arXiv subjects

Yu Sun

Publications and source records attributed to Yu Sun.

At least 91 records · Page 5Linked to original sources

arXiv2026

Accurate Network Traffic Matrix Prediction via LEAD: a Large Language Model-Enhanced Adapter-Based Conditional Diffusion Model

Driven by the evolution toward 6G and AI-native edge intelligence, network operations increasingly require predictive and risk-aware adaptation under stringent computation and latency constraints. Network Traffic Matrix (TM), which characterizes flow volumes between nodes, is a fundamental signal for proactive traffic engineering. However, accurate TM forecasting remains challenging due to the stochastic, non-linear, and bursty nature of network dynamics. Existing discriminative models often suffer from over-smoothing and provide limited uncertainty awareness, leading to poor fidelity under extreme bursts. To address these limitations, we propose LEAD, a Large Language Model (LLM)-Enhanced Adapter-based conditional Diffusion model. First, LEAD adopts a "Traffic-to-Image" paradigm to transform traffic matrices into RGB images, enabling global dependency modeling via vision backbones. Then, we design a "Frozen LLM with Trainable Adapter" model, which efficiently captures temporal semantics with limited computational cost. Moreover, we propose a Dual-Conditioning Strategy to precisely guide a diffusion model to generate complex, dynamic network traffic matrices. Experiments on the Abilene and GEANT datasets demonstrate that LEAD outperforms all baselines. On the Abilene dataset, LEAD attains a remarkable 45.2% reduction in RMSE against the best baseline, with the error margin rising only marginally from 0.1098 at one-step to 0.1134 at 20-step predictions. Meanwhile, on the GEANT dataset, LEAD achieves a 0.0258 RMSE at 20-step prediction horizon which is 27.3% lower than the best baseline.

cs.LG↗

arXiv2026

End-to-end reconstruction of OCT optical properties and speckle-reduced structural intensity via physics-based learning

Inverse scattering in optical coherence tomography (OCT) seeks to recover both structural images and intrinsic tissue optical properties, including refractive index, scattering coefficient, and anisotropy. This inverse problem is challenging due to attenuation, speckle noise, and strong coupling among parameters. We propose a regularized end-to-end deep learning framework that jointly reconstructs optical parameter maps and speckle-reduced OCT structural intensity for layer visualization. Trained with Monte Carlo-simulated ground truth, our network incorporates a physics-based OCT forward model that generates predicted signals from the estimated parameters, providing physics-consistent supervision for parameter recovery and artifact suppression. Experiments on the synthetic corneal OCT dataset demonstrate robust optical map recovery under noise, improved resolution, and enhanced structural fidelity. This approach enables quantitative multi-parameter tissue characterization and highlights the benefit of combining physics-informed modeling with deep learning for computational OCT.

cs.CV↗

arXiv2026

Super-Resolution and Denoising of Corneal B-Scan OCT Imaging Using Diffusion Model Plug-and-Play Priors

Optical coherence tomography (OCT) is pivotal in corneal imaging for both surgical planning and diagnosis. However, high-speed acquisitions often degrade spatial resolution and increase speckle noise, posing challenges for accurate interpretation. We propose an advanced super-resolution framework leveraging diffusion model plug-and-play (PnP) priors to achieve 4x spatial resolution enhancement alongside effective denoising of OCT Bscan images. Our approach formulates reconstruction as a principled Bayesian inverse problem, combining Markov chain Monte Carlo sampling with pretrained generative priors to enforce anatomical consistency. We comprehensively validate the framework using \emph{in vivo} fisheye corneal datasets, to assess robustness and scalability under diverse clinical settings. Comparative experiments against bicubic interpolation, conventional supervised U-Net baselines, and alternative diffusion priors demonstrate that our method consistently yields more precise anatomical structures, improved delineation of corneal layers, and superior noise suppression. Quantitative results show state-of-the-art performance in peak signal-to-noise ratio, structural similarity index, and perceptual metrics. This work highlights the potential of diffusion-driven plug-and-play reconstruction to deliver high-fidelity, high-resolution OCT imaging, supporting more reliable clinical assessments and enabling advanced image-guided interventions. Our findings suggest the approach can be extended to other biomedical imaging modalities requiring robust super-resolution and denoising.

eess.IV↗

arXiv2026

Open-Vocabulary Functional 3D Human-Scene Interaction Generation

Generating 3D humans that functionally interact with 3D scenes remains an open problem with applications in embodied AI, robotics, and interactive content creation. The key challenge involves reasoning about both the semantics of functional elements in 3D scenes and the 3D human poses required to achieve functionality-aware interaction. Unfortunately, existing methods typically lack explicit reasoning over object functionality and the corresponding human-scene contact, resulting in implausible or functionally incorrect interactions. In this work, we propose FunHSI, a training-free, functionality-driven framework that enables functionally correct human-scene interactions from open-vocabulary task prompts. Given a task prompt, FunHSI performs functionality-aware contact reasoning to identify functional scene elements, reconstruct their 3D geometry, and model high-level interactions via a contact graph. We then leverage vision-language models to synthesize a human performing the task in the image and estimate proposed 3D body and hand poses. Finally, the proposed 3D body configuration is refined via stage-wise optimization to ensure physical plausibility and functional correctness. In contrast to existing methods, FunHSI not only synthesizes more plausible general 3D interactions, such as "sitting on a sofa'', while supporting fine-grained functional human-scene interactions, e.g., "increasing the room temperature''. Extensive experiments demonstrate that FunHSI consistently generates functionally correct and physically plausible human-scene interactions across diverse indoor and outdoor scenes.

cs.CV↗

arXiv2026

CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation

Large Audio Language Models (LALMs) have garnered significant research interest. Despite being built upon text-based large language models (LLMs), LALMs frequently exhibit a degradation in knowledge and reasoning capabilities. We hypothesize that this limitation stems from the failure of current training paradigms to effectively bridge the acoustic-semantic gap within the feature representation space. To address this challenge, we propose CORD, a unified alignment framework that performs online cross-modal self-distillation. Specifically, it aligns audio-conditioned reasoning with its text-conditioned counterpart within a unified model. Leveraging the text modality as an internal teacher, CORD performs multi-granularity alignment throughout the audio rollout process. At the token level, it employs on-policy reverse KL divergence with importance-aware weighting to prioritize early and semantically critical tokens. At the sequence level, CORD introduces a judge-based global reward to optimize complete reasoning trajectories via Group Relative Policy Optimization (GRPO). Empirical results across multiple benchmarks demonstrate that CORD consistently enhances audio-conditioned reasoning and substantially bridges the audio-text performance gap with only 80k synthetic training samples, validating the efficacy and data efficiency of our on-policy, multi-level cross-modal alignment approach.

cs.SD↗

arXiv2026

VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction

Recent advances in video generation have been dominated by diffusion and flow-matching models, which produce high-quality results but remain computationally intensive and difficult to scale. In this work, we introduce VideoAR, the first large-scale Visual Autoregressive (VAR) framework for video generation that combines multi-scale next-frame prediction with autoregressive modeling. VideoAR disentangles spatial and temporal dependencies by integrating intra-frame VAR modeling with causal next-frame prediction, supported by a 3D multi-scale tokenizer that efficiently encodes spatio-temporal dynamics. To improve long-term consistency, we propose Multi-scale Temporal RoPE, Cross-Frame Error Correction, and Random Frame Mask, which collectively mitigate error propagation and stabilize temporal coherence. Our multi-stage pretraining pipeline progressively aligns spatial and temporal learning across increasing resolutions and durations. Empirically, VideoAR achieves new state-of-the-art results among autoregressive models, improving FVD on UCF-101 from 99.5 to 88.6 while reducing inference steps by over 10x, and reaching a VBench score of 81.74-competitive with diffusion-based models an order of magnitude larger. These results demonstrate that VideoAR narrows the performance gap between autoregressive and diffusion paradigms, offering a scalable, efficient, and temporally consistent foundation for future video generation research.

cs.CV↗

arXiv2026

Adaptive Model-Based Reinforcement Learning for Orbit Feedback Control in NSLS-II Storage Ring

The National Synchrotron Light Source II (NSLS-II) uses highly stable electron beam to produce high-quality X-ray beams with high brightness and low-emittance synchrotron radiation. The traditional algorithm to stabilize the beam applies singular value decomposition (SVD) on the orbit response matrix to remove noise and extract actions. Supervised learning has been studied on NSLS-II storage ring stabilization and other accelerator facilities recently. Several problems, for example, machine status drifting, environment noise, and non-linear accelerator dynamics, remain unresolved in the SVD-based and supervised learning algorithms. To address these problems, we propose an adaptive training framework based on model-based reinforcement learning. This framework consists of two types of optimizations: trajectory optimization attempts to minimize the expected total reward in a differentiable environment, and online model optimization learns non-linear machine dynamics through the agent-environment interaction. Through online training, this framework tracks the internal status drifting in the electron beam ring. Simulation and real in-facility experiments on NSLS-II reveal that our method stabilizes the beam position and minimizes the alignment error, defined as the root mean square (RMS) error between adjusted beam positions and the reference position, down to ~1$μ$m.

eess.SY↗

arXiv2026

MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free

Extending the input modality of Large Language Models~(LLMs) to the audio domain is essential for achieving comprehensive multimodal perception. However, it is well-known that acoustic information is intrinsically \textit{heterogeneous}, entangling attributes such as speech, music, and environmental context. Existing research is limited to a dense, parameter-shared adapter to model these diverse patterns, which induces \textit{gradient conflict} during optimization, as parameter updates required for distinct attributes contradict each other. To address this limitation, we introduce the \textit{\textbf{MoE-Adapter}}, a sparse Mixture-of-Experts~(MoE) architecture designed to decouple acoustic information. Specifically, it employs a dynamic gating mechanism that routes audio tokens to specialized experts capturing complementary feature subspaces while retaining shared experts for global context, thereby mitigating gradient conflicts and enabling fine-grained feature learning. Comprehensive experiments show that the MoE-Adapter achieves superior performance on both audio semantic and paralinguistic tasks, consistently outperforming dense linear baselines with comparable computational costs. Furthermore, we will release the related code and models to facilitate future research.

cs.SD↗

arXiv2026

FROST-Drive: Scalable and Efficient End-to-End Driving with a Frozen Vision Encoder

End-to-end (E2E) models in autonomous driving aim to directly map sensor inputs to control commands, but their ability to generalize to novel and complex scenarios remains a key challenge. The common practice of fully fine-tuning the vision encoder on driving datasets potentially limits its generalization by causing the model to specialize too heavily in the training data. This work challenges the necessity of this training paradigm. We propose FROST-Drive, a novel E2E architecture designed to preserve and leverage the powerful generalization capabilities of a pretrained vision encoder from a Vision-Language Model (VLM). By keeping the encoder's weights frozen, our approach directly transfers the rich, generalized world knowledge from the VLM to the driving task. Our model architecture combines this frozen encoder with a transformer-based adapter for multimodal fusion and a GRU-based decoder for smooth waypoint generation. Furthermore, we introduce a custom loss function designed to directly optimize for Rater Feedback Score (RFS), a metric that prioritizes robust trajectory planning. We conduct extensive experiments on Waymo Open E2E Dataset, a large-scale datasets deliberately curated to capture the long-tail scenarios, demonstrating that our frozen-encoder approach significantly outperforms models that employ full fine-tuning. Our results provide substantial evidence that preserving the broad knowledge of a capable VLM is a more effective strategy for achieving robust, generalizable driving performance than intensive domain-specific adaptation. This offers a new pathway for developing vision-based models that can better handle the complexities of real-world application domains.

cs.CV↗

arXiv2025

End-to-End Test-Time Training for Long Context

We formulate long-context language modeling as a problem in continual learning rather than architecture design. Under this formulation, we only use a standard architecture -- a Transformer with sliding-window attention. However, our model continues learning at test time via next-token prediction on the given context, compressing the context it reads into its weights. In addition, we improve the model's initialization for learning at test time via meta-learning at training time. Overall, our method, a form of Test-Time Training (TTT), is End-to-End (E2E) both at test time (via next-token prediction) and training time (via meta-learning), in contrast to previous forms. We conduct extensive experiments with a focus on scaling properties. In particular, for 3B models trained with 164B tokens, our method (TTT-E2E) scales with context length in the same way as Transformer with full attention, while others, such as Mamba 2 and Gated DeltaNet, do not. However, similar to RNNs, TTT-E2E has constant inference latency regardless of context length, making it 2.7 times faster than full attention for 128K context. Our code is publicly available.

cs.LG↗

arXiv2025

From Visual Perception to Deep Empathy: An Automated Assessment Framework for House-Tree-Person Drawings Using Multimodal LLMs and Multi-Agent Collaboration

Background: The House-Tree-Person (HTP) drawing test, introduced by John Buck in 1948, remains a widely used projective technique in clinical psychology. However, it has long faced challenges such as heterogeneous scoring standards, reliance on examiners subjective experience, and a lack of a unified quantitative coding system. Results: Quantitative experiments showed that the mean semantic similarity between Multimodal Large Language Model (MLLM) interpretations and human expert interpretations was approximately 0.75 (standard deviation about 0.05). In structurally oriented expert data sets, this similarity rose to 0.85, indicating expert-level baseline comprehension. Qualitative analyses demonstrated that the multi-agent system, by integrating social-psychological perspectives and destigmatizing narratives, effectively corrected visual hallucinations and produced psychological reports with high ecological validity and internal coherence. Conclusions: The findings confirm the potential of multimodal large models as standardized tools for projective assessment. The proposed multi-agent framework, by dividing roles, decouples feature recognition from psychological inference and offers a new paradigm for digital mental-health services. Keywords: House-Tree-Person test; multimodal large language model; multi-agent collaboration; cosine similarity; computational psychology; artificial intelligence

cs.AI↗

arXiv2025

Learning Dependency Models for Subset Repair

Inconsistent values are commonly encountered in real-world applications, which can negatively impact data analysis and decision-making. While existing research primarily focuses on identifying the smallest removal set to resolve inconsistencies, recent studies have shown that multiple minimum removal sets may exist, making it difficult to make further decisions. While some approaches use the most frequent values as the guidance for the subset repair, this strategy has been criticized for its potential to inaccurately identify errors. To address these issues, we consider the dependencies between attribute values to determine a more appropriate subset repair. Our main contributions include (1) formalizing the optimal subset repair problem with attribute dependencies and analyzing its computational hardness; (2) computing the exact solution using integer linear programming; (3) developing an approximate algorithm with performance guarantees based on cliques and LP relaxation; and (4) designing a probabilistic approach with an approximation bound for efficiency. Experimental results on real-world datasets validate the effectiveness of our methods in both subset repair performance and downstream applications.

cs.DS↗

arXiv2025

Sync Without Guesswork: Incomplete Time Series Alignment

Multivariate time series alignment is critical for ensuring coherent analysis across variables, but missing values and timestamp inconsistencies make this task highly challenging. Existing approaches often rely on prior imputation, which can introduce errors and lead to suboptimal alignments. To address these limitations, we propose a constraint-based alignment framework for incomplete multivariate time series that avoids imputation and ensures temporal and structural consistency. We further design efficient approximation algorithms to balance accuracy and scalability. Experiments on multiple real-world datasets demonstrate that our approach achieves superior alignment quality compared to existing methods under varying missing rates. Our contributions include: (1) formally defining incomplete multiple temporal data alignment problem; (2) proposing three approximation algorithms balancing accuracy and efficiency; and (3) validating our approach on diverse real-world datasets, where it consistently outperforms existing methods in alignment accuracy and the number of aligned tuples.

cs.DB↗

arXiv2025

Distillation of Discrete Diffusion by Exact Conditional Distribution Matching

Discrete diffusion models (DDMs) are a powerful class of generative models for categorical data, but they typically require many function evaluations for a single sample, making inference expensive. Existing acceleration methods either rely on approximate simulators, such as $τ$-leaping, or on distillation schemes that train new student models and auxiliary networks with proxy objectives. We propose a simple and principled distillation alternative based on \emph{conditional distribution matching}. Our key observation is that the reverse conditional distribution of clean data given a noisy state, $p_{0\mid t}(x_0 \mid x_t)$, admits a Markov decomposition through intermediate times and can be recovered from marginal density ratios and the known forward CTMC kernel. We exploit this structure to define distillation objectives that directly match conditional distributions between a pre-trained teacher and a low-NFE student, both for one-step and few-step samplers.

cs.LG↗

arXiv2025

Zo3T: Zero-Shot 3D-Aware Trajectory-Guided Image-to-Video Generation via Test-Time Training

Trajectory-Guided image-to-video (I2V) generation aims to synthesize videos that adhere to user-specified motion instructions. Existing methods typically rely on computationally expensive fine-tuning on scarce annotated datasets. Although some zero-shot methods attempt to trajectory control in the latent space, they may yield unrealistic motion by neglecting 3D perspective and creating a misalignment between the manipulated latents and the network's noise predictions. To address these challenges, we introduce Zo3T, a novel zero-shot test-time-training framework for trajectory-guided generation with three core innovations: First, we incorporate a 3D-Aware Kinematic Projection, leveraging inferring scene depth to derive perspective-correct affine transformations for target regions. Second, we introduce Trajectory-Guided Test-Time LoRA, a mechanism that dynamically injects and optimizes ephemeral LoRA adapters into the denoising network alongside the latent state. Driven by a regional feature consistency loss, this co-adaptation effectively enforces motion constraints while allowing the pre-trained model to locally adapt its internal representations to the manipulated latent, thereby ensuring generative fidelity and on-manifold adherence. Finally, we develop Guidance Field Rectification, which refines the denoising evolutionary path by optimizing the conditional guidance field through a one-step lookahead strategy, ensuring efficient generative progression towards the target trajectory. Zo3T significantly enhances 3D realism and motion accuracy in trajectory-controlled I2V generation, demonstrating superior performance over existing training-based and zero-shot approaches.

cs.CV↗

arXiv2025

A Novel Attention-Augmented Wavelet YOLO System for Real-time Brain Vessel Segmentation on Transcranial Color-coded Doppler

The Circle of Willis (CoW), vital for ensuring consistent blood flow to the brain, is closely linked to ischemic stroke. Accurate assessment of the CoW is important for identifying individuals at risk and guiding appropriate clinical management. Among existing imaging methods, Transcranial Color-coded Doppler (TCCD) offers unique advantages due to its radiation-free nature, affordability, and accessibility. However, reliable TCCD assessments depend heavily on operator expertise for identifying anatomical landmarks and performing accurate angle correction, which limits its widespread adoption. To address this challenge, we propose an AI-powered, real-time CoW auto-segmentation system capable of efficiently capturing cerebral arteries. No prior studies have explored AI-driven cerebrovascular segmentation using TCCD. In this work, we introduce a novel Attention-Augmented Wavelet YOLO (AAW-YOLO) network tailored for TCCD data, designed to provide real-time guidance for brain vessel segmentation in the CoW. We prospectively collected TCCD data comprising 738 annotated frames and 3,419 labeled artery instances to establish a high-quality dataset for model training and evaluation. The proposed AAW-YOLO demonstrated strong performance in segmenting both ipsilateral and contralateral CoW vessels, achieving an average Dice score of 0.901, IoU of 0.823, precision of 0.882, recall of 0.926, and mAP of 0.953, with a per-frame inference speed of 14.199 ms. This system offers a practical solution to reduce reliance on operator experience in TCCD-based cerebrovascular screening, with potential applications in routine clinical workflows and resource-constrained settings. Future research will explore bilateral modeling and larger-scale validation.

eess.IV↗

arXiv2025

V-ITI: Mitigating Hallucinations in Multimodal Large Language Models via Visual Inference-Time Intervention

Multimodal Large Language Models (MLLMs) excel in numerous vision-language tasks yet suffer from hallucinations, producing content inconsistent with input visuals, that undermine reliability in precision-sensitive domains. This issue stems from a fundamental problem of visual neglect, where models fail to adequately prioritize input images. Existing methods typically alleviate hallucinations by intervening in the attention score or output logits, focusing on "how to intervene" but overlooking the prerequisite "when to intervene", which leads to the "over-intervention" problem and subsequently introduces new hallucinations and unnecessary computational overhead. To address this gap, we first investigate the mechanism of visual neglect and reveal it can be accurately detected via head-level activation patterns in MLLMs. We thus propose V-ITI, a lightweight visual inference-time intervention framework integrating a Visual Neglect Detector that identifies visual neglect via head-level discriminative probes and a Visual Recall Intervenor that modulates activations with prestored visual activation information only when the visual neglect is detected. Extensive experiments across eight benchmarks and different MLLM families demonstrate that V-ITI consistently mitigates vision-related hallucinations while preserving general task performance.

cs.CV↗

arXiv2025

Toward generic control for soft robotic systems

Soft robotics has advanced rapidly, yet its control methods remain fragmented: different morphologies and actuation schemes still require task-specific controllers, hindering theoretical integration and large-scale deployment. A generic control framework is therefore essential, and a key obstacle lies in the persistent use of rigid-body control logic, which relies on precise models and strict low-level execution. Such a paradigm is effective for rigid robots but fails for soft robots, where the ability to tolerate and exploit approximate action representations, i.e., control compliance, is the basis of robustness and adaptability rather than a disturbance to be eliminated. Control should thus shift from suppressing compliance to explicitly exploiting it. Human motor control exemplifies this principle: instead of computing exact dynamics or issuing detailed muscle-level commands, it expresses intention through high-level movement tendencies, while reflexes and biomechanical mechanisms autonomously resolve local details. This architecture enables robustness, flexibility, and cross-task generalization. Motivated by this insight, we propose a generic soft-robot control framework grounded in control compliance and validate it across robots with diverse morphologies and actuation mechanisms. The results demonstrate stable, safe, and cross-platform transferable behavior, indicating that embracing control compliance, rather than resisting it, may provide a widely applicable foundation for unified soft-robot control.

cs.RO↗