arXiv subjects

Yang Yang

Publications and source records attributed to Yang Yang.

At least 307 records · Page 17Linked to original sources

arXiv2026

Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion

Multimodal learning (MML) is significantly constrained by modality imbalance, leading to suboptimal performance in practice. While existing approaches primarily focus on balancing the learning of different modalities to address this issue, they fundamentally overlook the inherent disproportion in model classification ability, which serves as the primary cause of this phenomenon. In this paper, we propose a novel multimodal learning approach to dynamically balance the classification ability of weak and strong modalities by incorporating the principle of boosting. Concretely, we first propose a sustained boosting algorithm in multimodal learning by simultaneously optimizing the classification and residual errors. Subsequently, we introduce an adaptive classifier assignment strategy to dynamically facilitate the classification performance of the weak modality. Furthermore, we theoretically analyze the convergence property of the cross-modal gap function, ensuring the effectiveness of the proposed boosting scheme. To this end, the classification ability of strong and weak modalities is expected to be balanced, thereby mitigating the imbalance issue. Empirical experiments on widely used datasets reveal the superiority of our method through comparison with various state-of-the-art (SOTA) multimodal learning baselines. The source code is available at https://github.com/njustkmg/NeurIPS25-AUG.

cs.CV↗

arXiv2026

$G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA

Retrieval-augmented generation is a practical paradigm for question answering over long documents, but it remains brittle for multimodal reading where text, tables, and figures are interleaved across many pages. First, flat chunking breaks document-native structure and cross-modal alignment, yielding semantic fragments that are hard to interpret in isolation. Second, even iterative retrieval can fail in long contexts by looping on partial evidence or drifting into irrelevant sections as noise accumulates, since each step is guided only by the current snippet without a persistent global search state. We introduce $G^2$-Reader, a dual-graph system, to address both issues. It evolves a Content Graph to preserve document-native structure and cross-modal semantics, and maintains a Planning Graph, an agentic directed acyclic graph of sub-questions, to track intermediate findings and guide stepwise navigation for evidence completion. On VisDoMBench across five multimodal domains, $G^2$-Reader with Qwen3-VL-32B-Instruct reaches 66.21\% average accuracy, outperforming strong baselines and a standalone GPT-5 (53.08\%).

cs.CL↗

arXiv2026

Early and Prediagnostic Detection of Pancreatic Cancer from Computed Tomography

Pancreatic ductal adenocarcinoma (PDAC), one of the deadliest solid malignancies, is often detected at a late and inoperable stage. Retrospective reviews of prediagnostic CT scans, when conducted by expert radiologists aware that the patient later developed PDAC, frequently reveal lesions that were previously overlooked. To help detecting these lesions earlier, we developed an automated system named ePAI (early Pancreatic cancer detection with Artificial Intelligence). It was trained on data from 1,598 patients from a single medical center. In the internal test involving 1,009 patients, ePAI achieved an area under the receiver operating characteristic curve (AUC) of 0.939-0.999, a sensitivity of 95.3%, and a specificity of 98.7% for detecting small PDAC less than 2 cm in diameter, precisely localizing PDAC as small as 2 mm. In an external test involving 7,158 patients across 6 centers, ePAI achieved an AUC of 0.918-0.945, a sensitivity of 91.5%, and a specificity of 88.0%, precisely localizing PDAC as small as 5 mm. Importantly, ePAI detected PDACs on prediagnostic CT scans obtained 3 to 36 months before clinical diagnosis that had originally been overlooked by radiologists. It successfully detected and localized PDACs in 75 of 159 patients, with a median lead time of 347 days before clinical diagnosis. Our multi-reader study showed that ePAI significantly outperformed 30 board-certified radiologists by 50.3% (P < 0.05) in sensitivity while maintaining a comparable specificity of 95.4% in detecting PDACs early and prediagnostic. These findings suggest its potential of ePAI as an assistive tool to improve early detection of pancreatic cancer.

cs.CV↗

arXiv2026

Assembling the Mind's Mosaic: Towards EEG Semantic Intent Decoding

Enabling natural communication through brain-computer interfaces (BCIs) remains one of the most profound challenges in neuroscience and neurotechnology. While existing frameworks offer partial solutions, they are constrained by oversimplified semantic representations and a lack of interpretability. To overcome these limitations, we introduce Semantic Intent Decoding (SID), a novel framework that translates neural activity into natural language by modeling meaning as a flexible set of compositional semantic units. SID is built on three core principles: semantic compositionality, continuity and expandability of semantic space, and fidelity in reconstruction. We present BrainMosaic, a deep learning architecture implementing SID. BrainMosaic decodes multiple semantic units from EEG/SEEG signals using set matching and then reconstructs coherent sentences through semantic-guided reconstruction. This approach moves beyond traditional pipelines that rely on fixed-class classification or unconstrained generation, enabling a more interpretable and expressive communication paradigm. Extensive experiments on multilingual EEG and clinical SEEG datasets demonstrate that SID and BrainMosaic offer substantial advantages over existing frameworks, paving the way for natural and effective BCI-mediated communication.

q-bio.NC↗

arXiv2026

LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal Models

Large multimodal models (LMMs) have achieved impressive performance on various vision-language tasks, but their substantial computational and memory costs hinder their practical deployment. Existing compression methods often decouple low-rank decomposition and quantization, leading to compounded reconstruction errors, especially in multimodal architectures with cross-modal redundancy. To address this issue, we propose LLaVA-FA, a novel efficient LMM that performs joint low-rank plus quantization approximation in the frequency domain. By leveraging the de-correlation and conjugate symmetry properties of Fourier transform, LLaVA-FA achieves more compact and accurate weight representations. Furthermore, we introduce PolarQuant, a polar-coordinate quantization method tailored for complex matrices, and an optional diagonal calibration (ODC) scheme that eliminates the need for large-scale calibration data. Extensive experimental results demonstrate that our proposed LLaVA-FA outperforms existing efficient multimodal models across multiple benchmarks while maintaining minimal activated parameters and low computational costs, validating its effectiveness as a powerful solution for compressing LMMs.

cs.CV↗

arXiv2026

GRASP: Guided Region-Aware Sparse Prompting for Adapting MLLMs to Remote Sensing

In recent years, Multimodal Large Language Models (MLLMs) have made significant progress in visual question answering tasks. However, directly applying existing fine-tuning methods to remote sensing (RS) images often leads to issues such as overfitting on background noise or neglecting target details. This is primarily due to the large-scale variations, sparse target distributions, and complex regional semantic features inherent in RS images. These challenges limit the effectiveness of MLLMs in RS tasks. To address these challenges, we propose a parameter-efficient fine-tuning (PEFT) strategy called Guided Region-Aware Sparse Prompting (GRASP). GRASP introduces spatially structured soft prompts associated with spatial blocks extracted from a frozen visual token grid. Through a question-guided sparse fusion mechanism, GRASP dynamically aggregates task-specific context into a compact global prompt, enabling the model to focus on relevant regions while filtering out background noise. Extensive experiments on multiple RSVQA benchmarks show that GRASP achieves competitive performance compared to existing fine-tuning and prompt-based methods while maintaining high parameter efficiency.

cs.CV↗

arXiv2026

Region-aware Spatiotemporal Modeling with Collaborative Domain Generalization for Cross-Subject EEG Emotion Recognition

Cross-subject EEG-based emotion recognition (EER) remains challenging due to strong inter-subject variability, which induces substantial distribution shifts in EEG signals, as well as the high complexity of emotion-related neural representations in both spatial organization and temporal evolution. Existing approaches typically improve spatial modeling, temporal modeling, or generalization strategies in isolation, which limits their ability to align representations across subjects while capturing multi-scale dynamics and suppressing subject-specific bias within a unified framework. To address these gaps, we propose a Region-aware Spatiotemporal Modeling framework with Collaborative Domain Generalization (RSM-CoDG) for cross-subject EEG emotion recognition. RSM-CoDG incorporates neuroscience priors derived from functional brain region partitioning to construct region-level spatial representations, thereby improving cross-subject comparability. It also employs multi-scale temporal modeling to characterize the dynamic evolution of emotion-evoked neural activity. In addition, the framework employs a collaborative domain generalization strategy, incorporating multidimensional constraints to reduce subject-specific bias in a fully unseen target subject setting, which enhances the generalization to unknown individuals. Extensive experimental results on SEED series datasets demonstrate that RSM-CoDG consistently outperforms existing competing methods, providing an effective approach for improving robustness. The source code is available at https://github.com/RyanLi-X/RSM-CoDG.

cs.CV↗

arXiv2026

ThinkTank-ME: A Multi-Expert Framework for Middle East Event Forecasting

Event forecasting is inherently influenced by multifaceted considerations, including international relations, regional historical dynamics, and cultural contexts. However, existing LLM-based approaches employ single-model architectures that generate predictions along a singular explicit trajectory, constraining their ability to capture diverse geopolitical nuances across complex regional contexts. To address this limitation, we introduce ThinkTank-ME, a novel Think Tank framework for Middle East event forecasting that emulates collaborative expert analysis in real-world strategic decision-making. To facilitate expert specialization and rigorous evaluation, we construct POLECAT-FOR-ME, a Middle East-focused event forecasting benchmark. Experimental results demonstrate the superiority of multi-expert collaboration in handling complex temporal geopolitical forecasting tasks. The code is available at https://github.com/LuminosityX/ThinkTank-ME.

cs.LG↗

arXiv2026

Sora as a World Model? A Complete Survey on Text-to-Video Generation

The evolution of video generation from text, from animating MNIST to simulating the world with Sora, has progressed at a breakneck speed. Here, we systematically discuss how far text-to-video generation technology supports essential requirements in world modeling. We curate 250+ studies on text-based video synthesis and world modeling. We then observe that recent models increasingly support spatial, action, and strategic intelligences in world modeling through adherence to completeness, consistency, invention, as well as human interaction and control. We conclude that text-to-video generation is adept at world modeling, although homework in several aspects, such as the diversity-consistency trade-offs, remains to be addressed.

cs.AI↗

arXiv2026

Physics-guided foundation model for universal speckle removal in ultrathin multimode fiber imaging

Ultrathin multimode fibers (MMFs) promise endoscopes with hair-scale diameters for accessing sub-millimeter anatomy, but in MMF far-field imaging the required small collection aperture drives speckle-dominated measurements that rapidly degrade image fidelity. Here we present Speckle Clean Network (SCNet), a physics-guided foundation model for universal speckle removal that makes photon-limited, single-fiber collection compatible with high-fidelity reconstruction across diverse scattering conditions without target-specific retraining. SCNet combines a Mixture of Experts (MoE) architecture with material-aware routing, wavelet-based frequency decomposition to separate structure from speckle across sub-bands, and a curriculum-style optimization that progressively enforces spectral consistency before spatial fidelity. Using an ultrathin dual-fiber holographic probe, we deliver wavefront-shaped illumination through one MMF and collect backscattered photons through a parallel MMF. We validate SCNet on 3D plastic objects over varying working distances, resolve 5.66 lp/mm on a paper USAF target, and restore fine structures on leaves and metal surfaces. On rabbit heart and kidney tissues, SCNet improves recovery of low-contrast anatomical texture under the same ultrathin collection constraint. We further compress SCNet through multi-teacher distillation to reduce computation while preserving reconstruction quality, enabling inference at 60 FPS. This work effectively decouples image quality from probe size, establishing a speckle-free ultrathin endoscopy for stand-off imaging in confined spaces.

physics.optics↗

arXiv2026

Genie Centurion: Accelerating Scalable Real-World Robot Training with Human Rewind-and-Refine Guidance

While Vision-Language-Action (VLA) models show strong generalizability in various tasks, real-world deployment of robotic policy still requires large-scale, high-quality human expert demonstrations. However, data collection via human teleoperation requires continuous operator attention, which is costly, hard to scale. To address this, we propose Genie Centurion (GCENT), a scalable and general data collection paradigm based on human rewind-and-refine guidance, enabling robots' interactive learning in deployment. GCENT starts at an imperfect policy and improves over time. When the robot execution failures occur, GCENT allows robots to revert to a previous state with a rewind mechanism, after which a teleoperator provides corrective demonstrations to refine the policy. This framework supports a one-human-to-many-robots supervision scheme with a Task Sentinel module, which autonomously predicts task success and solicits human intervention when necessary. Empirical results show that GCENT achieves up to 40% higher task success rates than state-of-the-art data collection methods, and reaches comparable performance using less than half the data in long-horizon and precise tasks. We also quantify the data yield-to-effort ratio under multi-robot scenarios, demonstrating GCENT's potential for scalable and cost-efficient robot policy training in real-world environments.

cs.RO↗

arXiv2026

Hypothesis Generation via LLM-Automated Language Bias for ILP

Inductive Logic Programming (ILP) is a principled approach for generalizing regularities from data and constructing hypotheses as interpretable logic programs. However, a key limitation is its reliance on expert-crafted language bias - the predicate inventory, types, and mode declarations that delimit the search space. We propose hypothesis generation via LLM-automated language bias: multi-agent LLMs design the bias from raw text and translate descriptions into typed facts, and a robust ILP solver induces rules under a global consistency objective. This approach reduces traditional ILP's reliance on predefined symbolic structures and the noise sensitivity of LLM-only pipelines that directly generate hypotheses as text or code. Extensive experiments in diverse, challenging scenarios validate superior performance, providing a practical, explainable, and verifiable route to hypothesis generation.

cs.AI↗

arXiv2026

Experimental robustness benchmarking of quantum neural networks on a superconducting quantum processor

Quantum machine learning (QML) models, like their classical counterparts, are vulnerable to adversarial attacks, hindering their secure deployment. Here, we report the first systematic experimental robustness benchmark for 20-qubit quantum neural network (QNN) classifiers executed on a superconducting processor. Our benchmarking framework features an efficient adversarial attack algorithm designed for QNNs, enabling quantitative characterization of adversarial robustness and robustness bounds. From our analysis, we verify that adversarial training reduces sensitivity to targeted perturbations by regularizing input gradients, significantly enhancing QNN's robustness. Additionally, our analysis reveals that QNNs exhibit superior adversarial robustness compared to classical neural networks, an advantage attributed to inherent quantum noise. Furthermore, the empirical upper bound extracted from our attack experiments shows a minimal deviation ($3 \times 10^{-3}$) from the theoretical lower bound, providing strong experimental confirmation of the attack's effectiveness and the tightness of fidelity-based robustness bounds. This work establishes a critical experimental framework for assessing and improving quantum adversarial robustness, paving the way for secure and reliable QML applications.

quant-ph↗

arXiv2026

Exact dynamics and bound states of a cavity coupled to a two-dimensional reservoir

We demonstrate a robust scheme for quantum information storage based on bound states in a two-dimensional coupled-cavity array. When a target cavity is tuned to resonance with the array, a bound state in the continuum (BIC) emerges, coexisting with two conventional bound states outside the band. The resulting dynamics reflects a delicate interplay between these bound states, which can be fully captured through exact analytical solutions. In the weak-coupling regime, the BIC dominates, enabling perfect and persistent information storage. At stronger coupling, all bound states contribute, leading to oscillatory behavior and reduced storage fidelity. These results, valid at both zero and finite reservoir temperatures and further supported by a single-particle framework, reveal distinctive non-Markovian features in continuous-variable systems and highlight the potential of photonic lattices for scalable all-optical decoherence-free quantum memory platforms.

quant-ph↗

arXiv2026

FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains

Building upon FutureX, which established a live benchmark for general-purpose future prediction, this report introduces FutureX-Pro, including FutureX-Finance, FutureX-Retail, FutureX-PublicHealth, FutureX-NaturalDisaster, and FutureX-Search. These together form a specialized framework extending agentic future prediction to high-value vertical domains. While generalist agents demonstrate proficiency in open-domain search, their reliability in capital-intensive and safety-critical sectors remains under-explored. FutureX-Pro targets four economically and socially pivotal verticals: Finance, Retail, Public Health, and Natural Disaster. We benchmark agentic Large Language Models (LLMs) on entry-level yet foundational prediction tasks -- ranging from forecasting market indicators and supply chain demands to tracking epidemic trends and natural disasters. By adapting the contamination-free, live-evaluation pipeline of FutureX, we assess whether current State-of-the-Art (SOTA) agentic LLMs possess the domain grounding necessary for industrial deployment. Our findings reveal the performance gap between generalist reasoning and the precision required for high-value vertical applications.

cs.AI↗

arXiv2026

Cross-Modal Attention Network with Dual Graph Learning in Multimodal Recommendation

Multimedia recommendation systems leverage user-item interactions and multimodal information to capture user preferences, enabling more accurate and personalized recommendations. Despite notable advancements, existing approaches still face two critical limitations: first, shallow modality fusion often relies on simple concatenation, failing to exploit rich synergic intra- and inter-modal relationships; second, asymmetric feature treatment-where users are only characterized by interaction IDs while items benefit from rich multimodal content-hinders the learning of a shared semantic space. To address these issues, we propose a Cross-modal Recursive Attention Network with dual graph Embedding (CRANE). To tackle shallow fusion, we design a core Recursive Cross-Modal Attention (RCA) mechanism that iteratively refines modality features based on cross-correlations in a joint latent space, effectively capturing high-order intra- and inter-modal dependencies. For symmetric multimodal learning, we explicitly construct users' multimodal profiles by aggregating features of their interacted items. Furthermore, CRANE integrates a symmetric dual-graph framework-comprising a heterogeneous user-item interaction graph and a homogeneous item-item semantic graph-unified by a self-supervised contrastive learning objective to fuse behavioral and semantic signals. Despite these complex modeling capabilities, CRANE maintains high computational efficiency. Theoretical and empirical analyses confirm its scalability and high practical efficiency, achieving faster convergence on small datasets and superior performance ceilings on large-scale ones. Comprehensive experiments on four public real-world datasets validate an average 5% improvement in key metrics over state-of-the-art baselines.

cs.IR↗

arXiv2026

Baiting AI: Deceptive Adversary Against AI-Protected Industrial Infrastructures

This paper explores a new cyber-attack vector targeting Industrial Control Systems (ICS), particularly focusing on water treatment facilities. Developing a new multi-agent Deep Reinforcement Learning (DRL) approach, adversaries craft stealthy, strategically timed, wear-out attacks designed to subtly degrade product quality and reduce the lifespan of field actuators. This sophisticated method leverages DRL methodology not only to execute precise and detrimental impacts on targeted infrastructure but also to evade detection by contemporary AI-driven defence systems. By developing and implementing tailored policies, the attackers ensure their hostile actions blend seamlessly with normal operational patterns, circumventing integrated security measures. Our research reveals the robustness of this attack strategy, shedding light on the potential for DRL models to be manipulated for adversarial purposes. Our research has been validated through testing and analysis in an industry-level setup. For reproducibility and further study, all related materials, including datasets and documentation, are publicly accessible.

cs.CR↗

arXiv2026

LPFQA: A Long-Tail Professional Forum-based Benchmark for LLM Evaluation

Large Language Models (LLMs) perform well on standard reasoning and question-answering benchmarks, yet such evaluations often fail to capture their ability to handle long-tail, expertise-intensive knowledge in real-world professional scenarios. We introduce LPFQA, a long-tail knowledge benchmark derived from authentic professional forum discussions, covering 7 academic and industrial domains with 430 curated tasks grounded in practical expertise. LPFQA evaluates specialized reasoning, domain-specific terminology understanding, and contextual interpretation, and adopts a hierarchical difficulty structure to ensure semantic clarity and uniquely identifiable answers. Experiments on over multiple mainstream LLMs reveal substantial performance gaps, particularly on tasks requiring deep domain reasoning, exposing limitations overlooked by existing benchmarks. Overall, LPFQA provides an authentic and discriminative evaluation framework that complements prior benchmarks and informs future LLM development.

cs.AI↗