering-oriented 3D primitives (\eg, 3D Gaussians) serve as two distinct yet highly complementary levels for scene understanding. Existing methods typically treat dynamic reconstruction and instance-level perception as separate tasks, despite their shared goal of estimating the underlying 3D world state. As a result, dynamic reconstruction is under-constrained while 3D detection lacks geometric grounding. To address this gap, we propose USR-Drive, a unified conditional generative framework that, given only posed multi-view driving videos, jointly recovers dense dynamic geometry and instance-level object layouts within a shared scene representation. Specifically, USR-Drive represents dense Gaussian primitives and sparse 3D bounding boxes as two aligned latent token streams and jointly denoises them with a unified multi-modal diffusion Transformer. Unlike prior paradigms that use boxes as external conditions or predict them with detached modules, USR-Drive treats them as mutually constrained state variables with a Unified Positional Encoding (UPE) that aligns heterogeneous tokens within a shared metric spatiotemporal coordinate. Via such unified representation and generative framework, the two modalities reinforce each other: geometry supplies dense metric evidence for box prediction, while boxes provide instance-level structural priors that help preserve spatial consistency and reduce ambiguity in sequential 3D geometric representation. Our approach successfully delivers state-of-the-art results for both dynamic reconstruction and 3D detection on the nuScenes and VKitti datasets.

cs.CV↗