Search arXiv⌕ Search

arXiv subjects

Jing Wang

Publications and source records attributed to Jing Wang.

At least 19 recordsLinked to original sources
arXiv2026

STEK: Structural-Terrain-Enhanced Koopman-Inspired Cross-Channel Regularization for Retrospective Battery Multi-Target Estimation

Retrospective battery characterization across heterogeneous cells is challenging because cycling records vary substantially with chemistry, protocol, cell format, capacity, and operating conditions. An endpoint charge--discharge curve captures the local condition of an evaluated cycle, while a cell-level lifecycle terrain summarizes structural evolution across the archived trajectory. We propose STEK, a structural-terrain-enhanced framework for retrospective battery multi-target estimation. STEK combines a cell-level lifecycle (dQ/dV) terrain with an endpoint-derived structural proxy through quality-proxy-conditioned gating. Bounded FiLM and a validity-gated residual head refine the endpoint-curve representation while preserving a curve-based prediction pathway. Battery-type and optional material-text representations further condition an identity-centered low-rank linear map, providing a Koopman-inspired cross-channel consistency objective without modeling temporal dynamics or performing rollout. Under the fixed seven-output MIX-battery protocol, the full retrospective setting improves aggregate performance over endpoint-only learned baselines across multiple temporal backbones; this comparison reflects both the additional archived context and the modeling design. Under matched auxiliary inputs, STEK outperforms direct concatenation and quality-unaware FiLM, while descriptor-removal tests show graceful fallback to the endpoint pathway. Deterministic rules remain preferable for directly recoverable capacity summaries. The method targets retrospective archive harmonization rather than online estimation from cycle t alone.

cs.AI↗
arXiv2026

Interaction-driven competing instabilities in two-dimensional checkerboard quadratic band crossing semimetals

Two-dimensional quadratic band crossing point (QBCP) semimetals serve as a fertile platform for interaction-driven quantum criticality, nevertheless, the role of the complete fermion-fermion interactions remains largely unexplored. To address this, we systematically investigate the low-energy physics of a spin-1/2 checkerboard-lattice QBCP semimetal by considering all 16 marginally short-range fermion-fermion interactions. Using the momentum-shell renormalization group, we derive the coupled flow equations, which reveal that the low-energy physics is governed by a series of fixed points. Depending on the initial conditions, the system may exhibit a single stable fixed point, several discrete fixed points, or three continuous groups of fixed points parameterized by a few variables. By introducing source terms and evaluating susceptibilities, we identify the dominant and subdominant instabilities. The leading phases include nematic spin-nematic (NSN), quantum anomalous Hall (QAH), chiral superconducting ($\mathrm{SC}_1$), and quantum spin Hall (QSH) orders. Moreover, several features distinguish our findings from previous simplified models. Off-diagonal interactions generate terms that promote orders absent in such models, the continuous groups allow systematic tuning of the leading instability, and trajectory-dependent instabilities emerge where the full RG flow, rather than the fixed point alone, determines the dominant state. These results offer a comprehensive theoretical understanding of low-energy quantum critical behaviors and phase instabilities in two-dimensional QBCP semimetals and related electron systems.

cond-mat.str-el↗
arXiv2026

Symmetry-protected isolation of the quantum metric in chiral type-II semi-Dirac semimetals

Quantum geometry, comprising the Berry curvature (BC) and the quantum metric (QM), underpins a wide array of topological and transport phenomena. However, in most solid-state platforms, BC and QM signals are inherently entangled, making their experimental separation highly challenging. Here, we demonstrate that the chiral limit of type-II semi-Dirac semimetals provides a symmetry-protected mechanism to cleanly isolate the QM. At the chiral limit where the spin-orbit gap $m_z=0$, chiral and $\mathcal{PT}$ symmetries strictly suppress the BC, its dipole (BCD), and the shift current, leaving the QM and its dipole (QMD) as the sole sources of the optical and nonlinear Hall responses. This pure-QM regime exhibits distinct experimental fingerprints, including a divergent longitudinal optical conductivity and a QMD-induced nonlinear Hall conductivity that exhibits a pronounced singularity as the chemical potential approaches the nodal point. Turning on a finite $m_z$ reactivates the BC channels, transitioning the system from a pure-QM phase into a mixed geometric phase. By deriving a scaling law for the nonlinear Hall conductivity, we establish a direct experimental strategy to separate the mixed Drude, BCD, and QMD contributions based on their distinct relaxation-time dependencies. Our findings identify chiral type-II semi-Dirac semimetals as highly tunable platforms for isolating and probing intrinsic quantum geometric effects.

cond-mat.mes-hall↗
arXiv2026

An Enhanced Isothermal Jeans Approach to Constraining Dark Matter Self-Interactions from Galactic Kinematics

We present an improved semi-analytical model to predict density profiles of self-interacting dark matter (SIDM) halos and apply it to constrain the self-scattering cross section using SPARC galaxy rotation curves. Building on the isothermal Jeans approach, our model incorporates (i) velocity-dependent cross sections, (ii) an empirical treatment of core collapse, and (iii) enhanced robustness for identifying solutions. These advances allow us to fit a large sample of galaxies, including systems with baryon-dominated centers often excluded in earlier studies. We find that roughly 1/6 of galaxies admit both a core-growth and a core-collapse solution, while the rest favor a unique evolutionary state. Joint constraints across the sample reveal clear velocity dependence: the allowed parameter space forms an L-shaped degeneracy, where both nearly constant, low cross sections ($σ_0\sim2\,{\rm cm}^2$/g, $ω\gtrsim500\,$km/s) and strongly velocity-dependent models ($σ_0\sim100\,{\rm cm}^2$/g, $ω\sim60\,$km/s) are viable. Adopting the core-growth interpretation yields best-fit values $σ_0\simeq5\,{\rm cm}^2$/g and $ω\simeq250\,$km/s. Our constraints are remarkably consistent with previous results derived from a variety of independent probes. Compared to cold dark matter (CDM) models, SIDM outperforms simple adiabatic-contraction profiles and rivals empirical feedback-based CDM profiles, yet shows no correlation with stellar-to-halo mass ratio, a proxy for feedback strength, offering a distinct explanation for dwarf galaxy diversity. Moreover, SIDM does not affect galaxy-halo scaling relations significantly and makes concentration systematically lower. Our results highlight SIDM as a compelling framework for small-scale structure, while future low-mass kinematic data will be crucial for breaking degeneracies in velocity-dependent cross-section models.

astro-ph.GA↗
arXiv2026

ROOF: Learning Humanoid Fall Recovery under Overhead Constraints

A fallen humanoid beneath an overhead obstacle faces a coupled recovery problem. It must create clearance while organizing support for a stable rise, since attempting to stand before making room can further increase obstruction. We introduce a reinforcement learning method with contact-supported geometric escape guidance, which rewards incremental reduction of robot-obstacle overlap without prescribing an escape path. To achieve this, a learned motion prior, together with posture-dependent support and joint-stall costs, is proposed to shape a single policy that learns when to clear the obstacle, how to establish support, and when to complete the rise, all using proprioception alone. In simulation, it recovers in 88.5% of trials beneath plates that can only be lifted, compared with 18.9% without geometric guidance, and in 98.6% of trials beneath free plates with randomized size, mass and placement. On a Unitree G1, the deployed policy recovered in 95 of 150 attempts across seven real-world obstacle scenes, including furniture and multi-object arrangements absent from training. Project page: https://lu-yidan.github.io/ROOF/

cs.RO↗
arXiv2026

Multimodal Deep Learning for Uncertainty-Aware Radiation Pneumonitis Risk Prediction

Radiation pneumonitis (RP) is a potentially serious complication of thoracic radiotherapy, making reliable risk prediction important for identifying high-risk patients and guiding effective toxicity management. Although deep learning models can predict RP risk, uncertainty quantification remains underdeveloped in radiation toxicity assessment. We developed a Multimodal Bayesian Diffusion Transformer (MM-DiT) that integrates pretreatment computed tomography (CT) and three-dimensional planning dose distributions for RP risk prediction and uncertainty quantification. MM-DiT combines self-supervised multimodal representation learning with Bayesian classification to estimate individual risk and characterize aleatoric, epistemic, and label uncertainty. In independent Mount Sinai Health System (MSHS) and RTOG cohorts, MM-DiT achieved areas under the receiver operating characteristic curve (AUCs) of $0.89$ and $0.86$, respectively, with expected calibration errors of $0.02$ and $0.03$. Incorporating post-treatment CT increased AUC to $0.95$ in MSHS and reduced aleatoric and epistemic uncertainty by approximately $40-45\%$ and $40\%$, respectively. These findings establish a framework for uncertainty-aware radiation toxicity prediction that complements risk estimates with information about predictive reliability. By integrating multimodal learning and uncertainty quantification, MM-DiT may advance more interpretable and trustworthy AI-assisted toxicity assessment and support individualized radiotherapy planning.

eess.IV↗
arXiv2026

VitronEdit: Universal Visual Editing across Images, Videos, and 3D Scenes

Recent advances in unified visual editing have begun to consolidate image and video editing within a single model, while 3D scene editing remains largely separate and constrained by scarce paired training data. Given the rich image and video editing supervision now available and the common editing semantics shared across modalities, a natural question is whether this knowledge can be transferred to data-scarce 3D editing. We present VitronEdit, a universal framework for image, video, and 3D scene editing. VitronEdit adopts a shared sequence representation and progressive multimodal training to transfer editing knowledge across modalities. We further introduce geometry-aware post-training, which leverages a pretrained geometry reconstruction model to provide depth and camera-pose supervision. Surprisingly, applying geometric supervision only to 3D samples yields the best overall performance, while image and video editing also improve despite receiving no direct geometric supervision, suggesting that geometric regularization transfers through the shared backbone. Our analysis further shows that image and video training mainly transfers editing semantics to 3D, whereas 3D supervision primarily improves multi-view consistency. The project page: https://vitron-llm.github.io/VitronEdit/.

cs.CV↗
arXiv2026

IMPACT: Inverter-Informed Multimodal Learning for Photovoltaic Generation Forecasting

This work develops a physics-informed multimodal deep learning framework for 10- to 110-minute-ahead probabilistic photovoltaic power forecasting. The forecasting model is built on a four-branch architecture that separately encodes plant-level temporal history and inverter-level spatial cloud dynamics through a graph attention encoder with a learned adjacency, known-future solar geometry, and the current meteorological state, fused through gated cross-attention. The geometry branch adds two forward-looking physical signals, spatial cloud heterogeneity and inverter ramp-down activity, each empirically weighted toward the horizon where it is most predictive. The decoder anchors its prediction to a smart persistence baseline, learning a horizon-conditioned correction, and the resulting quantile forecasts are calibrated online through a kernel-weighted adaptive conformal calibration step. The proposed model outperforms all 14 baselines, achieving a forecast skill score (FSS) of 0.2950, 0.099 above the next-best model. A branch-composition ablation shows that every branch contributes positively and the model retains substantial skill in challenging overcast and variable sky conditions (FSS 0.198 and 0.255).

cs.LG↗
arXiv2026

Strong counterexamples to Mubayi's supersaturation conjecture in every uniformity

The supersaturation problem asks, for a fixed $r$-graph $\mathcal F$, for the minimum number of copies of $\mathcal F$ in an $n$-vertex $r$-graph with $\ex(n,\mathcal F)+q$ edges. Mubayi conjectured a local form of supersaturation under a stability hypothesis: if $\mathcal F$ is non-$r$-partite and stable, meaning roughly that the extremal $\mathcal F$-free construction is unique and all near-extremal $\mathcal F$-free $r$-graphs are close to it, then this minimum should be at least $q c(n,\mathcal F)$, where $c(n,\mathcal F)$ is the minimum number of copies created by adding one edge to the extremal $\mathcal F$-free $r$-graph. We disprove this conjectured local lower bound in the strongest possible quantitative sense that the ratio to the conjectured lower bound can be made arbitrarily small. More precisely, for every $r\ge2$ and every $K>1$, we construct a stable non-$r$-partite $r$-graph $\mathcal F$ such that, for all sufficiently large $n$ and every $1\le q\leδn$, there is an $n$-vertex $r$-graph with $\ex(n,\mathcal F)+q$ edges containing at most $K^{-1}q c(n,\mathcal F)$ copies of $\mathcal F$. This arbitrarily large failure already occurs when $q=1$.

math.CO↗
arXiv2026

Nontrivial topological properties from the cooperation of static perturbations and Floquet fields in type-II semi-Dirac semimetals

In this work, we present a comprehensive theoretical study for the topological and anomalous transport properties of type-II SDSMs under three scenarios, i.e., static symmetry-breaking perturbations, periodic Floquet driving by two-frequency orthogonally polarized light (TFOPL), and their cooperative effects in the hybrid scenario. We first show that a static mass $m_z$ opens a bulk gap and drives the system into a Chern insulator with Chern number $C^{\rm per}=\pm 2\,{\rm sgn}(m_z)$. In comparison, TFOPL alone only shifts the positions of Dirac points and cannot open a full gap. Nevertheless, it produces a Berry curvature odd in the $x$-direction, yielding a finite Berry curvature dipole (BCD) along $x$ proportional to the sine of the initial phase, while the $y$-component vanishes. The hybrid scenario, by contrast, exhibits a remarkably rich phenomenology. Specifically, its gap-closure criterion becomes cubic and thus admits up to three real roots when the effective parameter along the $x$-direction is negative, thereby producing multiple light-tunable gap-closing points and a series of topological phase transitions. In particular, the BCD exhibits a double-peak structure with strong enhancement near gap-closing manifolds and synchronized sign reversal of the full vector under external tuning. We further analyze the anomalous Hall conductivity (AHC), anomalous Nernst conductivity (ANC), and anomalous thermal Hall conductivity (ATHC). The AHC and ATHC exhibit quantized plateaus that serve as signatures of Chern-insulator phases, while the ANC, being a Fermi-surface probe, provides complementary local information and can identify light-induced gaps even when global topological invariants remain unchanged. Taken together, these results offer useful insights into the topological properties of 2D type-II SDSMs and related systems.

cond-mat.mes-hall↗
arXiv2026

EVOLVE: Uncertainty-Aware Multivariate Time Series Anomaly Prediction with Adaptive Prototype Memories

Unsupervised multivariate time series anomaly prediction (AP) aims to estimate future anomaly risks from current observations, providing early-warning signals for proactive intervention and maintenance in complex systems. Existing unsupervised AP methods follow a perturbation-based paradigm, where predefined or random perturbations are injected into historical windows to simulate abnormal future evolution. However, these methods share perturbations across different variables and contexts, and learn deterministic history-to-future evolution. In reality, anomaly evolution is variable- and context-dependent: the same perturbation may be amplified into abnormal future dynamics in one variable or context, while being absorbed as normal fluctuation in another. In addition, future evolution is not uniquely determined by a historical window, since similar histories may lead to multiple plausible trajectories, such as gradual degradation or abrupt changes. To address these problems, we propose EVOLVE, a unified framework that models unsupervised AP via variable- and context-conditioned perturbations and uncertainty-aware future reasoning. EVOLVE constructs context-specific anomaly perturbations through an adaptive anomaly prototype memory, which can dynamically update and retrieve relevant perturbations at the variable level. EVOLVE models uncertainty by sampling multiple latent historical states and decoding through complementary smooth and deviation-amplifying evolution hypotheses, and the disagreement among decoded future trajectories is used to estimate future anomaly risk. Extensive experiments on six real-world benchmark datasets demonstrate that EVOLVE consistently outperforms state-of-the-art anomaly prediction baselines.

cs.LG↗
arXiv2026

FLORA: An Open Model Suite for Scaling Robotics Data Engines

The life-cycle of robotics foundation models crucially depends on data labels. Outcome reward labels are needed for monitoring real-world deployments. Process reward labels are needed during RL post-training. Timestamped captions are needed for filtering and balancing pretraining data. We present Flora, an industrial-quality data engine used for training GR00T models, that simultaneously covers these capabilities. Flora achieves SOTA scores on the captioning benchmark WGO-Bench and reward benchmarks RoboReward and Robometer. On internal benchmarks it is competitive with GPT-6 Astra while beating other frontier models. The model is substantially cheaper than API-based alternatives, roughly 125 times cheaper than GPT-6 Astra. Florais battle tested at scale, labeling 200,000 hours of data per day across 512 GB300s. By open-sourcing our data engine, we enable researchers to scale custom robotics datasets and explore emerging applications such as physical auto-research and human-to-robot transfer.

cs.RO↗
arXiv2026

CRAB: Cuboid-based Representation for As-built BIM from Point Clouds

As-built BIM reconstruction from point clouds demands semantic, volumetric, parametric, and editable building components, beyond 2D layouts or planar abstractions. Yet existing scan-to-BIM pipelines often rely on handcrafted rules, heuristic optimization, or manual correction, while learning-based methods fall short of recovering wall thickness, opening geometry, and component-level BIM structure. We introduce CRAB, a BIM-ready cuboid reconstruction framework that encodes walls, doors, windows, beams, and columns as compact architectural cuboids with IFC-compatible semantics and parameters. CRAB bridges point clouds and editable BIM by combining ProposalNet, which predicts coarse component cuboids, with AssemblyNet, a relation-aware Flow Matching model that refines geometry, predicts structural relationships, and enables automatic structural correction and human-guided editing. To address limited cuboid-level supervision, we extend Structured3D with component-wise cuboid annotations and construct cuboid-based procedural scenes. Experiments show CRAB surpasses floor plan and plane-based alternatives in component completeness, geometric accuracy, and generalization. For interior wall thickness estimation, CRAB achieves a mean error of 2.80 cm, with 79.50% of matched walls within 3 cm. The project page is available at https://vcc.tech/research/2026/CRAB.

cs.CV↗
arXiv2026

Agentic World Action Models

Recent world action models provide visual foresight and future prediction for robot manipulation, but lack explicit mechanisms for compositional skill reuse. Agentic robotics combines code-based planning and reasoning with reusable skills, but often lacks predictive grounding in physical dynamics. We introduce AW-0, an agentic world action model framework that integrates code-based planning with joint video and action prediction. We jointly model code, future video, and robot actions as three coupled generative streams within a unified mixture-of-transformers architecture. Within this architecture a code expert generates parameterized skill routines and control logic while video and action experts generate future visual states and low-level motor commands. Code serves two complementary roles: it structures multi-step prediction and control within the world model and represents skills as reusable programs for subsequent agentic execution. We further introduce an automated curation pipeline that labels robot and human video trajectories with aligned programs and consolidates recurring routines into reusable skill libraries. Evaluations on RoboTwin 2.0 and physical bimanual manipulation tasks show improved task performance over VLA and WAM baselines, alongside gains in language following, semantic reasoning and robustness, demonstrating that agentic code enables connection between planning, prediction and execution within WAMs.

cs.RO↗
arXiv2026

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety

General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety. We present Yuvion VL, a family of multimodal large language models purpose-built for content and AI safety, with both instruction-tuned and reasoning-oriented variants. Yuvion VL addresses this gap by treating safety as an inherently adversarial and multimodal problem and designing the entire pipeline around adversarial robustness. For data construction, we develop an automated pipeline integrating adversarial-aware data synthesis with multi-stage quality control, producing large-scale, high-quality multimodal samples augmented with domain knowledge and reasoning annotations. For training, we adopt a three-stage pipeline that includes continued pretraining for risk-concept cross-modal alignment, instruct post-training for production-grade safety tasks, and reasoning post-training for enhanced interpretability and performance in complex tasks. We further introduce Confuse-then-Contrast Fine-Tuning, a contrastive framework that mines model-specific confusions and constructs multi-image contrastive groups to enforce explicit discrimination of fine-grained visual-semantic elements, enabling the model to distinguish between visually similar cases with different safety implications in adversarial safety tasks. To support rigorous evaluation, we further introduce Yuvion VL RiskEval (YVRE), a collection of benchmarks covering diverse open and internal evaluations, with a focus on content and AI safety, adversarial robustness, and real-world capability requirements. Experiments show that Yuvion VL-32B achieves industry-leading safety performance, surpassing comparably sized open-source models and best closed-source commercial models, while maintaining comparable general capabilities.

cs.CV↗
arXiv2026

TriGeoBench: A Multimodal Mathematical Geometry Benchmark with Figures and TikZ

Multimodal Large Language Models show strong vision-language capabilities, yet their geometry-centric reasoning remains insufficiently understood. Existing mathematical benchmarks typically rely on rasterized figures and cover limited geometric knowledge areas and response formats, making it difficult to assess whether models reason over geometric structures or exploit superficial visual patterns. We introduce TriGeoBench, a geometry-centric multimodal benchmark constructed from Chinese middle- and high-school mathematics examinations. TriGeoBench contains 7,000 question-answer pairs and 12,235 geometric figures with TikZ code, spanning plane geometry, solid geometry, analytic geometry, function, and vector geometry across diverse response formats. Each instance forms a {question-answer pair, image, TikZ} triplet: question-answer pairs are stored in LaTeX, images as RGB figures, and TikZ preserves geometric topology, symbolic annotations, and relational structure. We evaluate representative open- and closed-source MLLMs through image-to-TikZ and multimodal reasoning probes. Results reveal persistent fine-grained structure and image-text alignment challenges. Oracle experiments with human-curated reference TikZ suggest that accurate executable representations provide complementary geometric cues; they do not evaluate an end-to-end conversion pipeline. TriGeoBench offers a testbed for structure-aware mathematical reasoning.

cs.AI↗
arXiv2026

High-Efficiency Silicon-Lithium Niobate Grating Coupler enabled by Fully-Etched Subwavelength Structures

A new approach of silicon-lithium niobate (Si-LN) grating couplers (GCs) with a fully-etched structure is proposed. The coupling strength is engineered through subwavelength structures, allowing improved directionality. The adjoint-based inverse design method is simultaneously adopted to achieve efficient coupling between photonic circuits and fibers. Considering the birefringence of LN, the proposed Si-LN GCs are optimized and fabricated for TE mode along the crystallographic Z and Y directions. The experimentally measured coupling efficiencies are -3.3 dB and -3.9 dB along the crystallographic Z and Y directions, respectively. The measured 3-dB bandwidths are broader than 54 nm and the back reflections can be suppressed down to -15 dB over 50 nm for both directions. The proposed Si-LN GCs are realized by only single-step Si etching, offering a practical solution for fast device prototyping in Si-LN photonic integrated circuits.

physics.optics↗
arXiv2026

Don't Rewrite the SID Map: Topology Preservation for Generative Retrieval in Dynamic E-Commerce Search

Generative retrieval assigns each item a discrete semantic identifier (SID) and retrieves items by autoregressively generating SID sequences. In dynamic environments such as e-commerce, new items arrive continuously, requiring periodic updates to the SID-to-Item mapping and model to maintain retrieval timeliness. Each update, however, can invalidate search paths already learned by the retriever, and the quantitative relationship between mapping change and retrieval quality has not been systematically characterized. We study this problem with extensive controlled experiments over 67 days of large-scale e-commerce search logs and obtain three core findings. (1) SID semantic drift causes severe retrieval degradation that may be masked by large beam sizes: mapping updates reduce HitRate by 41.78-62.05% at beam size 1 but only 8.33-10.85% at beam size 1000, as redundant candidate generation conceals the true severity of drift. (2) The fraction of changed SIDs is strictly monotonically related to retrieval quality: as the remapped fraction increases from 0% to 72.75%, HitRate decreases monotonically, dropping up to 42.66% at beam size 1. Full remapping remains substantially worse than the preservation policy under warm-start training, indicating that short-budget continued training alone cannot repair topology disruption. (3) The SID topology-preserving principle makes even the simplest warm-start strategy highly effective: fixing old-item SIDs, inserting new-items, and warm-starting from the previous model improves old-item HitRate by 10% and new-item HitRate by 109%, validated across two non-overlapping update cycles. These findings distill into a concise deployment principle: insert new-items, freeze old-items; warm-start when possible, otherwise freeze; never change SIDs the model has already learned. A three-week online A/B test on TmallAPP shows UCTCVR +0.29% and GMV +1.16%.

cs.IR↗