arXiv subjects

Zhenyu Yu

Publications and source records attributed to Zhenyu Yu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Tri-Subspaces Disentanglement for Multimodal Sentiment Analysis

Multimodal Sentiment Analysis (MSA) integrates language, visual, and acoustic modalities to infer human sentiment. Most existing methods either focus on globally shared representations or modality-specific features, while overlooking signals that are shared only by certain modality pairs. This limits the expressiveness and discriminative power of multimodal representations. To address this limitation, we propose a Tri-Subspace Disentanglement (TSD) framework that explicitly factorizes features into three complementary subspaces: a common subspace capturing global consistency, submodally-shared subspaces modeling pairwise cross-modal synergies, and private subspaces preserving modality-specific cues. To keep these subspaces pure and independent, we introduce a decoupling supervisor together with structured regularization losses. We further design a Subspace-Aware Cross-Attention (SACA) fusion module that adaptively models and integrates information from the three subspaces to obtain richer and more robust representations. Experiments on CMU-MOSI and CMU-MOSEI demonstrate that TSD achieves state-of-the-art performance across all key metrics, reaching 0.691 MAE on CMU-MOSI and 54.9% ACC-7 on CMU-MOSEI, and also transfers well to multimodal intent recognition tasks. Ablation studies confirm that tri-subspace disentanglement and SACA jointly enhance the modeling of multi-granular cross-modal sentiment cues.

cs.MM↗

arXiv2026

ViLBias: Detecting and Reasoning about Bias in Multimodal Content

Detecting bias in multimodal news requires models that reason over text--image pairs, not just classify text. In response, we present ViLBias, a VQA-style benchmark and framework for detecting and reasoning about bias in multimodal news. The dataset comprises 40,945 text--image pairs from diverse outlets, each annotated with a bias label and concise rationale using a two-stage LLM-as-annotator pipeline with hierarchical majority voting and human-in-the-loop validation. We evaluate Small Language Models (SLMs), Large Language Models (LLMs), and Vision--Language Models (VLMs) across closed-ended classification and open-ended reasoning (oVQA), and compare parameter-efficient tuning strategies. Results show that incorporating images alongside text improves detection accuracy by 3--5\%, and that LLMs/VLMs better capture subtle framing and text--image inconsistencies than SLMs. Parameter-efficient methods (LoRA/QLoRA/Adapters) recover 97--99\% of full fine-tuning performance with $<5\%$ trainable parameters. For oVQA, reasoning accuracy spans 52--79\% and faithfulness 68--89\%, both improved by instruction tuning; closed accuracy correlates strongly with reasoning ($r = 0.91$). ViLBias offers a scalable benchmark and strong baselines for multimodal bias detection and rationale quality.

cs.AI↗

arXiv2026

ADS-POI: Agentic Spatiotemporal State Decomposition for Next Point-of-Interest Recommendation

Next point-of-interest (POI) recommendation requires modeling user mobility as a spatiotemporal sequence, where different behavioral factors may evolve at different temporal and spatial scales. Most existing methods compress a user's history into a single latent representation, which tends to entangle heterogeneous signals such as routine mobility patterns, short-term intent, and temporal regularities. This entanglement limits the flexibility of state evolution and reduces the model's ability to adapt to diverse decision contexts. We propose ADS-POI, a spatiotemporal state decomposition framework for next POI recommendation. ADS-POI represents a user with multiple parallel evolving latent sub-states, each governed by its own spatiotemporal transition dynamics. These sub-states are selectively aggregated through a context-conditioned mechanism to form the decision state used for prediction. This design enables different behavioral components to evolve at different rates while remaining coordinated under the current spatiotemporal context. Extensive experiments on three real-world benchmark datasets from Foursquare and Gowalla demonstrate that ADS-POI consistently outperforms strong state-of-the-art baselines under a full-ranking evaluation protocol. The results show that decomposing user behavior into multiple spatiotemporally aware states leads to more effective and robust next POI recommendation. Our code is available at https://github.com/YuZhenyuLindy/ADS-POI.git.

cs.IR↗

arXiv2026

ReDiStory: Region-Disentangled Diffusion for Consistent Visual Story Generation

Generating coherent visual stories requires maintaining subject identity across multiple images while preserving frame-specific semantics. Recent training-free methods concatenate identity and frame prompts into a unified representation, but this often introduces inter-frame semantic interference that weakens identity preservation in complex stories. We propose ReDiStory, a training-free framework that improves multi-frame story generation via inference-time prompt embedding reorganization. ReDiStory explicitly decomposes text embeddings into identity-related and frame-specific components, then decorrelates frame embeddings by suppressing shared directions across frames. This reduces cross-frame interference without modifying diffusion parameters or requiring additional supervision. Under identical diffusion backbones and inference settings, ReDiStory improves identity consistency while maintaining prompt fidelity. Experiments on the ConsiStory+ benchmark show consistent gains over 1Prompt1Story on multiple identity consistency metrics. Code is available at: https://github.com/YuZhenyuLindy/ReDiStory

cs.CV↗

arXiv2026

StoryState: Agent-Based State Control for Consistent and Editable Storybooks

Large multimodal models have enabled one-click storybook generation, where users provide a short description and receive a multi-page illustrated story. However, the underlying story state, such as characters, world settings, and page-level objects, remains implicit, making edits coarse-grained and often breaking visual consistency. We present StoryState, an agent-based orchestration layer that introduces an explicit and editable story state on top of training-free text-to-image generation. StoryState represents each story as a structured object composed of a character sheet, global settings, and per-page scene constraints, and employs a small set of LLM agents to maintain this state and derive 1Prompt1Story-style prompts for generation and editing. Operating purely through prompts, StoryState is model-agnostic and compatible with diverse generation backends. System-level experiments on multi-page editing tasks show that StoryState enables localized page edits, improves cross-page consistency, and reduces unintended changes, interaction turns, and editing time compared to 1Prompt1Story, while approaching the one-shot consistency of Gemini Storybook. Code is available at https://github.com/YuZhenyuLindy/StoryState

cs.CV↗

arXiv2026

DeCorStory: Gram-Schmidt Prompt Embedding Decorrelation for Consistent Storytelling

Maintaining visual and semantic consistency across frames is a key challenge in text-to-image storytelling. Existing training-free methods, such as One-Prompt-One-Story, concatenate all prompts into a single sequence, which often induces strong embedding correlation and leads to color leakage, background blending, and identity drift. We propose DeCorStory, a training-free inference-time framework that explicitly reduces inter-frame semantic interference. DeCorStory applies Gram-Schmidt prompt embedding decorrelation to orthogonalize frame-level semantics, followed by singular value reweighting to strengthen prompt-specific information and identity-preserving cross-attention to stabilize character identity during diffusion. The method requires no model modification or fine-tuning and can be seamlessly integrated into existing diffusion pipelines. Experiments demonstrate consistent improvements in prompt-image alignment, identity consistency, and visual diversity, achieving state-of-the-art performance among training-free baselines. Code is available at: https://github.com/YuZhenyuLindy/DeCorStory

cs.CV↗

arXiv2026

PRIME: Policy-Reinforced Iterative Multi-agent Execution for Algorithmic Reasoning in Large Language Models

Large language models have demonstrated remarkable capabilities across diverse reasoning tasks, yet their performance on algorithmic reasoning remains limited. To handle this limitation, we propose PRIME (Policy-Reinforced Iterative Multi-agent Execution), a framework comprising three specialized agents, an executor for step-by-step reasoning, a verifier for constraint checking, and a coordinator for backtracking control, optimized through group relative policy optimization. For comprehensive evaluation, we introduce PRIME-Bench, the largest algorithmic reasoning benchmark to date, comprising 86 tasks across 12 categories with 51,600 instances. Tasks span sorting algorithms, graph and tree structures, automata and state machines, symbolic reasoning, and constraint-based puzzles, with execution traces reaching over one million steps. Compared to baseline approach, PRIME improves average accuracy from 26.8% to 93.8%, a 250% relative gain. The largest improvements occur on tasks requiring sustained state tracking, with Turing machine simulation improving from 9% to 92% and long division from 16% to 94%. Ablation studies identify iterative verification as the primary contributor, preventing the error propagation that causes baseline approaches to fail catastrophically. Analysis across model scales (8B-120B parameters) reveals that smaller models benefit disproportionately, achieving accuracy comparable to models 8x larger.

cs.CL↗

arXiv2026

Heat kernel-based p-energy norms on metric measure spaces

We investigate heat kernel-based and other $p$-energy norms (1<p<\infty) on bounded and unbounded metric measure spaces, in particular, on nested fractals and their blowups. With the weak-monotonicity properties for these norms, we generalise the celebrated Bourgain-Brezis-Mironescu (BBM) type characterization for p\neq2. When there admits a heat kernel satisfying the two-sided estimates, we establish the equivalence of various $p$-energy norms and weak-monotonicity properties, and show that these weak-monotonicity properties hold when p=2 (in the case of Dirichlet form). Our paper's key results concern the equivalence and verification of various weak-monotonicity properties on fractals. Consequently, many classical results on p-energy norms hold on nested fractals and their blowups, including the BBM type characterization and Gagliardo-Nirenberg inequality.

math.FA↗

arXiv2025

Adaptive Detector-Verifier Framework for Zero-Shot Polyp Detection in Open-World Settings

Polyp detectors trained on clean datasets often underperform in real-world endoscopy, where illumination changes, motion blur, and occlusions degrade image quality. Existing approaches struggle with the domain gap between controlled laboratory conditions and clinical practice, where adverse imaging conditions are prevalent. In this work, we propose AdaptiveDetector, a novel two-stage detector-verifier framework comprising a YOLOv11 detector with a vision-language model (VLM) verifier. The detector adaptively adjusts per-frame confidence thresholds under VLM guidance, while the verifier is fine-tuned with Group Relative Policy Optimization (GRPO) using an asymmetric, cost-sensitive reward function specifically designed to discourage missed detections -- a critical clinical requirement. To enable realistic assessment under challenging conditions, we construct a comprehensive synthetic testbed by systematically degrading clean datasets with adverse conditions commonly encountered in clinical practice, providing a rigorous benchmark for zero-shot evaluation. Extensive zero-shot evaluation on synthetically degraded CVC-ClinicDB and Kvasir-SEG images demonstrates that our approach improves recall by 14 to 22 percentage points over YOLO alone, while precision remains within 0.7 points below to 1.7 points above the baseline. This combination of adaptive thresholding and cost-sensitive reinforcement learning achieves clinically aligned, open-world polyp detection with substantially fewer false negatives, thereby reducing the risk of missed precancerous polyps and improving patient outcomes.

cs.CV↗

arXiv2025

Multi-Agent Medical Decision Consensus Matrix System: An Intelligent Collaborative Framework for Oncology MDT Consultations

Multidisciplinary team (MDT) consultations are the gold standard for cancer care decision-making, yet current practice lacks structured mechanisms for quantifying consensus and ensuring decision traceability. We introduce a Multi-Agent Medical Decision Consensus Matrix System that deploys seven specialized large language model agents, including an oncologist, a radiologist, a nurse, a psychologist, a patient advocate, a nutritionist and a rehabilitation therapist, to simulate realistic MDT workflows. The framework incorporates a mathematically grounded consensus matrix that uses Kendall's coefficient of concordance to objectively assess agreement. To further enhance treatment recommendation quality and consensus efficiency, the system integrates reinforcement learning methods, including Q-Learning, PPO and DQN. Evaluation across five medical benchmarks (MedQA, PubMedQA, DDXPlus, MedBullets and SymCat) shows substantial gains over existing approaches, achieving an average accuracy of 87.5% compared with 83.8% for the strongest baseline, a consensus achievement rate of 89.3% and a mean Kendall's W of 0.823. Expert reviewers rated the clinical appropriateness of system outputs at 8.9/10. The system guarantees full evidence traceability through mandatory citations of clinical guidelines and peer-reviewed literature, following GRADE principles. This work advances medical AI by providing structured consensus measurement, role-specialized multi-agent collaboration and evidence-based explainability to improve the quality and efficiency of clinical decision-making.

cs.MA↗

arXiv2025

DanceText: A Training-Free Layered Framework for Controllable Multilingual Text Transformation in Images

We present DanceText, a training-free framework for multilingual text editing in images, designed to support complex geometric transformations and achieve seamless foreground-background integration. While diffusion-based generative models have shown promise in text-guided image synthesis, they often lack controllability and fail to preserve layout consistency under non-trivial manipulations such as rotation, translation, scaling, and warping. To address these limitations, DanceText introduces a layered editing strategy that separates text from the background, allowing geometric transformations to be performed in a modular and controllable manner. A depth-aware module is further proposed to align appearance and perspective between the transformed text and the reconstructed background, enhancing photorealism and spatial consistency. Importantly, DanceText adopts a fully training-free design by integrating pretrained modules, allowing flexible deployment without task-specific fine-tuning. Extensive experiments on the AnyWord-3M benchmark demonstrate that our method achieves superior performance in visual quality, especially under large-scale and complex transformation scenarios. Code is avaible at https://github.com/YuZhenyuLindy/DanceText.git.

cs.CV↗

arXiv2025

ForgetMe: Evaluating Selective Forgetting in Generative Models

The widespread adoption of diffusion models in image generation has increased the demand for privacy-compliant unlearning. However, due to the high-dimensional nature and complex feature representations of diffusion models, achieving selective unlearning remains challenging, as existing methods struggle to remove sensitive information while preserving the consistency of non-sensitive regions. To address this, we propose an Automatic Dataset Creation Framework based on prompt-based layered editing and training-free local feature removal, constructing the ForgetMe dataset and introducing the Entangled evaluation metric. The Entangled metric quantifies unlearning effectiveness by assessing the similarity and consistency between the target and background regions and supports both paired (Entangled-D) and unpaired (Entangled-S) image data, enabling unsupervised evaluation. The ForgetMe dataset encompasses a diverse set of real and synthetic scenarios, including CUB-200-2011 (Birds), Stanford-Dogs, ImageNet, and a synthetic cat dataset. We apply LoRA fine-tuning on Stable Diffusion to achieve selective unlearning on this dataset and validate the effectiveness of both the ForgetMe dataset and the Entangled metric, establishing them as benchmarks for selective unlearning. Our work provides a scalable and adaptable solution for advancing privacy-preserving generative AI.

cs.CV↗

arXiv2025

Besov-Lipschitz norm and $p$-energy measure on scale-irregular Vicsek sets

In this paper, we establish the existence of $p$-energy norms and the corresponding $p$-energy measures for scale-irregular Vicsek sets, which may lack self-similarity. We also investigate the characterizations of $p$-energy norms in terms of Besov-Lipschitz norms, with their weak monotonicity and the corresponding Bourgain-Brezis-Mironescu convergence.

math.FA↗

arXiv2025

From Physics to Foundation Models: A Review of AI-Driven Quantitative Remote Sensing Inversion

Quantitative remote sensing inversion aims to estimate continuous surface variables-such as biomass, vegetation indices, and evapotranspiration-from satellite observations, supporting applications in ecosystem monitoring, carbon accounting, and land management. With the evolution of remote sensing systems and artificial intelligence, traditional physics-based paradigms are giving way to data-driven and foundation model (FM)-based approaches. This paper systematically reviews the methodological evolution of inversion techniques, from physical models (e.g., PROSPECT, SCOPE, DART) to machine learning methods (e.g., deep learning, multimodal fusion), and further to foundation models (e.g., SatMAE, GFM, mmEarth). We compare the modeling assumptions, application scenarios, and limitations of each paradigm, with emphasis on recent FM advances in self-supervised pretraining, multi-modal integration, and cross-task adaptation. We also highlight persistent challenges in physical interpretability, domain generalization, limited supervision, and uncertainty quantification. Finally, we envision the development of next-generation foundation models for remote sensing inversion, emphasizing unified modeling capacity, cross-domain generalization, and physical interpretability.

cs.CV↗

arXiv2025

Towards Transparent AI: A Survey on Explainable Large Language Models

Large Language Models (LLMs) have played a pivotal role in advancing Artificial Intelligence (AI). However, despite their achievements, LLMs often struggle to explain their decision-making processes, making them a 'black box' and presenting a substantial challenge to explainability. This lack of transparency poses a significant obstacle to the adoption of LLMs in high-stakes domain applications, where interpretability is particularly essential. To overcome these limitations, researchers have developed various explainable artificial intelligence (XAI) methods that provide human-interpretable explanations for LLMs. However, a systematic understanding of these methods remains limited. To address this gap, this survey provides a comprehensive review of explainability techniques by categorizing XAI methods based on the underlying transformer architectures of LLMs: encoder-only, decoder-only, and encoder-decoder models. Then these techniques are examined in terms of their evaluation for assessing explainability, and the survey further explores how these explanations are leveraged in practical applications. Finally, it discusses available resources, ongoing research challenges, and future directions, aiming to guide continued efforts toward developing transparent and responsible LLMs.

cs.CL↗

arXiv2025

A Layered Self-Supervised Knowledge Distillation Framework for Efficient Multimodal Learning on the Edge

We introduce Layered Self-Supervised Knowledge Distillation (LSSKD) framework for training compact deep learning models. Unlike traditional methods that rely on pre-trained teacher networks, our approach appends auxiliary classifiers to intermediate feature maps, generating diverse self-supervised knowledge and enabling one-to-one transfer across different network stages. Our method achieves an average improvement of 4.54\% over the state-of-the-art PS-KD method and a 1.14% gain over SSKD on CIFAR-100, with a 0.32% improvement on ImageNet compared to HASSKD. Experiments on Tiny ImageNet and CIFAR-100 under few-shot learning scenarios also achieve state-of-the-art results. These findings demonstrate the effectiveness of our approach in enhancing model generalization and performance without the need for large over-parameterized teacher networks. Importantly, at the inference stage, all auxiliary classifiers can be removed, yielding no extra computational cost. This makes our model suitable for deploying small language models on affordable low-computing devices. Owing to its lightweight design and adaptability, our framework is particularly suitable for multimodal sensing and cyber-physical environments that require efficient and responsive inference. LSSKD facilitates the development of intelligent agents capable of learning from limited sensory data under weak supervision.

cs.CV↗

arXiv2025

SatelliteFormula: Multi-Modal Symbolic Regression from Remote Sensing Imagery for Physics Discovery

We propose SatelliteFormula, a novel symbolic regression framework that derives physically interpretable expressions directly from multi-spectral remote sensing imagery. Unlike traditional empirical indices or black-box learning models, SatelliteFormula combines a Vision Transformer-based encoder for spatial-spectral feature extraction with physics-guided constraints to ensure consistency and interpretability. Existing symbolic regression methods struggle with the high-dimensional complexity of multi-spectral data; our method addresses this by integrating transformer representations into a symbolic optimizer that balances accuracy and physical plausibility. Extensive experiments on benchmark datasets and remote sensing tasks demonstrate superior performance, stability, and generalization compared to state-of-the-art baselines. SatelliteFormula enables interpretable modeling of complex environmental variables, bridging the gap between data-driven learning and physical understanding.

cs.CV↗

arXiv2025

DC4CR: When Cloud Removal Meets Diffusion Control in Remote Sensing

Cloud occlusion significantly hinders remote sensing applications by obstructing surface information and complicating analysis. To address this, we propose DC4CR (Diffusion Control for Cloud Removal), a novel multimodal diffusion-based framework for cloud removal in remote sensing imagery. Our method introduces prompt-driven control, allowing selective removal of thin and thick clouds without relying on pre-generated cloud masks, thereby enhancing preprocessing efficiency and model adaptability. Additionally, we integrate low-rank adaptation for computational efficiency, subject-driven generation for improved generalization, and grouped learning to enhance performance on small datasets. Designed as a plug-and-play module, DC4CR seamlessly integrates into existing cloud removal models, providing a scalable and robust solution. Extensive experiments on the RICE and CUHK-CR datasets demonstrate state-of-the-art performance, achieving superior cloud removal across diverse conditions. This work presents a practical and efficient approach for remote sensing image processing with broad real-world applications.

cs.CV↗