Searcharxiv⌕ Search

arXiv subjects

Meng Wang

Publications and source records attributed to Meng Wang.

At least 19 recordsLinked to original sources
arXiv2026

Spectroscopic Evidence of Competing Diagonal Spin Interactions and Spin Disproportionation in the Bilayer Nickelate La$_3$Ni$_2$O$_7$

A comprehensive spectroscopic map of the electronic, magnetic, and lattice excitations is presented for the bilayer nickelate La$_3$Ni$_2$O$_7$ using Raman scattering at ambient pressure. Upon entering the spin density wave state below 153 K, the $A_{1g}$ channel exhibits an abrupt electronic spectral gap with a clear isosbestic point. In contrast, the $B_{1g}$ and $B_{2g}$ channels are dominated by pronounced two-magnon (2M) excitations, representing a signature of incipient Mottness. These 2M signals in both channels constitute evidence for two distinct in-plane spin exchange interactions along the Ni-O bonding and its diagonal directions. Calculations based on the spin wave theory further reveal that the 2M mode in the $B_{2g}$ channel arises from the competition between two bond-diagonal antiferromagnetic interactions mediated by nickel $d_{x^2-y^2}$ orbitals. Furthermore, emergent low-energy 2M excitations below 10 meV are found to originate from distinct, weaker spin moments, supporting spin disproportionation. Simultaneously, an anomalous softening of $B_{1g}$ phonons from 280 down to 4.5 K is uncovered, suggesting the presence of an incipient lattice instability leading to checkerboard-type breathing modulations. Collectively, these findings identify a ground state of the bilayer nickelate characterized by competing bond-diagonal interactions, spin disproportionation, and an incipient lattice instability, establishing key ingredients for understanding the mechanism of nickelate superconductivity.

cond-mat.str-el↗
arXiv2026

Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation

Personalized image generation aims to synthesize text-driven images conditioned on reference images, while mainly casting the generation as image customization for foreground and style transfer for background. Previous arts of diffusion models suffers from the text misalignment with background for image customization and foreground for style transfer during the denoising process. Such facts, as we observed, rooted from the entanglement among hybrid frequency bands during the denoising process. In particular, the low-frequency band primarily captures color information, mid-frequency band encodes global structure, while high-frequency band corresponds to local texture. Besides, the early (high-noise) denoising stage mainly focuses on the low-and-mid frequency bands, while the late (low-noise) denoising stage progressively exhibits the high-frequency band, which, all together, overwhelm the text prompt guidance, suffering from the heavy reliance on reference image. To address such salient limitation, in this paper, we study personalized generation based on dual references - customization and color style reference - to propose a paradigm to disentangle these Dual image references within Frequency-aware Diffusion Models, dubbed Dual-FDM, to simultaneously tackle two crucial personalized image generation tasks: customization style transfer and color style transfer, by disentangling different frequency bands via mask strategy within frequency domain. We further compute the ratio of information entropy of the substituted frequency bands to adaptively modulate the denoising timesteps between the early and late stages. Extensive experiments validate the superiority of Dual-FDM over the state-of-the-art diffusion models for personalized image generation. Our code can be accessed from https://github.com/htyjers/Dual-FDM.

cs.CV↗
arXiv2026

EviCast: Forecasting Retrieval Gains Through Shared Response Calibration

Retrieval-augmented generation (RAG) extends large language models with external evidence, yet relevant evidence does not ensure that a generator can use it. Indiscriminate retrieval can degrade task performance while adding retrieval and long-context inference costs. Existing methods neither determine before large-scale execution whether a generator, task distribution, and retriever configuration is worth deploying nor diagnose multiple candidate retrievers under a shared budget. We introduce EviCast, a framework that forecasts retrieval value through interventional evidence-state decomposition. EviCast measures a generator's response to controlled evidence states once and combines this shared profile with the offline evidence-state distribution of each candidate retriever, yielding the end-to-end net utility and its 95% lower confidence bound without executing every RAG configuration. A state-refinement analysis characterizes when its binary and topology-aware instantiations are exact and when shared calibration is statistically more efficient than per-retriever calibration. In frozen evaluations, EviCast correctly decides all 14 HotpotQA retrieval configurations with a forecast error of 2.75 F1 points while reducing diagnostic generation calls by 80%, and it attains the lowest forecast error among seven predictors in the low-budget regime. Its topology-aware instantiation, EviCast-T, captures the complementarity between terminal and bridge evidence, correctly deciding all 16 configurations on MuSiQue and HotpotQA and 23 of 24 after prospective transfer to a third dataset. These results show that retrieval deployment depends on both evidence availability and the generator's ability to convert evidence structure into stable net utility. Code is available at https://github.com/YiboWang2002/EviCast.

cs.CL↗
arXiv2026

EEG-HealthLLM: Hierarchical Adaptation of Large Language Models for Unified Heterogeneous EEG Health Assessment

Electroencephalography (EEG) provides a non-invasive means for neurological and mental health assessment, yet existing EEG models are typically developed for individual tasks and are difficult to unify across heterogeneous signal configurations and assessment objectives. Large language models (LLMs) offer a common interface for multiple tasks, but adapting heterogeneous EEG signals to a shared LLM raises a key challenge: how to preserve task-specific signal characteristics while enabling effective language-side parameter sharing. To address this problem, we propose EEG-HealthLLM, a unified and parameter-efficient framework for heterogeneous EEG health assessment. We introduce an Asymmetric Hierarchical Adaptation Strategy: task-specific EEG adapters preserve heterogeneous spatio-temporal dynamics, while a unified shared LoRA is injected into the LLM backbone (e.g., Phi-3) to capture shared high-level assessment semantics across tasks. We further establish EEG-HealthBench by reorganizing five existing EEG resources into paradigms covering epileptic seizure detection, major depressive disorder assessment, anxiety risk assessment, depressive symptom risk assessment, and emotional state assessment under a unified subject-independent protocol. Extensive experiments show that EEG-HealthLLM achieves an average balanced accuracy (BAC) of 69.58%, ranking first among the evaluated methods in both average BAC and macro-F1. Compared with independent single-task LoRA adaptation, it improves average BAC from 67.70% to 69.58% while reducing the aggregate language-side adapter footprint by 80.0%. Further analyses reveal task-dependent cross-task interactions and trade-offs, supporting the proposed hierarchical adaptation strategy. The implementation is publicly available at https://github.com/Marui-88/EEG-HealthLLM.

cs.CL↗
arXiv2026

Superconductivity of bilayer two-orbital Hubbard model for La$_{3}$Ni$_{2}$O$_{7}$ under high pressure

By combining density functional theory (DFT) and density matrix renormalization group calculations, we investigate the unusual pressure dependence of superconducting transition temperature ($T_c$) in the nickelate superconductor La$_{3}$Ni$_{2}$O$_{7}$. Using the hopping integrals and on-site potentials obtained by fitting the DFT band structures, we map a quantum phase diagram of a bilayer two-orbital Hubbard model with increasing pressure in a ladder geometry, which has an intermediate Hubbard repulsion and a Hund's coupling. Near $3/8$ filling, we find a strong spin density wave order, which at $3/8$ filling shows a real-space spin pattern similar to the spin-charge stripe order along a lattice direction. At $21/64$ filling, we find a superconducting phase with interlayer superconductivity (SC) in both the $d_{z^2}$ and $d_{x^2-y^2}$ orbitals, as well as in-plane SC in the $d_{z^2}$ orbital. Intriguingly, the SC is weakened with increasing pressure and transits to a Luttinger liquid above $80$ GPa, which qualitatively agrees with the experimental observations of decreasing $T_c$ with increasing pressure and a transition to Fermi liquid above $80$ GPa in La$_{3}$Ni$_{2}$O$_{7}$. Through a comparative study, we further show that the ratio of interaction to hopping integral, which reduces moderately with increasing pressure, may play a dominant role in the weakening of SC. Our results of this experimentally relevant model not only find a robust SC through suppressing the competing spin density wave order, but also give new insight into the unusual pressure dependence of SC in La$_{3}$Ni$_{2}$O$_{7}$.

cond-mat.supr-con↗
arXiv2026

VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection

Time-series anomaly detection (TSAD) requires identifying both immediate Point Anomalies and long-range Context Anomalies. However, existing foundation models face a fundamental trade-off: 1D temporal models provide fine-grained pointwise localization but lack a global contextual perspective, while 2D vision-based models capture global patterns but suffer from information bottlenecks due to a lack of temporal alignment and coarse-grained pointwise detection. To resolve this dilemma, we propose VETime, the first TSAD framework that unifies temporal and visual modalities through fine-grained visual-temporal alignment and dynamic fusion. VETime introduces a Reversible Image Conversion and a Patch-Level Temporal Alignment module to establish a shared visual-temporal timeline, preserving discriminative details while maintaining temporal sensitivity. Furthermore, we design an Anomaly Window Contrastive Learning mechanism and a Task-Adaptive Multi-Modal Fusion to adaptively integrate the complementary perceptual strengths of both modalities. Extensive experiments demonstrate that VETime significantly outperforms state-of-the-art models in zero-shot scenarios, achieving superior localization precision with lower computational overhead than current vision-based approaches. Code available at: https://github.com/yyyangcoder/VETime .

cs.CV↗
arXiv2026

MER-Bench: Benchmarking Multimodal Emotional Reappraisal for Image-Text Memes

Multimodal Emotional Reappraisal (MER) aims to shift affective interpretation by rewriting and editing a situation without altering its underlying semantic context. Despite advances in controllable editing and sentiment transfer, MER remains challenging under coupled multimodal constraints, especially in internet memes where images, embedded text, and layout jointly encode affective meaning. To bridge this gap, we present MER-Bench, a systematic benchmark for MER on image-text memes, containing over 3,000 real-world memes with fine-grained annotations for emotion transformation and structure-preserving multimodal editing. MER-Bench spans diverse visual, textual, and structural settings and is paired with a structured MLLM-as-a-Judge evaluation suite, comprising eight fine-grained metrics and three aggregated objectives for emotional alignment, content fidelity, and transformation strength. Extensive evaluation of 14 advanced multimodal models reveals that: (1) current models struggle to jointly balance affect, semantics, structure, and text; (2) strong visual editing does not imply effective MER, with poor embedded text rendering and affect-aware rewriting remaining key bottlenecks. Our results identify MER as a critical capability gap in current multimodal generation systems and highlight affective image-text reasoning as a key challenge for future work. Project Page: https://github.com/one-seven17/MER-Bench

cs.CV↗
arXiv2026

CAPTURER: A Dexterous Aerial Manipulator for Dynamic and Precise Grasping across Diverse Environments

As a representative form of embodied robotic interaction, aerial grasping requires close coordination between the aerial platform and manipulator. Most existing systems perform aerial grasping with static or slowly moving targets under fixed scenarios. Dynamic and precise grasping across different conditions introduces additional challenges, including target motion, localization drift, dynamic coupling, and external disturbances. In this work, we present CAPTURER, a dexterous aerial manipulator for centimeter-level grasping across diverse environments. To achieve the challenging goal, we first develop an onboard perception system for state estimation and target detection. Drift correction and global pose transformation are introduced to improve target localization during flight. A cooperative motion planner is proposed to coordinate the mobility of the aerial platform with the dexterity of the manipulator according to the relative target state. To maintain grasping accuracy under disturbances, we design a disturbance-rejection controller to compensate for dynamic coupling, model uncertainty, and external disturbances. The capability of CAPTURER is validated through indoor and outdoor experiments with both static and moving targets. The results demonstrate that CAPTURER achieves centimeter-level grasping accuracy for a marker pen measuring only 1.5 cm in diameter at flight speeds exceeding 1.5 m/s.

cs.RO↗
arXiv2026

Can LLMs Design Video Coding Tools? A Case Study on Planar Mode

This paper explores whether large language models (LLMs) can design video coding tools, a highly challenging task due to the intricate algorithmic coupling of tool modifications. In particular, we present an empirical case study on the Planar mode, a long-standing intra prediction tool in video coding standards. Our experiments operate within a generation-and-evaluation loop, with the LLM generating new Planar predictors, encoder trials evaluating their coding performance, and the LLM re-generating refined implementations based on the evaluation feedback. We first examine directly replacing the default Planar mode in the Fraunhofer Versatile Video Encoder (VVenC) under its faster preset. Experimental results demonstrate that the LLM-generated mode can outperform the conventional Planar mode on this lightweight toolset, achieving 0.18% bitrate savings with 0.4% complexity overhead on the standard benchmark. We further extend our evaluation to the Enhanced Compression Model (ECM). Leveraging newly introduced directional Planar modes, we investigate two integration strategies: directly replacing them, and introducing the LLM-generated predictor as an additional prediction mode with new syntax elements. The empirical results suggest that both strategies can yield coding gains under a constrained low-resolution setting. Overall, this study offers preliminary evidence and practical insights, highlighting both the potential and open challenges of LLM-based coding tool design.

cs.MM↗
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

Regret-Based Max-Pressure Traffic Signal Control under Uncertain Traffic States

Max-pressure (MP) traffic signal control selects phases using pressure scores computed from estimated traffic states, but these states are uncertain and their consequences depend on whether they alter phase ranking and how much pressure is lost. This paper develops a decision-oriented Regret-Based Max-Pressure framework that represents uncertainty through phase-selection regret, defined as the pressure loss of a candidate phase relative to the pressure-maximizing phase under each plausible latent state. We propose Stochastic Regret MP, which minimizes expected regret under a calibrated residual distribution, and Distributionally Robust (DR) Regret MP, which minimizes worst-case expected regret over a Wasserstein ambiguity set. Robustifying regret rather than absolute pressure makes the formulation invariant to state-dependent pressure components shared by all candidate phases, thereby focusing robustness on relative phase quality. We further derive an explicit queue-linear pressure-loss bound and establish strong queue stability when the net-service reserve exceeds the resulting loss coefficient. Numerical experiments show that both methods reduce normalized true-state pressure regret by about 70% relative to Point-estimate MP, while DR Regret MP yields lower network queues than direct robustification of absolute pressure. In microscopic SUMO experiments on a 28-intersection real-world network, Stochastic Regret MP and DR Regret MP reduce mean delay by 18.9% and 14.9%, respectively, and retain benefits under detector undercount and failure. The results show that representing uncertainty through its decision consequences can improve reliable traffic control under imperfect state information.

eess.SY↗
arXiv2026

RetiJev: Fast and Source-Grounded Ophthalmic Decision Models

Ophthalmic clinical decision support requires fast, accurate, and privacy-preserving inference, yet autoregressive large language models (LLMs) incur substantial latency and computational overhead for decisions among predefined actions. We therefore investigate a decision-oriented alternative to generative reasoning. Specifically, we first introduce RetiJev-Data, a source-grounded ophthalmology corpus comprising 78,158 clinical-decision and diagnosis questions derived from articles in PubMed Central and a MeSH vocabulary covering 531 eye diseases, and 50,074 guideline-grading questions spanning 11 grading systems, along with a 24,662-question evaluation benchmark. Based on this, we develop RetiJev, a family of 0.8B-9B decision models that directly score candidate answers without autoregressive decoding. Across all model sizes, RetiJev outperforms both a 27B LLM and the commercial Jev 1.13 decision model on guideline grading by 10.4-23.0 points. RetiJev-9B further achieves the highest accuracy on clinical decisions, improving over both baselines by 5.4-6.5 points while matching them on diagnosis. It answers a case in 158 ms on one GPU, 3.5x faster than LLM generation and 470x faster than reasoning. Models are released at https://github.com/Awenbocc/RetiJev.

cs.CL↗
arXiv2026

DICL-Qwen3VL: Decoupled Confidence Calibration for Interpretable Workwear Detection

Poor illumination and occlusion obscure clothing cues in indoor work sites, while diverse clothing styles complicate workwear compliance judgments. Although vision-language models (VLMs) support localization and semantic reasoning, their predictions often lack explicit supporting evidence, and a single confidence score cannot distinguish visual uncertainty from ambiguity in compliance judgments. We propose DICL-Qwen3VL, a decoupled interpretable VLM that integrates structured workwear detection, evidence generation, and separate visual and reasoning confidence estimates. First, low-rank adaptation (LoRA) adapts Qwen3-VL to localize visible upper-body clothing and identify workwear. Second, decoupled calibration separates visual observations from compliance reasoning and assigns a confidence score to each. Token entropy and sensitivity to image perturbations provide supervision for visual confidence, linking confidence estimation to the generated observations and their dependence on image content. Finally, group relative policy optimization (GRPO) jointly optimizes detection accuracy, output validity, and confidence calibration. Experiments on the company-collected Indoor Construction Site Workwear Dataset (ICSWD) and the web-collected Indoor Construction Workwear Dataset (WICWD) yield mAP@50 values of 0.730 and 0.753, respectively, outperforming the evaluated LoRA-adapted VLM baselines, including Qwen3-VL. The framework also provides explicit evidence and separate confidence scores to support manual review in industrial safety monitoring. WICWD is publicly available at https://github.com/DaErwen1/WICWD.

cs.CV↗
arXiv2026

STC-MGNet: Spatial-Temporal-Channel Attention-Enhanced Multimodal Graph Network for Pedestrian Intention Prediction

Accurate prediction of pedestrian crossing intentions plays a critical role in enhancing the safety of pedestrian-vehicle interactions in autonomous driving. However, effectively capturing subtle spatiotemporal patterns in pedestrian pose sequences and integrating complementary visual and ego-vehicle motion information remain challenging. This paper proposes a spatial-temporal-channel attention-enhanced multimodal graph network (STC-MGNet) for pedestrian crossing intention prediction. STC-MGNet introduces a spatial-temporal-channel (STC) attention-enhanced pose graph encoder to learn discriminative representations from pedestrian pose sequences. Three parallel attention branches selectively emphasize informative skeletal joints, observation frames, and feature channels, with their outputs integrated through learnable fusion weights. To leverage complementary visual and ego-vehicle motion information, a multi-stage cross-modal channel modulation mechanism is introduced to adaptively refine pose representations through modality-specific channel gating at successive graph encoding stages. Experimental results demonstrate that STC-MGNet achieves accuracy rates of 70%, 87%, and 88% on the JAADbeh, JAADall, and PIE datasets, respectively, outperforming several representative baseline methods. Ablation experiments further highlight the complementary contributions of visual and ego-vehicle motion information to prediction performance.

cs.CV↗
arXiv2026

Generative AI Availability, Grades, and Student Satisfaction at a Large University

The availability of generative AI (GenAI) has raised concerns that college students substitute GenAI for cognitive effort, earning high grades without learning. If this "GenAI substitution hypothesis" is true, grades should rise disproportionately in GenAI-susceptible courses--those relying more on assessments like take-home problem sets and essays rather than in-class exams. Student satisfaction (self-reported understanding and interest) may also shift. We test this hypothesis using syllabus and administrative data from a large U.S. university (2016-2025; 138,386 students; 72,730 course offerings). We measure GenAI susceptibility by extracting assessment types from syllabi with a human-validated LLM pipeline. We then use a difference-in-differences design comparing courses before and after ChatGPT's release, modeling COVID-19 effects as persistent or transient. Effects on grades and satisfaction are small and sensitive to COVID modeling choices, with no detectable differences by students' prior academic preparation. Exploratory analyses show that the link between pre-college test scores and grades has not detectably weakened in more susceptible courses, and that instructors have been making courses less susceptible since before ChatGPT. Our findings temper concerns that GenAI inflates grades and reduces satisfaction, partly because instructors may adapt their pedagogy.

cs.CY↗
arXiv2026

REVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces

Frontier LLM agents perform complex interactive tasks, but their inference costs motivate transferring their experience to smaller open-source agents. Distillation and latent communication typically require target-model training or access to source-model internals. We study how textual frontier-model trajectories can provide reusable local controls for a frozen agent. Inspired by protocol reverse engineering, we introduce $\textit{Agentic Latents}$, comprising anchored states and dynamic profiles of feedback--response cycles elicited by replay in the target model. Our training-free framework, $\textbf{REVEAL}$ ($\textbf{REV}$erse $\textbf{E}$ngineering $\textbf{A}$gentic $\textbf{L}$atents), uses these profiles and trajectory outcomes to match and select local events from successful and failed rollouts of the same task and source model. Their response-transition contrasts yield a target-specific steering direction, applied before each response. Within-benchmark evaluations on Terminal-Bench 2.1 and Humanity's Last Exam with tools report higher accuracy than unmodified agents across three targets. Representation analyses and behavioral case studies support reusing frontier-model experience as local activation control.

cs.AI↗
arXiv2026

Gas radiation and the gravity limit of flicker in a co-flowing hydrogen jet diffusion flame

Although weak at normal gravity, gas radiation sets the gravity at which a co-flowing hydrogen jet diffusion flame stops flickering. Flamelet-based simulations with unity Lewis numbers, which reproduce the flicker frequency measured by femtosecond coherent anti-Stokes Raman scattering within 4%, are combined with local stability analysis. At one tenth of normal gravity, the adiabatic flame flickers, the radiating flame does not, and switching the emission off restores flicker. Radiation acts through two mechanisms that do not weaken at reduced gravity. The hot outer layer loses buoyancy in proportion to the gas residence time, and a disturbance that displaces the flame also displaces its emission, which damps the disturbance on the lean flank (displaced-emission damping). Freezing the radiative source, which removes only its response to disturbances, slows the downstream recession of the oscillation more than tenfold. Both mechanisms slow the upstream spreading of disturbances. This spreading, competing with the co-flow, sets the onset location and the critical co-flow. Without radiation, the spreading speed scales with the square root of gravity; its radiative reduction does not. At reduced gravity, the flicker limit therefore becomes a straight line relating the square root of the co-flow Froude number to a radiation number, the ratio of buoyant to radiative time scales. The calibrated line places the critical gravity for the experimental co-flow at 0.13 times normal gravity, 2.6 times the adiabatic value. It correctly predicted whether two further flames keep flickering. Beyond the limit, transient wave packets can mimic flicker throughout a short drop-tower test.

physics.flu-dyn↗
arXiv2026

Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation

While long chain-of-thought (CoT) distillation significantly improves the reasoning abilities of language models, its underlying mechanism remains poorly understood. Current pipelines generally rely on rejection sampling to gather reasoning traces across diverse prompts, assuming that factual correctness and broad problem coverage are indispensable. Surprisingly, we find that training exclusively on flawed reasoning trajectories or a restricted prompt set yields nearly comparable performance. Driven by this counterintuitive finding, we propose the Behavioral Hypothesis: the essence of Long-CoT distillation is behavioral alignment with structured reasoning patterns, rather than factual knowledge memorization. We then validate this by demonstrating substantial reasoning gains even when models are fine-tuned exclusively on previously mastered problems-effectively isolating behavioral alignment from novel knowledge injection. Having established that reasoning patterns are the true bottleneck, we investigate how to learn them across varying levels of complexity optimally. We reveal a critical interplay: while the recent probability-based loss excels at learning simple patterns, the standard cross-entropy loss is essential for scaling to complex CoTs. We believe these insights demystify CoT distillation and provide a principled foundation for the future development of reasoning models. Code is available on https://github.com/yuyongcan/Long-CoT-Distillation.

cs.CL↗