arXiv subjects

Yang Yang

Publications and source records attributed to Yang Yang.

At least 73 records · Page 4Linked to original sources

arXiv2026

Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling

To mitigate the scalability bottleneck in the radio access network (RAN) in federated edge learning (FEEL), over-the-air federated learning (AirFL) exploits waveform superposition over multiple-access channels (MACs) for analog model aggregation. However, coherent AirFL typically relies on stringent PHY-layer conditions such as accurate channel state information (CSI), tight time/frequency synchronization, and frequent transceiver calibration for signal alignment. However, these requirements, if not impossible to be met, incur substantial communication and computation overhead. In this paper, we propose a non-coherent AirFL (NCAirFL) protocol over a broadband single-antenna MAC, leveraging binary dithering, unbiased non-coherent detection, and long-term error feedback to waive the need for instantaneous CSI. For NCAirFL with general smooth non-convex objectives and a constant learning rate, we establish a convergence bound achieving the convergence rate in the same order of $\mathcal{O}(1/\sqrt{T})$ as communication-ideal FedAvg, where $T$ is the total number of communication rounds. To further improve communication efficiency under data and wireless resource heterogeneity, we also derive a lower bound on the expected single-round objective decrease in the global loss conditioned on device scheduling, building upon which a surrogate objective function is obtained for jointly optimal device selection and power control. Experimental results on MNIST and CIFAR-10 corroborate that NCAirFL achieves learning performance close to FedAvg in practical settings, with the proposed device scheduling policy substantially accelerating convergence.

cs.IT↗

arXiv2026

Near-Horizon Tidal Disruption Events

Tidal disruption events (TDEs) offer a unique dynamical probe of the spacetime geometry around supermassive black holes (SMBHs). While conventional TDEs occur around SMBHs of $M_\bullet \sim 10^6 - 10^7 M_\odot$, where stars are disrupted far from the event horizon, here we identify a special class of TDEs around rapidly spinning SMBHs with masses $M_\bullet \gtrsim 10^8 M_\odot$, where the tidal-disruption radius approaches the gravitational radius. We term these events "near-horizon TDEs" and, by calculating geodesics in Kerr spacetime, investigate how the proximity of the horizon modifies the debris evolution and subsequent fallback. We find that for stars encountering the SMBH on parabolic orbits, up to $\sim (90 \%-95 \%)$ of the stellar debris either plunges directly into the SMBH or escapes the system. Bound orbits, by contrast, retain a substantially larger fraction of the debris. Using the resulting debris distribution, we calculate the fallback rates and find that bound orbits produce intrinsically higher peak fallback rates and shorter decay timescales, by factors of $\sim 10^3$ relative to parabolic orbits. However, when the stellar orbital angular momentum is particularly low, the peak fallback rate can be substantially suppressed by debris lost to plunge orbits. This combination of rapid fallback and a mass deficit naturally explains overluminous TDEs such as ASASSN-15lh, which standard TDE models have struggled to reproduce. Our work establishes near-horizon TDEs as a new probe of strong-field gravity and a promising tool for identifying massive, rapidly spinning SMBHs.

astro-ph.HE↗

arXiv2026

A growth gap for anisotropic minimal graphs

We prove a growth gap for the gradient of entire anisotropic minimal graphs. For each $n\geq2$ and each smooth uniformly elliptic parametric integrand $Φ$ on $\mathbb{R}^{n+1}$, there is an exponent $α=α(n,Φ)>0$ such that every smooth nonaffine entire $Φ$-minimal graph $u:\mathbb{R}^n\to\mathbb{R}$ satisfies $\sup_{B_R^n}|Du|\geq cR^α$ for all $R\geq R_0$, for some constants $c>0$ and $R_0<\infty$ depending on the solution. In particular, gradient growth $o(R^α)$ forces flatness, resolving a conjecture of Mooney and the author. The result holds in every dimension, without any assumption that $Φ$ is close to the Euclidean area integrand.

math.AP↗

arXiv2026

Brain4FMs: A Benchmark of Foundation Models for Electrical Brain Signal

Brain foundation models (BFMs) are advancing neurotechnology by learning transferable representations from neural signals, with broad potential in clinical diagnosis and neuroscience research. Their development relies on large-scale pretraining corpora of electrical brain signals, including scalp electroencephalography (EEG) and intracranial EEG (iEEG). However, existing BFM benchmarks primarily focus on EEG, cover only a limited subset of models, and provide limited analysis beyond downstream performance. We introduce Brain4FMs, the first unified benchmark, to our knowledge, for jointly evaluating BFMs on EEG and iEEG. It integrates 17 representative models and 21 public datasets across clinical diagnosis, sleep staging, communication, and affective computing. Brain4FMs is open and plug-and-play, with dataset-aware preprocessing, cross-subject evaluation, heterogeneous multichannel handling, and standardized downstream adaptation workflows. The benchmark reveals performance variation across tasks, signal modalities, and adaptation protocols, with no single BFM consistently dominating all evaluation scenarios. % To better understand these heterogeneous transfer behaviors, we further conduct exploratory analyses of model-specific properties. To better understand these behaviors, we further conduct exploratory analyses of model-specific properties of spatial, spectral, and discrete representations. The code is available at https://github.com/wajtsq/Brain4FMs.

cs.LG↗

arXiv2026

ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control

Long-form story generation requires models to preserve narrative consistency across extended contexts, yet existing prompting-based methods often accumulate temporal, factual, character, commonsense, and stylistic errors as the story grows. We propose ConWriter, a training-free framework for consistency-aware long-form story generation. ConWriter writes stories incrementally at the scene level, guided by static story requirements, dynamic narrative memory, symbolic state reasoning, and uncertainty-aware risk signals. Rather than treating long-story generation as a single free-form decoding process, ConWriter maintains evolving story states, checks whether new scenes satisfy required narrative transitions, and uses uncertainty-aware risk signals to prioritize validation and localized repair. This enables consistency control during generation, before local errors propagate into later scenes. We evaluate ConWriter on ConStory-Bench across four long-story tasks, three target lengths, and multiple base LLMs following the official evaluation protocol. Across models and story lengths, ConWriter consistently matches or improves upon direct generation and outperforms the recent training-free baseline DOME in narrative consistency. These results demonstrate the effectiveness of lightweight neuro-symbolic consistency control for training-free long-form story generation. Code is available on \href{https://github.com/jindongli-Ai/ConWriter}{GitHub}.

cs.CL↗

arXiv2026

A Halfspace Theorem for Global Anisotropic Perimeter Minimizers

We prove an arbitrary-dimensional halfspace theorem for global minimizers of a smooth uniformly elliptic anisotropic perimeter: if the nonempty boundary of a minimizing set is contained in a halfspace, then the set itself is a halfspace. No evenness of the integrand or regularity of the minimizing boundary is assumed. The proof combines wall contact with a plane-peeling argument for the complementary phase defect and a simultaneous second blow-down. We also give a direct, self-contained exterior-barrier proof of the two-dimensional stationary anisotropic statement. Its rigidity conclusion is already covered by Bergner's earlier halfspace theorem; the proof is retained because it works directly with the anisotropic Euler-Lagrange operator.

math.AP↗

arXiv2026

From Topical Relevance to Answerability: Entailment Distillation for Conversational Retrieval

Existing conversational retrievers commonly treat topical relevance as a proxy for answerability. However, a passage that closely matches the dialogue context is not necessarily the one that supports the correct answer. We identify this mismatch as a systematic answerability gap. To address this issue, we propose CLEAR, a framework that shifts conversational retrieval from topical relevance to answerability. The core of CLEAR is entailment distillation, which transfers answer-passage entailment supervision into a cross-encoder reranker so that the reranker discriminates answer-supporting passages from topical distractors at inference time, without requiring answers. CLEAR is complemented by a passage-centric abductive recall module that brings low-similarity yet answerable passages into the candidate pool by inferring answerable queries from passages with an LLM. Across TopiOCQA, QReCC, and out-of-domain TREC CAsT datasets, CLEAR consistently improves top-ranked precision over strong query-rewriting and dense-retrieval baselines, with the largest gains observed in conversations involving heavier topical noise. Moreover, applying our reranker on top of an LLM-driven query rewriter yields further gains.

cs.IR↗

arXiv2026

OptiXDE: A fast optical-inspired solver for differential equations

OptiXDE is a matrix-free spectral operator framework for differential equations on uniform grids and embedded domains. Inspired by angular-spectrum propagation in Fourier optics, it maps transform-diagonal spatial operators to analytical modal multipliers and composes them with physical-space operators for nonlinearities, geometry and boundary enforcement. A common transform--operator--inverse-transform backbone is demonstrated across transient diffusion, periodic and embedded-domain Poisson problems, the cubic nonlinear Schr"odinger equation, viscous Burgers dynamics, the two-dimensional Allen--Cahn equation and incompressible flows from the Taylor--Green vortex to embedded-cylinder vortex shedding. Transform-compatible linear problems are recovered near the floating-point limit, whereas errors on the singular L-shaped domain remain localized near the re-entrant corner and regularized interface. Nonlinear benchmarks recover second-order temporal convergence and the expected conservative or dissipative behavior, while incompressibility remains near round-off level during long-time vortex shedding. The matrix-free updates require $\mathcal{O}(N\log N)$ work and $\mathcal{O}(N)$ memory. Device-resident transform workloads reach $94.9\times$ GPU acceleration, and the complete embedded-cylinder solver achieves a $42.1\times$ CPU--GPU speedup under matched numerical settings. These results establish OptiXDE as a deterministic and extensible operator-centric framework for structured and embedded-domain differential equations.

math.NA↗

arXiv2026

TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning

Multimodal recommendation systems (MRS) jointly model user-item interaction graphs and rich item content, but this tight coupling makes user data difficult to remove once learned. Approximate machine unlearning offers an efficient alternative to full retraining, yet current MRS unlearning applies reverse updates largely uniformly across model components. We show that this uniform treatment is misaligned with modern MRS: deleted-data influence is distributed unevenly across \textit{ranking behavior}, \textit{modality branches}, and \textit{model modules}. This non-uniformity gives rise to three bottlenecks in MRS unlearning: target-item persistence in the collaborative graph, modality imbalance across feature branches, and concentrated module-level sensitivity in the parameter space. To address this mismatch, we propose \textbf{targeted reverse update} (TRU), a plug-and-play unlearning framework for MRS. Instead of applying a uniform global reversal, TRU performs three coordinated interventions across the model hierarchy: a ranking fusion gate to suppress residual target-item influence in ranking, branch-wise modality scaling to preserve retained multimodal representations, and capacity-aware parameter-group selection to localize reverse updates to deletion-sensitive modules. Across two backbones, three datasets, and three unlearning regimes, TRU achieves a stronger retain--forget trade-off than MMRecUn in most settings. In two challenging user-level cases, TRU also attains favorable operating points among all evaluated baselines. Security audits report the lowest MIA BalAcc and a tie for the lowest ASR among approximate methods in both audited settings, while wall-clock trajectories show earlier convergence to favorable retain--forget regions.

cs.AI↗

arXiv2026

LLM-Based Knowledge Graph Completion Combining Discrete Structural Coding with Similar Entity Information

Knowledge graph completion requires models to use both textual descriptions and relational structure. Existing LLM-based methods either encode KG structure as discrete tokens or refine a restricted set of candidate entities, and these two directions have largely been studied separately. We propose CoSC for LLM-based KGC, which combines discrete structural coding with similar entity information. Specifically, an LLM generates an initial candidate entity ranking from discrete structural codes, after which information from entities with structures similar to that of the query entity refines the ranking. Experiments on FB15k-237 show that CoSC outperforms existing baselines on MRR and Hits@10 while remaining competitive on Hits@1.

cs.AI↗

arXiv2026

When and What to Teach: Budget-Aware Online Adaptation for Web Agents

Web agents have achieved significant success in automating complex internet tasks but deploying them in real-world environments requires continuous online adaptation. Given that deploying powerful proprietary models remains commercially cost-prohibitive, practitioners must rely on lightweight local models that evolve post-deployment via online teaching from a stronger teacher. However, standard interactive feedback imposes prohibitive costs. We show that conventional trajectory-level preference optimization wastes budget on both unresolvable episodes and redundant execution turns. To resolve these inefficiencies, we propose \textbf{Score-Guided Online Teaching with Budgeted Trajectory Trimming}, a budget-aware framework that systematically orchestrates \textbf{when} and \textbf{what} to teach. Specifically, our framework integrates a solvability-aware teacher gate to dictate \textbf{when} to query the teacher model and a score-guided turn selection mechanism to decide \textbf{what} informative turns to retain. Extensive experiments on MiniWoB and TimeWarp demonstrate that our method achieves comparable first-pass success while reducing teacher calls by 22.6\% and student training compute by 52.1\% on average. Our code is available at https://github.com/zjw131f1fc/budgeted-online-teaching.

cs.AI↗

arXiv2026

Two-dimensional quantum Griffith singularity in three-dimensional ZrN$_x$ superconducting films

We report the experimental observation of two-dimensional (2D) quantum Griffiths singularity (QGS) in $\sim$200-nm-thick epitaxial ZrN$_x$ superconducting films. The films possess a rock-salt structure and are three-dimensional (3D) with respect to superconductivity. For each film with $x \gtrsim 1.30$, the low-temperature magnetoresistance isotherms under fields perpendicular and parallel to the film plane cross over at a broad magnetic field range independently rather than at a single crossing point. Despite the macroscopic 3D nature of the superconductivity, the magnetoresistance isotherms at selected adjacent temperatures follow the theoretical prediction of power-law scaling for 2D superconducting systems, rather than that for 3D systems. The effective critical exponent $zν$, obtained by analyzing the magnetoresistance isotherms using the 2D power-law scaling, increases with decreasing temperature and diverges as the quantum phase transition is approached. In addition, the resistivity data near the superconductor-insulator or superconductor-metal transitions obey an activated scaling form that describes the quantum phase transition of 2D superconducting systems governed by an infinite-randomness critical point. The QGS in the ZrN$_x$ films is attributed to quenched disorder induced by intrinsic defects, such as Zr vacancies and N interstitials, which creates spatially inhomogeneous superconducting rare regions. The dynamics of these rare regions, which may exhibit effective 2D characteristics near the quantum critical point, dominate the transport properties of the system near the quantum phase transition. Our results provide compelling evidence for the existence of QGS in 3D superconductors and highlight the crucial role of disorder-induced inhomogeneity in determining the critical behavior of quantum phase transitions.

cond-mat.supr-con↗

arXiv2026

Energy Partition in AGN-driven Bubbles of NGC 4438: From Nuclear Bubbles to a Galaxy-scale Outflow

Jets launched by accreting supermassive black holes represent a major mode of active galactic nucleus (AGN) feedback. However, how their energy is divided among bulk kinetic motion, thermal gas, magnetic fields, cosmic rays (CRs), and radiation - and how this distribution changes with spatial scale - remains poorly constrained. NGC 4438 provides a unique laboratory for probing this evolution, hosting two 200-pc-scale nuclear bubbles and a lopsided ~10 kpc galaxy-scale outflow plausibly associated with the same AGN. We present a multi-wavelength analysis to investigate the morphology, radiation mechanisms, and energetics of these structures. Joint radio-X-ray modeling shows that the non-thermal emission in the nuclear bubbles may require two distinct populations of cosmic-ray electrons, suggesting that in addition to shock acceleration at the bubble rim, the highest-energy particles may be linked to acceleration processes closer to the unresolved central engine. A spatially resolved energy inventory reveals that bulk kinetic energy dominates the current energy budget of the nuclear bubbles, while roughly half of the injected energy has already been transformed into thermal, CR, and magnetic energy, as well as radiative losses. Across all bubble sizes, the thermal and magnetic pressures are consistent within the uncertainties, implying that magnetic fields remain dynamically significant on all examined spatial scales. Furthermore, the empirical correlation between radio luminosity and jet power, established for kiloparsec-scale jet bubbles (MerloniHeinz2007), matches the energetics of the galaxy-scale outflow but substantially overestimates the power of the 200-pc-scale nuclear bubbles, underscoring the scale dependence of jet energy dissipation.

astro-ph.HE↗

arXiv2026

Report Supervision

Segmentation models can surpass radiologists, classification models, and vision-language models in tumor detection. Importantly, segmentation models outline tumors, allowing radiologists to better verify and trust the AI output. Their main limitation is the scarcity of tumor masks: creating one 3D tumor mask takes up to 30 minutes, so most public CT datasets contain only a few hundred masks, and even the largest private datasets contain only a couple of thousand. Tumor masks are not produced in clinical routine, but radiology reports are. Public datasets contain tens of thousands of CT-Report pairs, and hospitals contain hundreds of thousands. These reports describe tumors in detail, providing large-scale, informative training data. Here, we introduce Report Supervision (R-Super), a training framework that uses reports to directly supervise and improve tumor segmentation. R-Super introduces new loss functions that teach segmentation models to segment tumors that match report descriptions of tumor count, sizes, and locations. Reports are only used for training. We evaluated R-Super on kidney and pancreatic tumor segmentation, exploring diverse training data sizes, up to 41,418 CT-Report plus 3,488 pancreatic tumor CT-Mask pairs. On external validation, R-Super increased tumor detection F1-Score and segmentation DSC by up to +15% with respect to mask-only training. It also surpassed alternative methods such as CLIP and multi-task learning. Leveraging numerous readily available reports to supplement scarce masks, R-Super strongly improves AI performance when very few training masks are available (e.g., 50), and when many masks are available (e.g., 3,488), unlocking scale in tumor segmentation.

cs.CV↗

arXiv2026

Shaping the Evolutionary Dynamics of Robot Morphology via Adaptive Control Learning

Robot co-design via bi-level optimization couples within-lifetime controller learning for fitness evaluation with cross-generational morphological evolution. Prior work has established that well-adapted morphology facilitates faster control learning, a property termed morphological intelligence. Yet how control learning reciprocally shapes morphological evolution remains unexplored. This paper examines both directions for a holistic account of brain-body interplay. We first show that morphological contributions to control learning decouple into two orthogonal dimensions. We formalize the convergence speed as morphological intelligence and identify the performance ceiling as a complementary quantity termed true potential. A concise functional relation is then established to jointly characterize both quantities from individual learning curves, which, when aggregated at the population level, capture evolutionary profiles. Through extensive experiments on simulated voxel-based soft robots, we reveal that premature fitness evaluation systematically underestimates true potential and biases selection towards fast learners. This restricts design space exploration, compromising both optimization efficiency and morphological diversity. Notably, the widely recognized morphological Baldwin effect emerges as an artifact of this bias rather than a general evolutionary tendency. We therefore propose AdaControl, which monitors disproportionate selection for morphological intelligence during evolution and allocates minimally sufficient control learning for unbiased fitness evaluation. With AdaControl, a simple genetic algorithm rivals state-of-the-art generative-model-based co-design methods in discovering diverse high-performing designs while cutting computation by up to 80% versus exhaustive control.

cs.RO↗

arXiv2026

RoboLDA: A Probabilistic Generative Model for Uncovering Embodied Hierarchical Structures in Voxel-based Soft Robots

Recent advances in robotics highlight hierarchical configurations of robot morphology, where multiple levels of functional substructures synergize to facilitate intelligent behaviors. This hierarchical perspective, while particularly advantageous for voxel-based soft robots (VSRs) to ease design and control complexities, is hindered by its heavy reliance on domain expertise. In this work, we address the following question: can we derive such hierarchical design principles solely from existing successful designs? We answer affirmatively by presenting RoboLDA, a Bayesian probabilistic model that decomposes VSR morphology generation into a four-level hierarchy: "task-robot-organ-voxel", and is trained via variational inference. Through extensive experiments on simulated VSRs, we verify the presence of consistent, intuitive hierarchical patterns underlying high-performing VSR designs and showcase RoboLDA's proficiency to extract and leverage these hierarchical priors for zero-shot robot design in unseen tasks. The generated designs, even without further optimization, achieve on average 106.4% of the optimized performance produced by evolutionary algorithms. Additionally, the organ structures inferred by RoboLDA serve as valid functional substructures, significantly enhancing synergistic motion control when integrated with modular control policies. Our work pioneers hierarchical generative modeling of robot morphology, offering a promising pathway towards more interpretable and generalizable development of embodied agents.

cs.RO↗

arXiv2026

Generative Evolutionary Design of Voxel-Based Soft Robots with Provable Optimality

Voxel-based soft robots (VSRs) present a promising avenue for developing artificial organisms with lifelike intelligence. However, the vast design spaces and expensive evaluations substantially challenge their design optimization. Here we develop MISCO, a novel evolutionary framework empowered by deep generative models to optimize VSR designs with theoretical guarantees. MISCO integrates an estimation-of-distribution algorithm with a meticulously designed variational autoencoder featuring multi-task learning, position awareness, and inter-voxel signaling. These key components enhance the representational capacity of VSR morphologies and facilitate highly efficient sampling and optimization of morphological distributions. We provide theoretical guarantees for MISCO's asymptotic convergence to globally optimal designs, alongside a favorable convergence rate. Extensive simulated experiments further demonstrate MISCO's exceptional effectiveness in navigating vast design spaces, evolving high-performing VSRs for diverse tasks while flexibly balancing optimization efficiency and morphological diversity. Being validated both empirically and theoretically, MISCO represents a step change towards more scalable and reliable soft robot development.

cs.RO↗

arXiv2026

Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection

As the misuse of AI-generated images grows, generalizable image detection techniques are urgently needed. Recent state-of-the-art (SOTA) methods adopt aligned training datasets to reduce content, size, and format biases, empowering models to capture robust forgery cues. A common strategy employs reconstruction techniques, e.g., VAE and DDIM, to construct aligned synthetic negatives. However, relying on a single reconstruction process yields a narrow and homogeneous artifact distribution, leaving forensic traces from other artifact-forming mechanisms underrepresented. To broaden artifact coverage without sacrificing alignment, we construct adversarial restoration-based negatives with SRGAN, whose learned upsampling and texture restoration yield traces complementary to VAE reconstruction while preserving content, size, and format. Directly mixing the two aligned fake domains is nontrivial because their artifact manifolds and optimization directions can conflict. We therefore propose Artifact-Complementary Expert Fusion (ACEF), a two-stage framework for robust AIGC detection. ACEF first constructs two artifact-specific experts via LoRA adaptation on a frozen foundation backbone. It then freezes them and introduces Layer-wise Artifact-Complementary Fusion (LACF) to integrate multi-layer source-specific and cross-artifact evidence through an adaptive gate. Extensive experiments on 13 diverse benchmarks demonstrate the effectiveness of our method.

cs.CV↗