Searcharxiv⌕ Search

arXiv subjects

Yidi Wang

Publications and source records attributed to Yidi Wang.

At least 19 recordsLinked to original sources
arXiv2026

R2S-Eval: Robot Evaluation with Real-to-Sim Calibration via Vision-Language Models

Evaluating robot manipulation policies is becoming increasingly important as generalist models, particularly vision-language-action (VLA) models, are deployed on physical robots. However, conventional real-world evaluation remains labor-intensive, unstable, and insufficiently informative. It requires repeated hardware trials, manual scene resets, and continuous operator monitoring, may produce different policy rankings across repeated evaluations, and primarily relies on success-rate metrics that provide limited information about execution quality. In contrast, humans assess robot performance by observing and comparing complete behaviors rather than relying solely on binary success outcomes. To this end, we propose R2S-Eval, an evaluation pipeline that combines real-to-sim calibration with vision-language model (VLM) preference evaluation. The real-to-sim component efficiently generates rollout videos in a simulator calibrated to the real-world evaluation setting, thereby reducing the need for repeated hardware trials. The VLM evaluator assesses the execution quality of rollout videos and produces pairwise preferences, which are subsequently aggregated into policy rankings. We further introduce a protocol to assess whether the proposed evaluation pipeline yields validated policy conclusions while mitigating the key challenges of conventional real-world evaluation. Experiments in both simulation and real-world settings demonstrate that R2S-Eval produces reliable and stable policy conclusions, achieves agreement with human preferences, substantially reduces repeated hardware-operation effort, and reveals behavior-quality differences that are not captured by binary success labels. In general, R2S-Eval advances robot evaluation from manual success counting toward automated, statistically stable, and quality-aware evaluation of robot behavior. Project page: https://r2s-eval.github.io.

cs.RO↗
arXiv2026

Modality Fault Lines: Structural Corruptions Reveal Fragile Omni-Modal Reasoning

Omni-modal large language models are increasingly evaluated on clean text--vision--audio inputs, where every channel is present, synchronized, and readily interpretable. Such scores are often taken as evidence of robust cross-modal fusion, but clean evaluation cannot tell whether success depends on stable cross-modal structure or on cues sufficient only in intact inputs. To address this gap, we define a modality fault line: a boundary at which model behavior becomes unstable when a modality remains present and human-interpretable, but its internal evidence structure is perturbed. We introduce SCEval (Structure-Corruption Evaluation) a diagnostic evaluation protocol that keeps the question, answer space, and modality channels fixed while applying controlled structural corruptions to text, vision, and audio individually and jointly. Built from $273$ human-verified tri-modal examples from Social-IQ, OmniBench, and VALOR, SCEval evaluates $15$ proprietary and open-source omni-modal systems. The results show that structural corruption lowers clean accuracy, text--vision damage forms the most stable shared fault line, and multi-modal degradation is non-additive rather than a simple function of the number of corrupted modalities. Clean omni-modal accuracy therefore does not establish that a model will remain reliable when cross-modal evidence becomes structurally unreliable.

cs.CL↗
arXiv2026

Physics-Informed CNN-LSTM for Street-Scale Urban Flood Prediction: Reconciling Aggregate Accuracy and Street-Level Plausibility

Deep learning surrogate models trained with mean-squared-error loss produce statistically accurate but physically unconstrained flood predictions: water may flow uphill, appear spontaneously, or smooth over street-level corridors. We develop a physics-informed training framework for CNN-LSTM models that predict urban flood depths at 15 min intervals over a 128x128 spatial grid. Three differentiable penalty terms are embedded into the loss: (i) a gravity loss penalizing depth increases against the water-surface-elevation gradient, (ii) a continuity loss enforcing local mass conservation with rainfall-adaptive thresholds, and (iii) a topography-aware false-alarm penalty modulated by the topographic wetness index (TWI). We evaluate on the Norfolk, Virginia flood dataset spanning two storm events (August 2017 and September 2022, 300 samples), with all variants trained on identical splits and robustness assessed over repeated random splits and leave-one-storm-out tests. A road-proximal evaluation restricted to a TWI-derived street mask quantifies street-level skill. The physics-constrained model achieves near-zero gravity violations (order 1e-6) and the highest street-channel recall (0.77 +/- 0.09 vs 0.44 +/- 0.10 for the unconstrained baseline), the capability most relevant to traffic routing, and its advantage more than doubles on a held-out storm; a uniform false-alarm variant attains 16% lower mean absolute error but suppresses street recall to 0.25. The TWI-modulated penalty reconciles this trade-off: it improves on the uniform variant on every metric, recovering 60% higher street recall at the lowest MAE among constrained variants and the best street-level F1. These results expose a fundamental tension between aggregate pixel-level error and application-specific physical plausibility, and show that terrain-aware loss modulation offers a principled resolution.

cs.LG↗
arXiv2026

Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for embodied intelligence, enabling robots to perform tasks based on natural language instructions and current visual input. However, existing VLA models struggle with long-horizon tasks due to compounding errors. Prior methods decompose tasks into subtasks of fixed granularity, which cannot adapt to the varying complexity of execution states, limiting their robustness in long-horizon tasks. To overcome this, we introduce Anticipation Model, which adaptively and recursively generates future subgoals. This model continuously adapts as the task unfolds, adjusting future subgoals in response to evolving dynamics, facilitating more reliable planning paths. Building on this concept, we propose Anticipation-VLA, a hierarchical VLA model that leverages the anticipation model to generate actionable subgoals that guide VLA policy execution. We implement Anticipation-VLA with finetuning a Unified Multimodal Model (UMM) for high-level subgoal generation and a goal-conditioned VLA policy for low-level action execution. Experiments in both simulated and real-world robotic tasks demonstrate the effectiveness of Anticipation-VLA, highlighting the importance of adaptive and recursive subgoal generation for robust policy execution.

cs.RO↗
arXiv2026

Nanoscale electronic variations in altermagnetic $\alpha$-MnTe

Altermagnets exhibit spin-split electronic bands like ferromagnets, yet they are magnetically compensated like collinear antiferromagnets. Altermagnets thus combine the benefits of ferromagnets and antiferromagnets, opening routes to tailored materials and applications. However, reported bulk signatures such as the anomalous Hall response in candidate altermagnets have been inconsistent across samples, suggesting that inhomogeneity may affect their functionality in electronic devices. Here, we use low-temperature scanning tunneling microscopy and spectroscopy to map the local electronic landscape of $\alpha$-MnTe on atomically flat cleaved single crystals. We resolve two distinct electronic regions. In Region A, the chemical potential lies near the valence-band edge and varies by $\sim$100 meV on the nanometer length scale. In Region B, the chemical potential lies near the middle of a wider band gap. We further identify an incommensurate charge modulation with periodicity (2.5$\pm$0.1)$a$, observed exclusively in Region A. Our work establishes that $\alpha$-MnTe can exhibit significant electronic non-uniformity, suggesting that nanoscale characterization is essential for its reliable use in electronic applications.

cond-mat.str-el↗
arXiv2026

Probing the Penetration Depth of Topological Surface States by Magnetic Impurity Scattering in V-doped Sb$_2$Te$_3$

Topological insulators host Dirac surface states (SS) protected by time-reversal symmetry. Inter-surface hybridization can gap the SS and give rise to the quantum spin Hall effect in films that are sufficiently thin compared to the SS penetration depth. However, quantifying the SS penetration depth typically requires painstaking synthesis of multiple films with varying thickness. Here we introduce a direct method to probe the SS penetration depth in bulk crystals, by studying the interplay between SS and magnetic impurities in \SVT. Using scanning tunneling microscopy and spectroscopy, we find that even sparse magnetic impurities ($\lesssim0.25\%$ vanadium) can gap the Dirac SS. However, a single V impurity induces only localized states, and does not form an impurity band, so the gapped Dirac dispersion is preserved away from the impurity. In high magnetic fields, we observe an energy shift of the $0^\text{th}$ Landau level and a suppression of quasiparticle lifetime at the Dirac point, indicating \newtext{magnetic} scattering of the SS. Crucially, by employing V impurities at different depths as precise scattering probes, we reveal the SS penetration depth on the sub-nanometer scale in a bulk crystal.

cond-mat.mes-hall↗
arXiv2026

Large language models for optical network O&M: Agent-embedded workflow for automation

With the continuous expansion of optical networks and the increasing diversity of services, existing operation and maintenance (O&M) approaches are increasingly challenged to meet the rising demands for intelligence and efficiency. Large language models (LLMs), endowed with advanced semantic understanding and contextual analysis capabilities, are emerging as a promising enabler for intelligent optical network O&M. Recent studies have demonstrated the feasibility of applying LLMs to optical network management, marking an important step toward intelligent automation. However, systematic investigations into how LLMs can be effectively integrated into existing O&M workflows remain limited. This paper addresses this gap by drawing inspiration from best practices in real-world O&M workflows and systematically identifying scenarios that are well suited for LLM integration. We highlight that agent-based design is key to improving the executability of tasks, and we propose a multi-Agent collaborative O&M architecture that integrates LLM capabilities with existing O&M tools. The proposed architecture leverages core LLM-related technologies including prompt engineering and tool invocation, to build Agent solutions targeting key tasks such as optical channel management, performance optimization, and fault management. This work presents a conceptual framework for embedding LLM-based Agents into optical network O&M workflows, forming agentized processes that demonstrate the feasibility of LLM-assisted task execution and lay the groundwork for future autonomous O&M systems featuring closed-loop perception, decision-making, and action.

physics.optics↗
arXiv2026

Kondo Reshapes Multiple Orders in a $5f$ van der Waals Material

Electron interactions can drive magnetism, superconductivity, and topology. However, the realization of these phases remains limited in van der Waals materials, and the full landscape of strong correlations remains uncharted in any context. While interactions between conduction electrons and localized spins yield a well-known competition between heavy fermions (Kondo hybridization) and magnetic order (RKKY exchange), such spin-driven competition represents only part of the correlated electron phase diagram. Here we demonstrate that a heavy-fermion state can also compete with charge order, such as the charge density wave (CDW) state typical in the van der Waals $4f$ rare-earth tritellurides (RTe$_3$). We exploit the spatially-extended $5f$ orbitals of $\beta$-UTe$_3$ to enhance Kondo hybridization compared to its isostructural RTe$_3$ cousins. Our scanning tunneling spectroscopy on $\beta$-UTe$_3$ shows Fano resonances characteristic of the heavy fermion state, while our quasiparticle interference imaging reveals the disappearance of Fermi-level nesting and the appearance of flat bands. We extend the tritelluride tight-binding model to include Kondo coupling and quantify the Fermi surface reconstruction. Consistent with the destruction of nesting, we observe no CDW in $\beta$-UTe$_3$. Our expansion of the Kondo phase diagram beyond spin-mediated competition opens new possibilities for proximity-induced phase engineering in correlated van der Waals heterostructures.

cond-mat.str-el↗
arXiv2025

The \'{e}tale Brauer-Manin obstruction for classifying stacks

We study the strong approximation for classifying stacks $BG$, where $G$ is a linear algebraic group over a number field $k$. More specifically, we prove that the \'etale Brauer-Manin obstruction is the only obstruction to strong approximation for $BG$. To prove the result, we formulate the theory of torsors and Galois twists for algebraic stacks.

math.NT↗
arXiv2025

PCR-CA: Parallel Codebook Representations with Contrastive Alignment for Multiple-Category App Recommendation

Modern app store recommender systems struggle with multiple-category apps, as traditional taxonomies fail to capture overlapping semantics, leading to suboptimal personalization. We propose PCR-CA (Parallel Codebook Representations with Contrastive Alignment), an end-to-end framework for improved CTR prediction. PCR-CA first extracts compact multimodal embeddings from app text, then introduces a Parallel Codebook VQ-AE module that learns discrete semantic representations across multiple codebooks in parallel -- unlike hierarchical residual quantization (RQ-VAE). This design enables independent encoding of diverse aspects (e.g., gameplay, art style), better modeling multiple-category semantics. To bridge semantic and collaborative signals, we employ a contrastive alignment loss at both the user and item levels, enhancing representation learning for long-tail items. Additionally, a dual-attention fusion mechanism combines ID-based and semantic features to capture user interests, especially for long-tail apps. Experiments on a large-scale dataset show PCR-CA achieves a +0.76% AUC improvement over strong baselines, with +2.15% AUC gains for long-tail apps. Online A/B testing further validates our approach, showing a +10.52% lift in CTR and a +16.30% improvement in CVR, demonstrating PCR-CA's effectiveness in real-world deployment. The new framework has now been fully deployed on the Microsoft Store.

cs.IR↗
arXiv2025

ECLIP: Energy-efficient and Practical Co-Location of ML Inference on Spatially Partitioned GPUs

As AI inference becomes mainstream, research has begun to focus on improving the energy consumption of inference servers. Inference kernels commonly underutilize a GPU's compute resources and waste power from idling components. To improve utilization and energy efficiency, multiple models can co-locate and share the GPU. However, typical GPU spatial partitioning techniques often experience significant overheads when reconfiguring spatial partitions, which can waste additional energy through repartitioning overheads or non-optimal partition configurations. In this paper, we present ECLIP, a framework to enable low-overhead energy-efficient kernel-wise resource partitioning between co-located inference kernels. ECLIP minimizes repartitioning overheads by pre-allocating pools of CU masked streams and assigns optimal CU assignments to groups of kernels through our resource allocation optimizer. Overall, ECLIP achieves an average of 13% improvement to throughput and 25% improvement to energy efficiency.

eess.SY↗
arXiv2025

Observatory Science with eXTP

Scheduled for launch in 2030, the enhanced X-ray Timing and Polarization (eXTP) telescope is a Chinese space-based mission aimed at studying extreme conditions and phenomena in astrophysics. eXTP will feature three main payloads: Spectroscopy Focusing Arrays (SFAs), Polarimetry Focusing Arrays (PFAs), and a Wide-field Camera (W2C). This white paper outlines observatory science, incorporating key scientific advances and instrumental changes since the publication of the previous white paper [1]. We will discuss perspectives of eXTP on the research domains of flare stars, supernova remnants, pulsar wind nebulae, cataclysmic variables, X-ray binaries, ultraluminous X-ray sources, AGN, and pulsar-based positioning and timekeeping.

astro-ph.IM↗
arXiv2025

Out-of-Distribution Graph Models Merging

This paper studies a novel problem of out-of-distribution graph models merging, which aims to construct a generalized model from multiple graph models pre-trained on different domains with distribution discrepancy. This problem is challenging because of the difficulty in learning domain-invariant knowledge implicitly in model parameters and consolidating expertise from potentially heterogeneous GNN backbones. In this work, we propose a graph generation strategy that instantiates the mixture distribution of multiple domains. Then, we merge and fine-tune the pre-trained graph models via a MoE module and a masking mechanism for generalized adaptation. Our framework is architecture-agnostic and can operate without any source/target domain data. Both theoretical analysis and experimental results demonstrate the effectiveness of our approach in addressing the model generalization problem.

cs.LG↗
arXiv2025

ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts

A central challenge in reinforcement learning (RL) is its dependence on extensive real-world interaction data to learn task-specific policies. While recent work demonstrates that large language models (LLMs) can mitigate this limitation by generating synthetic experience (noted as imaginary rollouts) for mastering novel tasks, progress in this emerging field is hindered due to the lack of a standard benchmark. To bridge this gap, we introduce ImagineBench, the first comprehensive benchmark for evaluating offline RL algorithms that leverage both real rollouts and LLM-imaginary rollouts. The key features of ImagineBench include: (1) datasets comprising environment-collected and LLM-imaginary rollouts; (2) diverse domains of environments covering locomotion, robotic manipulation, and navigation tasks; and (3) natural language task instructions with varying complexity levels to facilitate language-conditioned policy learning. Through systematic evaluation of state-of-the-art offline RL algorithms, we observe that simply applying existing offline RL algorithms leads to suboptimal performance on unseen tasks, achieving 35.44% success rate in hard tasks in contrast to 64.37% of method training on real rollouts for hard tasks. This result highlights the need for algorithm advancements to better leverage LLM-imaginary rollouts. Additionally, we identify key opportunities for future research: including better utilization of imaginary rollouts, fast online adaptation and continual learning, and extension to multi-modal tasks. Our code is publicly available at https://github.com/LAMDA-RL/ImagineBench.

cs.LG↗
arXiv2024

AHSG: Adversarial Attack on High-level Semantics in Graph Neural Networks

Adversarial attacks on Graph Neural Networks aim to perturb the performance of the learner by carefully modifying the graph topology and node attributes. Existing methods achieve attack stealthiness by constraining the modification budget and differences in graph properties. However, these methods typically disrupt task-relevant primary semantics directly, which results in low defensibility and detectability of the attack. In this paper, we propose an Adversarial Attack on High-level Semantics for Graph Neural Networks (AHSG), which is a graph structure attack model that ensures the retention of primary semantics. By combining latent representations with shared primary semantics, our model retains detectable attributes and relational patterns of the original graph while leveraging more subtle changes to carry out the attack. Then we use the Projected Gradient Descent algorithm to map the latent representations with attack effects to the adversarial graph. Through experiments on robust graph deep learning models equipped with defense strategies, we demonstrate that AHSG outperforms other state-of-the-art methods in attack effectiveness. Additionally, using Contextual Stochastic Block Models to detect the attacked graph further validates that our method preserves the primary semantics of the graph.

cs.LG↗
arXiv2024

When Large Language Models Meet Optical Networks: Paving the Way for Automation

Since the advent of GPT, large language models (LLMs) have brought about revolutionary advancements in all walks of life. As a superior natural language processing (NLP) technology, LLMs have consistently achieved state-of-the-art performance on numerous areas. However, LLMs are considered to be general-purpose models for NLP tasks, which may encounter challenges when applied to complex tasks in specialized fields such as optical networks. In this study, we propose a framework of LLM-empowered optical networks, facilitating intelligent control of the physical layer and efficient interaction with the application layer through an LLM-driven agent (AI-Agent) deployed in the control layer. The AI-Agent can leverage external tools and extract domain knowledge from a comprehensive resource library specifically established for optical networks. This is achieved through user input and well-crafted prompts, enabling the generation of control instructions and result representations for autonomous operation and maintenance in optical networks. To improve LLM's capability in professional fields and stimulate its potential on complex tasks, the details of performing prompt engineering, establishing domain knowledge library, and implementing complex tasks are illustrated in this study. Moreover, the proposed framework is verified on two typical tasks: network alarm analysis and network performance optimization. The good response accuracies and sematic similarities of 2,400 test situations exhibit the great potential of LLM in optical networks.

cs.NI↗
arXiv2024

GCAPS: GPU Context-Aware Preemptive Priority-based Scheduling for Real-Time Tasks

Scheduling real-time tasks that utilize GPUs with analyzable guarantees poses a significant challenge due to the intricate interaction between CPU and GPU resources, as well as the complex GPU hardware and software stack. While much research has been conducted in the real-time research community, several limitations persist, including the absence or limited availability of GPU-level preemption, extended blocking times, and/or the need for extensive modifications to program code. In this paper, we propose GCAPS, a GPU Context-Aware Preemptive Scheduling approach for real-time GPU tasks. Our approach exerts control over GPU context scheduling at the device driver level and enables preemption of GPU execution based on task priorities by simply adding one-line macros to GPU segment boundaries. In addition, we provide a comprehensive response time analysis of GPU-using tasks for both our proposed approach as well as the default Nvidia GPU driver scheduling that follows a work-conserving round-robin policy. Through empirical evaluations and case studies, we demonstrate the effectiveness of the proposed approaches in improving taskset schedulability and response time. The results highlight significant improvements over prior work as well as the default scheduling approach, with up to 40% higher schedulability, while also achieving predictable worst-case behavior on Nvidia Jetson embedded platforms.

cs.DC↗