arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 163 records · Page 9Linked to original sources

arXiv2026

World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis

We propose world-language-action (WLA) models as a new class of embodied foundation models. WLA takes textual instructions, images, and robot states as inputs to jointly predict textual subtasks, subgoal images, and robot actions, conjoining the \emph{world modeling interface} to learn from extensive egocentric videos as in the world-action model (WAM) and the \emph{language reasoning} capacities to solve complex long-horizon tasks as in vision-language-action (VLA) models. At the core of WLA lies an \emph{autoregressive (AR)} Transformer backbone, instead of a bidirectional diffusion Transformer as in WAMs, to predict the \emph{next state}, comprising the \emph{semantic-level} textual intention and complementary \emph{fine-grained} physical dynamics. The physical dynamics are supervised by the world modeling objective based on a dedicated World Expert, and are leveraged to ease the characterization of the state-action correlation for the Action Expert. WLA leverages meta-queries to make the world prediction \emph{implicitly} impact the action generation so that the former can be disabled during inference. The world prediction can also be activated to enable test-time scaling for improved robot control. Our WLA-0 prototype, with 2B active parameters, achieves 40 ms per inference on an NVIDIA RTX 5090. Evaluations across simulated and real-world environments demonstrate that WLA-0 achieves state-of-the-art multi-task and long-horizon learning abilities, e.g., 92.94\% success rate on RoboTwin2.0 Clean and 56.5\% success rate on RMBench. WLA-0 also holds the promise to learn novel tasks directly from \emph{cross-embodiment robot videos} without action annotations.

cs.RO↗

arXiv2026

Distributionally robust shortfall risk portfolio model with moment ambiguity sets

This paper employs shortfall risk to measure portfolio risk. Assume stock returns follow polynomial relations with their influence factors. We propose a moment-based distributionally robust optimization (DRO) shortfall risk portfolio model. For piecewise linear loss functions, we show that this DRO model can be transformed into a tractable linear conic optimization problem with nonnegative polynomial cones. A Moment-SOS relaxation algorithm is proposed to solve the transformed problem. Its finite and asymptotic convergence properties are studied. For optimizers computed from our algorithm, we give convenient conditions verify their global optimality for the original DRO problem. Numerical experiments involving real stock market data are given to show the efficiency of our approach.

math.OC↗

arXiv2026

MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation

Generative visual models fundamentally struggle with precise spatial control. This arises from a core disconnect: models can process textual descriptions of space but cannot directly map numerical coordinates onto the 2D image canvas. We introduce MetaPoint, a method that bridges this gap by representing a continuous 2D coordinate as a single, special token. Crucially, MetaPoint requires no new architectural components; it directly leverages the model's inherent positional encoding schemes to interpret these coordinates, treating our token as a virtual point on the canvas. This lightweight approach enables pixel-level control of an object's position with one token or its bounding box with two, all without requiring architectural changes or bespoke attention masking. The MetaPoint tokens are designed to be compositional, serving as spatial primitives. This allows a planner agent to decompose a high-level user request into a structured sequence of primitives for the generator. By providing a simple, precise, and scalable building block for spatial control, MetaPoint unlocks more powerful compositional generative agents and enables intuitive, interactive editing systems.

cs.CV↗

arXiv2026

Assessing and Mitigating Miscalibration in LLM-Based Social Science Measurement

Large language models (LLMs) are increasingly used in social science as scalable measurement tools for converting unstructured text into variables that can enter standard empirical designs. Measurement validity demands more than high average accuracy, which requires well calibrated confidence that faithfully reflects the empirical probability of each measurement being correct. This paper studies the model miscalibration in LLM-based social science measurement. We begin with a case study on FOMC and show that confidence based filtering can change downstream regression estimates when LLM confidence is miscalibrated. We then audit calibration across 14 social science constructs covering both proprietary models, including GPT-5-mini, DeepSeek-V3.2, and open source models. Across tasks and model families, reported confidence is poorly aligned with tolerance-based correctness. As a simple mitigation, we propose a soft label distillation pipeline for calibrating Bert with LLM. The method converts an LLM score and its verbalized confidence into a soft target distribution, then trains a smaller discriminative classifier on encoder models for these targets. Averaged across datasets, this approach reduces ECE by 43.2\% and Brier by 34.0\%. These results suggest that LLM-based social science pipelines should treat calibration as part of measurement validity, rather than as an optional post-processing concern.

cs.AI↗

arXiv2026

Partially Observable Adversarial Patch Attacks on Vision-Language-Action Models in Robotics

Vision-language-action (VLA) models are gaining attention in robotics, yet their robustness to adversarial attacks remains largely unexplored. Existing work shows that adversarial patches can mislead VLA-based robots but assumes full access to the entire execution trajectory, an unrealistic requirement in practice. We address this limitation by formulating a partially observable threat model, where the adversary can exploit only a short prefix of the trajectory to generate a fixed patch applied to all subsequent frames. Under this setting, we propose a two-phase framework. First, we localize the patch using the model's attention maps to identify visually critical regions that correspond to the full instruction. Then, we optimize the patch to disrupt the semantic grounding of target objects and increase the curvature of action trajectories, thereby compounding failures in both perception and control. Extensive experiments in simulation and real-world robotic environments show that our method sustains adversarial effects under partial observability, inducing long-horizon disruptions and significantly reducing task success rates.

cs.RO↗

arXiv2026

A Unified and Reproducible Experimentation Framework for Speech Understanding

Speech foundation models and Speech LLMs have advanced speech understanding, yet deployment-oriented model selection is hindered by non-comparable evaluations caused by mismatched post-processing, and by training results that are hard to reproduce across data scales and pipelines. We present SURE, a unified experimentation framework that standardizes prediction formats, normalization, and scoring. SURE evaluates strong systems across paradigms, from conventional pipelines to Speech LLMs, on representative tasks under realistic acoustic and linguistic stressors. Beyond evaluation, SURE introduces an agent-assisted training conversion flow that maps paper and code into versioned, runnable training pipelines under a unified protocol on matched open-data subsets. Overall, SURE improves comparability and reproducibility for deployment-oriented evaluation.

eess.AS↗

arXiv2026

Local Observability and Moving Horizon Estimation-based Training of Feedforward Neural Networks

In this paper, we propose a moving horizon estimation (MHE)-based training method for feedforward neural networks (FNNs) with rectified linear unit (ReLU) activation functions to determine their ideal weights from a control-theoretic perspective. This allows for a rigorous theoretical analysis of the trained network. First, we reformulate the FNN as a dynamical system with the weights as states. Then, we investigate the local observability of such a system. For two-layer FNNs with fixed output weights, we derive a sufficient condition under which the observability rank condition holds, ensuring a locally observable state. We also show that multi-layer FNNs in general fail to satisfy the observability rank condition. Based on this analysis, we develop a persistently exciting (PE) input design method, which renders a state distinguishable from its neighbors. The resulting local observability provides convergence guarantees for the proposed MHE-based training, where only the projection of the state onto the observable subspace is updated using a fixed-length window of input-output data. The effectiveness of the approach is illustrated via numerical examples.

eess.SY↗

arXiv2026

Uncertainty-Aware Gaussian Map for Vision-Language Navigation

Vision-Language Navigation (VLN) requires an agent to navigate 3D environments following natural language instructions. During navigation, existing agents commonly encounter perceptual uncertainty, such as insufficient evidence for reliable grounding or ambiguity in interpreting spatial cues, yet they typically ignore such information when predicting actions. In this work, we explicitly model three forms of perceptual uncertainty (i.e., geometric, semantic, and appearance uncertainty) and integrate them into the agent's observation space to enable informed decision-making. Concretely, our agent first constructs a Semantic Gaussian Map (SGM), composed of differentiable 3D Gaussian primitives initialized from panoramic observations, that encodes both the geometric structure and semantic content of the environment. On top of SGM, geometric uncertainty is estimated through variational perturbations of Gaussian position and scale to assess structural reliability; semantic uncertainty is captured by perturbing Gaussian semantic attributes to reveal ambiguous interpretations; and appearance uncertainty is characterized by Fisher Information, which measures the sensitivity of rendered observations to Gaussian-level variations. These uncertainties are incorporated into SGM, extending it into a unified 3D Value Map, which grounds them as affordances and constraints that support reliable navigation. Comprehensive evaluations across multiple VLN benchmarks show the effectiveness of our agent.

cs.CV↗

arXiv2026

A higher-harmonic observable for the chiral magnetic effect in heavy-ion collisions

The chiral magnetic effect (CME) is a phenomenon in which electric charge is separated by a strong magnetic field from local domains of chirality imbalance in quantum chromodynamics. The CME-sensitive azimuthal correlator difference $Δγ$ between opposite- and same-sign charged hadron pairs is designed to detect charge separation along the magnetic field, on average perpendicular to the reaction plane. However, the search for the CME is hindered by large background contributions to $Δγ$ from particle correlations coupled with elliptic flow. In this work, we explore higher-harmonic components in differential $Δγ(ϕ_{\rm pair})$ as a function of the pair azimuthal angle. Such components could arise from event-by-event fluctuations of the magnetic fields throughout the collision zone, in both direction and magnitude. We show by using heavy-ion physics models that the hexadecapole component of $Δγ(ϕ_{\rm pair})$ is sensitive to the CME and insensitive to physics backgrounds. This could offer a unique observable for the CME that is robust against background contributions.

nucl-th↗

arXiv2026

CktGen: Automated Analog Circuit Design with Generative Artificial Intelligence

The automatic synthesis of analog circuits presents significant challenges. Most existing approaches formulate the problem as a single-objective optimization task, overlooking that design specifications for a given circuit type vary widely across applications. To address this, we introduce specification-conditioned analog circuit generation, a task that directly generates analog circuits based on target specifications. The motivation is to leverage existing well-designed circuits to improve automation in analog circuit design. Specifically, we propose CktGen, a simple yet effective variational autoencoder that maps discretized specifications and circuits into a joint latent space and reconstructs the circuit from that latent vector. Notably, as a single specification may correspond to multiple valid circuits, naively fusing specification information into the generative model does not capture these one-to-many relationships. To address this, we decouple the encoding of circuits and specifications and align their mapped latent space. Then, we employ contrastive training with a filter mask to maximize differences between encoded circuits and specifications. Furthermore, classifier guidance along with latent feature alignment promotes the clustering of circuits sharing the same specification, avoiding model collapse into trivial one-to-one mappings. By canonicalizing the latent space with respect to specifications, we can search for an optimal circuit that meets valid target specifications. We conduct comprehensive experiments on the open circuit benchmark and introduce metrics to evaluate cross-model consistency. Experimental results demonstrate that CktGen achieves substantial improvements over state-of-the-art methods.

cs.LG↗

arXiv2026

Systematic sensitivity study of the $J/ψ$ nuclear modification factor to polarization assumptions

Heavy quarkonium is one of the key candidates to study the fundamental properties of Quark-Gluon Plasma (QGP) created in heavy-ion ($A$+$A$) collisions. Comparing the production of the $J/ψ$ meson in proton+proton ($p$+$p$) and $A$+$A$ collisions, namely the nuclear modification factor ($R_{\rm AA}$), provides the quantitative understanding of the QGP. Normally, the $R_{\rm AA}$ is measured under the assumption that the quarkonium is unpolarized. However, recent measurements on the $J/ψ$ polarization in the forward rapidity region from the LHC experiments suggest that the $J/ψ$ meson has a small but non-negligible polarization. In this paper, we evaluate the systematic sensitivity of the kinematic acceptance to the $J/ψ$ polarization assumptions in the measurement of $R_{\rm AA}$. Using available data from the ALICE and LHCb experiments in the forward rapidity region, and exploring extreme polarization scenarios in the central rapidity region at RHIC and LHC energies, we demonstrate the maximum envelope of systematic uncertainties induced by unknown polarization states. The results indicate that the unpolarized assumption introduces a dominant, unquantified systematic uncertainty. Having precise measurements of quarkonium polarization in heavy-ion collisions is critical to obtaining an accurate interpretation of how heavy quarkonium interacts with the QGP.

nucl-ex↗

arXiv2026

Low-Luminosity Type IIP Supernovae from the Zwicky Transient Facility Census of the Local Universe. I: Luminosity Function, Volumetric Rate

We present the luminosity function and volumetric rate of a sample of Type IIP supernovae (SNe) from the Zwicky Transient Facility Census of the Local Universe survey (CLU). This is the largest sample of Type IIP SNe from a systematic volume-limited survey to-date. The final sample includes 330 Type IIP SNe and 36 low-luminosity Type II (LLIIP) SNe with $M_{\textrm{r,peak}}>-16$ mag, which triples the literature sample of LLIIP SNe. The fraction of LLIIP SNe is $19^{+3}_{-4}\%$ of the total CLU Type IIP SNe population ($8^{+1}_{-2}\%$ of all core-collapse SNe). This implies that while LLIIP SNe likely represent the fate of core-collapse SNe of $8-12$ \Msun\ progenitors, they alone cannot account for the fate of all massive stars in this mass range. To derive an absolute rate, we estimate the ZTF pipeline efficiency as a function of the apparent magnitude and the local surface brightness. We derive a volumetric rate of $(3.9_{-0.4}^{+0.4}) \times 10^{4}\ \textrm{Gpc}^{-3}\ \textrm{yr}^{-1}$ for Type IIP SNe and $(7.3_{-0.6}^{+0.6}) \times 10^{3}\ \textrm{Gpc}^{-3}\ \textrm{yr}^{-1}$ for LLIIP SNe. Now that the rate of LLIIP SNe is robustly derived, the unresolved discrepancy between core-collapse SN rates and star-formation rates cannot be explained by LLIIP SNe alone.

astro-ph.HE↗

arXiv2026

Harnessing AI for Inverse Partial Differential Equation Problems: Past, Present, and Prospects

Solving inverse partial differential equation (PDE) problems is a fundamental topic in scientific research due to its broad significance across a wide range of real-world applications. Inverse PDE problems arise across medical imaging, geophysics, materials science, and aerodynamics, where the goal is to infer hidden causes, design structures, or control physical states. In this paper, we provide a comprehensive review of recent advances in solving inverse PDE problems using artificial intelligence (AI). We first introduce the basic formulation, key challenges, and traditional numerical foundations of inverse PDE problems, and then organize it into three major categories: inverse problems, inverse design, and control problems. For each category, we further present a methodological paradigms, and review representative state-of-the-art approaches from recent years. We then summarize representative applications across scientific and industrial domains, including mechanical systems, aerodynamic problems, thermal systems, full-waveform inversion, system identification, and medical imaging. Finally, we discuss open challenges and future prospects, such as physics-informed architectures, limited real-world data, uncertainty quantification, and inverse foundation models. This survey aims to provide the first unified and systematic perspective on AI for inverse PDE problems, demonstrating how modern learning-based methods are reshaping inverse problems, inverse design, and control problems in PDE-governed systems.

cs.AI↗

arXiv2026

The pair-instability origin of supernova 2023vbw

Stars in the initial and carbon-oxygen core mass ranges of $\sim140-260$ and $50-130$ M$_\odot$, respectively, with low metallicity are predicted to experience copious electron-positron pair production in their cores, leading to a runaway thermonuclear explosion that obliterates the entire star in a luminous and long-duration pair-instability supernova explosion. Some previous supernovae have been interpreted in this context but lack the full range of predicted properties. Here, we report detailed observations and modeling of the hydrogen-rich supernova 2023vbw, which exploded in a low-metallicity ($\sim0.1$ Z$_\odot$) environment in a dwarf star-forming galaxy at a redshift of $0.088$. Its light curve exhibits a luminous ($1.6\times10^{43}$ erg s$^{-1}$) and long-duration ($190$ days) main peak, resulting in a total radiated energy of $3\times10^{50}$ erg, more than an order of magnitude greater than canonical core-collapse supernovae. Semi-analytical light-curve modeling yields a blue supergiant-like progenitor with an ejecta mass of $170-350$ M$_\odot$, radioactive nickel mass of $1.2-1.6$ M$_\odot$, and explosion energy of $(6-13)\times10^{52}$ erg, well matched by pair-instability models. The early and late-phase light curve and spectra also show evidence for interaction of the supernova ejecta with an aspherical circumstellar medium. Discoveries of numerous such events with the upcoming Rubin Observatory and Roman Space Telescope will shed light on the deaths of the most massive stars in the Universe.

astro-ph.HE↗

arXiv2026

A Picture is Worth a Thousand Words? An Empirical Study of Aggregation Strategies for Visual Financial Document Retrieval

Visual RAG has offered an alternative to traditional RAG. It treats documents as images and uses vision encoders to obtain vision patch tokens. However, hundreds of patch tokens per document create retrieval and storage challenges in a vector database. Practical deployment requires aggregating them into a single vector. This raises a critical question: does single-vector aggregation lose key information in financial documents? We develop a diagnostic benchmark using financial documents where changes in single digits can lead to significant semantic shifts. Our experiments show that single-vector aggregation collapses different documents with almost identical vectors. Metrics show that the patch level detects semantic changes, and confirm that aggregation obscures these details. We identify global texture dominance as the root cause. Our findings are consistent across model scales, retrieval-optimized embeddings, and multiple mitigation strategies, highlighting significant risks for single-vector visual document retrieval in financial applications.

cs.CV↗

arXiv2026

DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic Distraction

Vision-language models (VLMs) are trained on large-scale image-text corpora that may contain private, copyrighted, or otherwise sensitive data, motivating membership inference as a tool for training-data auditing. This is especially challenging for deployed VLMs, where auditors typically observe only generated textual responses. Existing VLM membership inference attacks either rely on probability-level signals unavailable in such settings, or use mask-based semantic prediction tasks whose effectiveness depends on object-centric visual assumptions. To address these limitations, we propose DistractMIA, an output-only black-box framework based on semantic distraction. Rather than removing visual evidence, DistractMIA preserves the original image, inserts a known semantic distractor, and measures how generated responses change. This design is motivated by the intuition that member samples remain more anchored to the original image semantics, while non-member samples are more easily redirected toward the distractor. To make this signal reliable, DistractMIA calibrates distractor configurations on a reference set and derives membership scores from repeated textual generations, capturing response stability and distractor uptake without accessing logits, probabilities, or hidden states. Experiments across multiple VLMs and benchmarks show that DistractMIA consistently outperforms both output-only and stronger-access baselines. Its performance on a medical benchmark further demonstrates applicability beyond object-centric natural images.

cs.CV↗

arXiv2026

Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs

Hidden states change substantially across the layers of modern language models, but most layer-wise analyses focus on one aspect of that change. We propose Layer-wise Representation Dynamics (LRD), a framework with three layer-wise measurement families: Frenet (Grassmann speed and curvature) for global subspace motion, Neighborhood Retention Score (NRS) for local nearest-neighbor retention, and Graph Filtration Mutual Information (GFMI) for alignment with the final layer. Applying LRD to 31 models (encoder-based and decoder-based embedders, plus base LLMs) on 30 MTEB tasks reveals architectural and task-level differences that are not apparent from final-layer representations alone. We then use LRD for two applications: label-free model selection and inference-time layer pruning. For selection, all three model-level scores correlate positively with downstream MTEB performance, with end-to-end subspace displacement (d_{0,L}) the strongest, and the same direction holds on a smaller base-LLM MMLU panel. For pruning, GFMI is the only measurement-guided rule that beats Random at the 15% and 20% budgets and has the best median change at every budget. Frenet is effective only at the lightest budget, while NRS does not transfer from model selection to pruning. These results show that layer-wise structure provides signal for both interpretation and deployment decisions.

cs.LG↗

arXiv2026

Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration

The advancement of diffusion-based text-to-music generation has opened new avenues for zero-shot music editing. However, existing methods fail to achieve stem-specific timbre transfer, which requires altering specific stems while strictly preserving the background accompaniment. This limitation severely hinders practical application, since real-world production necessitates precise manipulation of components within dense mixtures. Our key finding is that, while vanilla cross-attention captures semantic features of stems, it lacks the spectral resolution to strictly localize targets in dense mixtures, leading to boundary leakage. To resolve this dilemma, we propose Polyphonia, a zero-shot editing framework with Acoustic-Informed Attention Calibration. Rather than relying solely on diffuse semantic attention, Polyphonia leverages a probabilistic acoustic prior to establish coarse boundaries, enabling non-target stems preserved precise semantic synthesis. For evaluation, we propose PolyEvalPrompts, a standardized prompt set with 1,170 timbre transfer tasks in polyphonic music. Specifically, Polyphonia achieves an increase of 15.5% in target alignment compared to baselines, while maintaining competitive music fidelity and non-target integrity.

cs.SD↗