Searcharxiv⌕ Search

arXiv subjects

Wei Dai

Publications and source records attributed to Wei Dai.

At least 73 records · Page 4Linked to original sources
arXiv2026

WaterVideoQA: ASV-Centric Perception and Rule-Compliant Reasoning via Multi-Modal Agents

While autonomous navigation has achieved remarkable success in passive perception (e.g., object detection and segmentation), it remains fundamentally constrained by a void in knowledge-driven, interactive environmental cognition. In the high-stakes domain of maritime navigation, the ability to bridge the gap between raw visual perception and complex cognitive reasoning is not merely an enhancement but a critical prerequisite for Autonomous Surface Vessels to execute safe and precise maneuvers. To this end, we present WaterVideoQA, the first large-scale, comprehensive Video Question Answering benchmark specifically engineered for all-waterway environments. This benchmark encompasses 3,029 video clips across six distinct waterway categories, integrating multifaceted variables such as volatile lighting and dynamic weather to rigorously stress-test ASV capabilities across a five-tier hierarchical cognitive framework. Furthermore, we introduce NaviMind, a pioneering multi-agent neuro-symbolic system designed for open-ended maritime reasoning. By synergizing Adaptive Semantic Routing, Situation-Aware Hierarchical Reasoning, and Autonomous Self-Reflective Verification, NaviMind transitions ASVs from superficial pattern matching to regulation-compliant, interpretable decision-making. Experimental results demonstrate that our framework significantly transcends existing baselines, establishing a new paradigm for intelligent, trustworthy interaction in dynamic maritime environments.

cs.CV↗
arXiv2026

Polariton-mediated binding of anti-aligned dipolar excitons

Interacting bosonic quasiparticles are the cornerstone for exploring many-body physics and nonlinear quantum phenomena in correlated light-matter systems. Strongly interacting dipolar excitons in van der Waals heterostructures have attracted significant interest due to their out-of-plane electric dipole moments and high tunability via the quantum-confined Stark effect (QCSE). However, leveraging these tunable dipolar excitons in strongly coupled exciton-photon systems to explore exotic many-body physics and macroscopic quantum phenomena remains experimentally elusive. Here, we report the strong coupling of dipolar excitons in a gated bilayer MoS2 device integrated with a one-dimensional photonic crystal hosting bound-states-in-continuum (BIC). The resulting polaritons hybridize cavity photons with a coherent superposition of two electrically tunable anti-aligned dipolar excitons, effectively binding them into composite quasiparticle states. By tuning the dipolar excitons into non-degenerate states via the QCSE, we realize in situ reconfiguration of the polariton wavefunction and observe an emergent polariton branch exhibiting non-monotonic Stark shifts. Notably, these tunable polaritons allow for customized control over nonlinear interactions through distinct excitonic hybridization and dipolar configurations. This in situ tunability offers a scalable pathway toward electrically programmable quantum fluids of light and correlated polariton phases in on-chip photonic integrated circuits.

physics.optics↗
arXiv2026

Towards Causality-Aware Modeling for Multimodal Brain-Muscle Interactions

Robust characterization of dynamic causal interactions in multivariate biomedical signals is essential for advancing computational and algorithmic methods in biomedical imaging. Conventional approaches, such as Dynamic Bayesian Networks (DBNs), often assume linear or simple statistical dependencies, while manifold based techniques like Convergent Cross Mapping (CCM) capture nonlinear, lagged interactions but lack probabilistic quantification and interventional modeling. We introduce a DBN informed CCM framework that integrates geometric manifold reconstruction with probabilistic temporal modeling. Applied to multimodal EEG-EMG recordings from dystonic and neurotypical children, the method quantifies uncertainty, supports interventional simulation, and reveals distinct frequency specific reorganization of corticomuscular pathways in dystonia. Experimental results show marked improvements in predictive consistency and causal stability as compared to baseline approaches, demonstrating the potential of causality aware multimodal modeling for developing quantitative biomarkers and guiding targeted neuromodulatory interventions.

eess.SP↗
arXiv2026

Human Behavior Atlas: Benchmarking Unified Psychological and Social Behavior Understanding

Using intelligent systems to perceive psychological and social behaviors, that is, the underlying affective, cognitive, and pathological states that are manifested through observable behaviors and social interactions, remains a challenge due to their complex, multifaceted, and personalized nature. Existing work tackling these dimensions through specialized datasets and single-task systems often miss opportunities for scalability, cross-task transfer, and broader generalization. To address this gap, we curate Human Behavior Atlas, a unified benchmark of diverse behavioral tasks designed to support the development of foundation models for understanding psychological and social behaviors. Human Behavior Atlas comprises over 100,000 samples spanning text, audio, and visual modalities, covering tasks on affective states, cognitive states, pathologies, and social processes. Our unification efforts can reduce redundancy and cost, enable training to scale efficiently across tasks, and enhance generalization of behavioral features across domains. On Human Behavior Atlas, we train three models: Omnisapiens-7B SFT, Omnisapiens-7B BAM, and Omnisapiens-7B RL. We show that training on Human Behavior Atlas enables models to consistently outperform existing multimodal LLMs across diverse behavioral tasks. Pretraining on Human Behavior Atlas also improves transfer to novel behavioral datasets; with the targeted use of behavioral descriptors yielding meaningful performance gains. The benchmark, models, and codes can be found at: https://github.com/MIT-MI/human_behavior_atlas.

cs.AI↗
arXiv2026

GENIUS: Generative Fluid Intelligence Evaluation Suite

Unified Multimodal Models (UMMs) have shown remarkable progress in visual generation. Yet, existing benchmarks predominantly assess $\textit{Crystallized Intelligence}$, which relies on recalling accumulated knowledge and learned schemas. This focus overlooks $\textit{Generative Fluid Intelligence (GFI)}$: the capacity to induce patterns, reason through constraints, and adapt to novel scenarios on the fly. To rigorously assess this capability, we introduce $\textbf{GENIUS}$ ($\textbf{GEN}$ Fluid $\textbf{I}$ntelligence Eval$\textbf{U}$ation $\textbf{S}$uite). We formalize $\textit{GFI}$ as a synthesis of three primitives. These include $\textit{Inducing Implicit Patterns}$ (e.g., inferring personalized visual preferences), $\textit{Executing Ad-hoc Constraints}$ (e.g., visualizing abstract metaphors), and $\textit{Adapting to Contextual Knowledge}$ (e.g., simulating counter-intuitive physics). Collectively, these primitives challenge models to solve problems grounded entirely in the immediate context. Our systematic evaluation of 12 representative models reveals significant performance deficits in these tasks. Crucially, our diagnostic analysis disentangles these failure modes. It demonstrates that deficits stem from limited context comprehension rather than insufficient intrinsic generative capability. To bridge this gap, we propose a training-free attention intervention strategy. Ultimately, $\textbf{GENIUS}$ establishes a rigorous standard for $\textit{GFI}$, guiding the field beyond knowledge utilization toward dynamic, general-purpose reasoning. Our dataset and code will be released at: $\href{https://github.com/arctanxarc/GENIUS}{https://github.com/arctanxarc/GENIUS}$.

cs.LG↗
arXiv2026

UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics

Scaling generalist GUI agents is hindered by the data scalability bottleneck of expensive human demonstrations and the "distillation ceiling" of synthetic teacher supervision. To transcend these limitations, we propose UI-Oceanus, a framework that shifts the learning focus from mimicking high-level trajectories to mastering interaction physics via ground-truth environmental feedback. Through a systematic investigation of self-supervised objectives, we identify that forward dynamics, defined as the generative prediction of future interface states, acts as the primary driver for scalability and significantly outweighs inverse inference. UI-Oceanus leverages this insight by converting low-cost autonomous exploration, which is verified directly by system execution, into high-density generative supervision to construct a robust internal world model. Experimental evaluations across a series of models demonstrate the decisive superiority of our approach: models utilizing Continual Pre-Training (CPT) on synthetic dynamics outperform non-CPT baselines with an average success rate improvement of 7% on offline benchmarks, which amplifies to a 16.8% gain in real-world online navigation. Furthermore, we observe that navigation performance scales with synthetic data volume. These results confirm that grounding agents in forward predictive modeling offers a superior pathway to scalable GUI automation with robust cross-domain adaptability and compositional generalization.

cs.LG↗
arXiv2026

A new strategy for achieving multiple continuous cooling stages in an adiabatic demagnetization refrigerator

This paper presents a three-stage continuous adiabatic demagnetization refrigerator (CADR) simultaneously providing cooling platforms at two different temperatures. Unlike conventional CADR with two continuous stages, this system does not require an extra continuous stage. It is achieved with carefully designed heat switch operations and stage sequences. This new strategy significantly reduces system complexity and mass. The detailed implementation of the two cooling platforms is described, and factors limiting system performance are analyzed. This CADR system has achieved a cooling power of 20 μW@1 K and 4 μW@300 mK simultaneously, offering a new design strategy for the development of CADR with multiple continuous stages.

astro-ph.IM↗
arXiv2026

Robust Processing and Learning: Principles, Methods, and Wireless Applications

This tutorial-style overview article examines the fundamental principles and methods of robustness, using wireless sensing and communication (WSC) as the narrative and exemplifying framework. First, we formalize the conceptual and mathematical foundations of robustness, highlighting the interpretations and relations across robust statistics, optimization, and machine learning. Key techniques, such as robust estimation and testing, distributionally robust optimization, and regularized and adversary training, are investigated. Together, the costs of robustness in system design, for example, the compromised nominal performances and the extra computational burdens, are discussed. Second, we review recent robust signal processing solutions for WSC that address model mismatch, data scarcity, adversarial perturbation, and distributional shift. Specific applications include robust ranging-based localization, modality sensing, channel estimation, receive combining, waveform design, and federated learning. Through this effort, we aim to introduce the classical developments and recent advances in robustness theory to the general signal processing community, exemplifying how robust statistical, optimization, and machine learning approaches can address the uncertainties inherent in WSC systems.

eess.SP↗
arXiv2026

Nonlinear Neumann boundary problems for $n$-Laplacian Liouville equation on a half space

In this paper, for general $n\geq2$, we classify solutions to $n$-Laplacian Liouville equation with positive nonlinear Neumann boundary condition on the half-space $\mathbb{R}^{n}_{+}$. Under the positive nonlinear Neumann boundary condition, our result extend the classification result for the second order Liouville equation in \cite{Li} from $n=2$ to general $n\geq2$, and also extend the classification result for critical $p$-Laplacian equation in \cite{Zhou} from $p<n$ to $p=n$.

math.AP↗
arXiv2026

Provable Defense Framework for LLM Jailbreaks via Noise-Augumented Alignment

Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the statistical stability of an ensemble. We introduce Certified Semantic Smoothing (CSS) via Stratified Randomized Ablation, a technique that partitions inputs into immutable structural prompts and mutable payloads to derive rigorous lo norm guarantees using the Hypergeometric distribution. To resolve performance degradation on sparse contexts, we employ Noise-Augmented Alignment Tuning (NAAT), which transforms the base model into a semantic denoiser. Extensive experiments on Llama-3 show that our method reduces the Attack Success Rate of gradient-based attacks from 84.2% to 1.2% while maintaining 94.1% benign utility, significantly outperforming character-level baselines which degrade utility to 74.3%. This framework provides a deterministic certificate of safety, ensuring that a model remains robust against all adversarial variants within a provable radius.

cs.CL↗
arXiv2026

A Control Theoretic Approach to Decentralized AI Economy Stabilization via Dynamic Buyback-and-Burn Mechanisms

The democratization of artificial intelligence through decentralized networks represents a paradigm shift in computational provisioning, yet the long-term viability of these ecosystems is critically endangered by the extreme volatility of their native economic layers. Current tokenomic models, which predominantly rely on static or threshold-based buyback heuristics, are ill-equipped to handle complex system dynamics and often function pro-cyclically, exacerbating instability during market downturns. To bridge this gap, we propose the Dynamic-Control Buyback Mechanism (DCBM), a formalized control-theoretic framework that utilizes a Proportional-Integral-Derivative (PID) controller with strict solvency constraints to regulate the token economy as a dynamical system. Extensive agent-based simulations utilizing Jump-Diffusion processes demonstrate that DCBM fundamentally outperforms static baselines, reducing token price volatility by approximately 66% and lowering operator churn from 19.5% to 8.1% in high-volatility regimes. These findings establish that converting tokenomics from static rules into continuous, structurally constrained control loops is a necessary condition for secure and sustainable decentralized intelligence networks.

cs.GT↗
arXiv2026

MathDoc: Benchmarking Structured Extraction and Active Refusal on Noisy Mathematics Exam Papers

The automated extraction of structured questions from paper-based mathematics exams is fundamental to intelligent education, yet remains challenging in real-world settings due to severe visual noise. Existing benchmarks mainly focus on clean documents or generic layout analysis, overlooking both the structural integrity of mathematical problems and the ability of models to actively reject incomplete inputs. We introduce MathDoc, the first benchmark for document-level information extraction from authentic high school mathematics exam papers. MathDoc contains \textbf{3,609} carefully curated questions with real-world artifacts and explicitly includes unrecognizable samples to evaluate active refusal behavior. We propose a multi-dimensional evaluation framework covering stem accuracy, visual similarity, and refusal capability. Experiments on SOTA MLLMs, including Qwen3-VL and Gemini-2.5-Pro, show that although end-to-end models achieve strong extraction performance, they consistently fail to refuse illegible inputs, instead producing confident but invalid outputs. These results highlight a critical gap in current MLLMs and establish MathDoc as a benchmark for assessing model reliability under degraded document conditions. Our project repository is available at \href{https://github.com/winnk123/papers/tree/master}{GitHub repository}

cs.CV↗
arXiv2025

A Lightweight Transfer Learning-Based State-of-Health Monitoring with Application to Lithium-ion Batteries in Autonomous Air Vehicles

Accurate and rapid state-of-health (SOH) monitoring plays an important role in indicating energy information for lithium-ion battery-powered portable mobile devices. To confront their variable working conditions, transfer learning (TL) emerges as a promising technique for leveraging knowledge from data-rich source working conditions, significantly reducing the training data required for SOH monitoring from target working conditions. However, traditional TL-based SOH monitoring is infeasible when applied in portable mobile devices since substantial computational resources are consumed during the TL stage and unexpectedly reduce the working endurance. To address these challenges, this paper proposes a lightweight TL-based SOH monitoring approach with constructive incremental transfer learning (CITL). First, taking advantage of the unlabeled data in the target domain, a semi-supervised TL mechanism is proposed to minimize the monitoring residual in a constructive way, through iteratively adding network nodes in the CITL. Second, the cross-domain learning ability of node parameters for CITL is comprehensively guaranteed through structural risk minimization, transfer mismatching minimization, and manifold consistency maximization. Moreover, the convergence analysis of the CITL is given, theoretically guaranteeing the efficacy of TL performance and network compactness. Finally, the proposed approach is verified through extensive experiments with a realistic autonomous air vehicles (AAV) battery dataset collected from dozens of flight missions. Specifically, the CITL outperforms SS-TCA, MMD-LSTM-DA, DDAN, BO-CNN-TL, and AS$^3$LSTM, in SOH estimation by 83.73%, 61.15%, 28.24%, 87.70%, and 57.34%, respectively, as evaluated using the index root mean square error.

cs.AI↗
arXiv2025

A New Particle Filter for Target Tracking in MIMO OFDM Integrated Sensing and Communications

Particle filtering for target tracking using multi-input multi-output (MIMO) pulse-Doppler radars faces three long-standing obstacles: a) the absence of reliable likelihood models for raw radar data; b) the computational and statistical complications that arise when nuisance parameters (e.g., complex path gains) are augmented into state vectors; and c) the prohibitive computational burden of extracting noisy measurements of range, Doppler, and angles from snapshots. Motivated by an optimization-centric interpretation of Bayes' rule, this article addresses these challenges by proposing a new particle filtering framework that evaluates each hypothesized state using a tailored cost function, rather than relying on an explicit likelihood relation. The framework yields substantial reductions in both running time and tracking error compared to existing schemes. In addition, we examine the implementation of the proposed particle filter in MIMO orthogonal frequency-division multiplexing (OFDM) systems, aiming to equip modern communication infrastructure with integrated sensing and communications (ISAC) capabilities. Experiments suggest that MIMO-OFDM with pulse-Doppler processing holds considerable promise for ISAC, particularly when wide bandwidth, extended on-target time, and large antenna aperture are utilized.

eess.SP↗
arXiv2025

Bayesian Inference of Heavy-Quark Dissipation and Jet Transport Parameters from D-Meson observables in heavy-ion collisions at the LHC energies

We perform the first simultaneous Bayesian inference of the temperature-dependent heavy-quark spatial diffusion coefficient $2πT\mathcal{D}_s$ and the scaled jet transport coefficient $\hat{q}/T^3$ in the quark-gluon plasma, utilizing $D$-meson nuclear modification factor $R_\text{AA}$ and elliptic flow $v_2$ data from Pb-Pb collisions at $\sqrt{s_\text{NN}} = 5.02\ \text{TeV}$. The analysis employs a unified improved Langevin transport model that incorporates both collisional and radiative energy loss, followed by coalescence plus fragmentation hadronization. The posterior distributions of the parameters of $\hat{q}/T^3$ and those of $2πT\mathcal{D}_s$ are well constrained, and compared with the results of theoretical models or other experimental data extraction, respectively. The $30-50\%$ centrality data provide significantly stronger constraints than the $0-10\%$ data. The extracted ratio $\hat{q}/κ$ between the quark jet transport and heavy-quark diffusion coefficients exhibits a non-monotonic temperature dependence, deviating from the value $2$ estimated from the definition, with a value interval spanning 0.25--0.8 corresponding to the mean values of the inferred parameters. This work establishes a data-driven quantitative relationship between these two fundamental transport properties in the same observables, offering crucial insight into their interplay in the strongly coupled medium.

nucl-th↗
arXiv2025

Analyzing Image Beyond Visual Aspect: Image Emotion Classification via Multiple-Affective Captioning

Image emotion classification (IEC) is a longstanding research field that has received increasing attention with the rapid progress of deep learning. Although recent advances have leveraged the knowledge encoded in pre-trained visual models, their effectiveness is constrained by the "affective gap" , limits the applicability of pre-training knowledge for IEC tasks. It has been demonstrated in psychology that language exhibits high variability, encompasses diverse and abundant information, and can effectively eliminate the "affective gap". Inspired by this, we propose a novel Affective Captioning for Image Emotion Classification (ACIEC) to classify image emotion based on pure texts, which effectively capture the affective information in the image. In our method, a hierarchical multi-level contrastive loss is designed for detecting emotional concepts from images, while an emotional attribute chain-of-thought reasoning is proposed to generate affective sentences. Then, a pre-trained language model is leveraged to synthesize emotional concepts and affective sentences to conduct IEC. Additionally, a contrastive loss based on semantic similarity sampling is designed to solve the problem of large intra-class differences and small inter-class differences in affective datasets. Moreover, we also take the images with embedded texts into consideration, which were ignored by previous studies. Extensive experiments illustrate that our method can effectively bridge the affective gap and achieve superior results on multiple benchmarks.

cs.CV↗
arXiv2025

Continual Alignment for SAM: Rethinking Foundation Models for Medical Image Segmentation in Continual Learning

In medical image segmentation, heterogeneous privacy policies across institutions often make joint training on pooled datasets infeasible, motivating continual image segmentation-learning from data streams without catastrophic forgetting. While the Segment Anything Model (SAM) offers strong zero-shot priors and has been widely fine-tuned across downstream tasks, its large parameter count and computational overhead challenge practical deployment. This paper demonstrates that the SAM paradigm is highly promising once its computational efficiency and performance can be balanced. To this end, we introduce the Alignment Layer, a lightweight, plug-and-play module which aligns encoder-decoder feature distributions to efficiently adapt SAM to specific medical images, improving accuracy while reducing computation. Building on SAM and the Alignment Layer, we then propose Continual Alignment for SAM (CA-SAM), a continual learning strategy that automatically adapts the appropriate Alignment Layer to mitigate catastrophic forgetting, while leveraging SAM's zero-shot priors to preserve strong performance on unseen medical datasets. Experimented across nine medical segmentation datasets under continual-learning scenario, CA-SAM achieves state-of-the-art performance. Our code, models and datasets will be released on \mbox{https://github.com/azzzzyo/Continual-Alignment-for-SAM.}

cs.CV↗
arXiv2025

Extreme polaritonic interactions in a room-temperature deterministic sub-nanocavity quantum electrodynamic platform

Pushing nanoscale optical confinement to its ultimate limits defines the regime of nano-cavity quantum electrodynamics (nano-cQED), where light--matter interactions approach the fundamental quantum limits of individual atoms, e.g., picocavities. However, realizing such extreme confinement in a stable and controllable manner remains a key challenge. Here, we introduce a van der Waals material-based nano-cQED platform by coupling monolayer MoS2 excitons to plasmonic sub-nanocavities formed via assembly of ultrasmall gold clusters (3-5 nm) in the nanogap of a nanoparticle-on-mirror nanocavity. These clusters emulate the field-confining role of atomic protrusions of the picocavities through a resonance-insensitive lightning-rod effect, achieving deep-subwavelength mode volumes. In this nano-cQED testbed, we observe pronounced multi-branch Rabi splittings and ultrastrong lower-branch polaritonic photoluminescence with up to 10^4-fold enhancement. This deterministic architecture provides a controllable pathway to access picocavity-like behavior and opens new opportunities for single-molecule spectroscopy and the exploration of nano-cQED.

physics.optics↗