Searcharxiv⌕ Search

arXiv subjects

Yuke Wang

Publications and source records attributed to Yuke Wang.

At least 19 recordsLinked to original sources
arXiv2026

Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models

The safety of large vision-language models is increasingly stress-tested by multimodal jailbreaks, yet existing attacks remain largely static at the meta level: template-based attacks freeze the image-text layout, while iterative attacks adapt only the image-text content with fixed attack strategies and frozen attacker parameters. We propose Meta-Adaptive Multimodal Jailbreaking (MAMJ), which instead optimizes the attacker itself along two axes: an attack strategy prompt (ASP) governing attack iteration and attacker model weights determining attack effectiveness. Across groups of multimodal attack trajectories, an LLM-based critique first refines the ASP, after which group-aggregated attack success rate (ASR) rewards update those weights. On MM-SafetyBench, MAMJ achieves 81.0%, 78.9%, and 82.3% ASR against GPT-4o, Gemini-3-Pro-Preview, and Seed 2.0, respectively, outperforming the strongest sample-level baseline by up to 24.1 percentage points. The learned attacker, comprising the optimized ASP and attacker weights, also transfers without retraining to unseen victims and remains effective under representative defenses. These results reveal a systemic vulnerability of frontier VLMs to meta-adaptive jailbreaks and motivate defenses against meta-level adversaries. Code is available at https://github.com/Alibaba-VELLDEPTH/MetaJailbreak-VLM.

cs.CR↗
arXiv2026

Synthetic Wastewater Epidemiology Data Generation using Patterns-of-Life Simulation

Wastewater contains rich biological signals that can be used to monitor population health, track infectious diseases, and detect emerging outbreaks. Pathogens and other biomarkers in sewage provide a unique, noninvasive view of disease prevalence at the community level. However, extracting these signals requires extensive field sampling, laboratory analysis, and expert interpretation. Consequently, wastewater-based epidemiology (WBE) datasets are scarce, geographically fragmented, and rarely released as open data. Even when available, existing datasets typically cover short time periods and limited geographic regions, restricting their usefulness for method development, benchmarking, and large-scale modeling. To address this gap, we present an application of an existing patterns-of-life simulation framework for generating synthetic infectious disease and wastewater pathogen datasets for wastewater-based epidemiology. Our approach extends a patterns-of-life simulation framework by using it as a model of human mobility and behavior while incorporating disease transmission and pathogen shedding dynamics. The resulting framework generates high-resolution spatial and temporal datasets capturing infection dynamics, mobility behavior, and wastewater-associated pathogen signals. We release a fully simulated dataset containing check-in records, social network links, infection states, pathogen loads, and ground-truth disease transmission information. These data support controlled experimentation for outbreak detection, source localization, resource allocation, surveillance strategy design, mobility-aware wastewater analysis, and targeted public health interventions. We provide datasets for Fulton County and demonstrate that the framework generalizes to other regions by generating data for any city with available OpenStreetMap information.

q-bio.PE↗
arXiv2026

PLoRA: An NDP-Enhanced Pooled-Memory System for Cost-Efficient Multi-LoRA Serving

Multi-LoRA serving is how one base model becomes thousands of specialized variants, one adapter per user, task, or agent, and the deployments can hold 1000-plus adapters. Serving them is hard because the workload inverts what GPUs provide: terabytes of memory against only tens of TFLOPS, and because every published system stages its adapters from CPU DRAM over PCIe, where each access pays a kernel stop and a host-run copy and capacity ends at the motherboard's DIMM slots. Meanwhile, memory-semantic fabrics such as CXL and NVLink are converging on pooled memory that an accelerator addresses with its own loads and stores, and near-data processing (NDP) can place compute beside the pooled data. How to serve multi-LoRA workloads on such hardware remains unexplored. This paper introduces PLoRA, an NDP-enhanced pooled-memory system for cost-efficient multi-LoRA serving. PLoRA keeps adapters and KV cache in the pool and returns only reduced results over the link, through a read-compute interface the GPU drives with its own loads and stores. Above this architecture, a GPU memory management system picks among four LoRA and two attention execution strategies for each adapter and caches the most performance-critical bytes in GPU memory, guided by a link-parameterized cost model. On one H100 serving 1000 adapters, PLoRA attains the lowest decode latency on every model and workload we measure, averaging 6.6x below a real-machine S-LoRA at under 3.4% added device area. The link itself stops mattering: throughput saturates at 32 GB/s on short contexts, a quarter of CXL 3.1, and the verdict survives scale: per-GPU demand falls from 7B to a modeled 1.2T deployment once adapter traffic shards with the tensor parallelism. The design runs unchanged from CXL-class to NVLink-class fabrics, and surplus bandwidth buys pooled capacity rather than speed.

cs.AR↗
arXiv2026

Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication

3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated regions, causing global inconsistency, or rely on global Gaussian-level exchanges, which lead to substantial growth in inter-GPU communication and quickly dominate iteration time. We propose Splaxel, a communication-efficient distributed 3DGS training framework based on pixel-level local rendering and global composition. Instead of synchronizing Gaussians, each GPU renders its local subset and exchanges only partial pixel values, maintaining mathematical consistency while keeping communication cost stable as the scene size increases. Splaxel further reduces pixel-level redundancy through geometric and transmittance visibility prediction and improves GPU utilization via conflict-free camera-view consolidation. Evaluated on large-scale datasets with up to 120M Gaussians, Splaxel achieves up to 7.6$\times$ speedup over the state-of-the-art distributed 3DGS framework while preserving high reconstruction quality.

cs.DC↗
arXiv2026

AoiZora: Topology-Aware Auto-Parallel Optimization for Inference of Diffusion Transformers

Video diffusion has quickly grown into a key generative serving workload, yet producing each clip demands many denoising iterations over large spatio-temporal latents, which puts low-latency inference out of reach on a single device. A denoising step is therefore typically distributed across multiple accelerators, and TPU sub-slices have become an attractive and practical fabric for doing so. Current auto-parallel systems, however, search almost exclusively over logical device meshes and disregard how a chosen sharding is actually laid out on the physical TPU interconnect -- an oversight that leaves large, topology-dependent performance on the table. We address this gap with AoiZora, a compiler-mediated topology planner built for low-latency video diffusion inference on TPU sub-slices. Its guiding principle is to reconnect logical sharding with physical placement by drawing on different points in the compilation flow: AoiZora first eliminates weak sharding candidates from inexpensive pre-compilation IRs, then compiles only the ones that survive and orders their physical placements using compiled HLO together with a topology-aware communication model. The winning plan is realized along the ordinary compiler path, leaving model code, compiler lowering, collective kernels, and network routing entirely intact. On TPU v5e sub-slices, AoiZora reduces Wan 2.1 one-step denoising latency by as much as 1.42x relative to existing solutions.

cs.DC↗
arXiv2026

FlashCP: Load-Balanced Communication-Efficient Context Parallelism for LLM Training

Context parallelism (CP) is essential for training large-scale, long-context language models, as it partitions sequences to reduce memory overhead. However, existing CP methods suffer from workload imbalance, inefficient kernels, and redundant communication due to static sequence sharding and key-value (KV) tensor communication. We present FlashCP, a load-balanced and communication-efficient framework for CP training. FlashCP introduces a sharding-aware communication mechanism to eliminate redundant KV communication and proposes a novel Whole-Doc sharding strategy that maximizes communication savings while maintaining balanced workloads. To efficiently combine Whole-Doc and Per-Doc sharding, FlashCP further designs a heuristic algorithm to search for near-optimal sharding plans. Extensive experiments show that FlashCP achieves up to 1.63x speedup over state-of-the-art CP frameworks across diverse datasets.

cs.DC↗
arXiv2026

From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting

Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover. However, existing LLM-based news-forecasting pipelines face two practical limitations: relevant news articles often exceed the model's context window, and iterative retrieval of supplementary news is typically unguided, leading to redundant updates and slow convergence. We address these issues with a novel framework that combines importance-aware news compression and process-level retrieval supervision. First, we train an importance reward model that estimates the forecasting utility of each article and uses this signal to allocate compression budgets during sequential pairwise fusion, preserving informative content within a fixed context limit. Second, we introduce a process reward model (PRM) that ranks multiple supplementary-news candidates conditioned on the current error profile and the history of previously selected articles, replacing one-shot blind retrieval with quality-controlled selection. Both components are trained offline using historical data with ground truth; inference uses the frozen filtering logic and compression modules without any reflection loop. Experiments on finance, energy, traffic, and bitcoin forecasting benchmarks show that our method improves prediction accuracy over strong baselines, significantly reduces the number of refinement iterations compared to the iterative baseline, and remains effective when relevant articles span thousands of tokens.

cs.AI↗
arXiv2026

Characterization-Guided GPU Fault Resilience in NVIDIA MPS

NVIDIA Multi-Process Service (MPS) enables fine-grained GPU sharing by allowing multiple processes to execute concurrently on the same GPU, making it an important mechanism for improving GPU utilization. However, MPS has weak fault resilience: a fault in one process can terminate all co-running processes, limiting its adoption in resilience-critical settings such as multi-tenant GPU clusters. In this work, we design fault-resilient MPS to solve this problem. Our design is guided by insights from a systematic characterization of GPU faults and a deep analysis of their end-to-end processing pipeline. Based on these insights, we design two complementary mechanisms. A fault isolation mechanism for the dominant memory-related faults that can be fully isolated by software intervention in the open GPU driver kernel module. For other faults whose process is within proprietary software, we design a practical mechanism -- fast recovery using virtual memory based GPU-resident state sharing. Our evaluation on different GPUs and workloads shows that these mechanisms can handle corresponding faults effectively with minimal overhead.

cs.DC↗
arXiv2026

ALTO: Adaptive LoRA Tuning and Orchestration for Heterogeneous LoRA Training Workloads

Low-Rank Adaptation (LoRA) is now the dominant method for parameter-efficient fine-tuning of large language models, but achieving a high-quality adapter often requires systematic hyperparameter tuning because LoRA performance is highly sensitive to configuration choices. In practice, this leads to many concurrent LoRA jobs, often spanning heterogeneous tasks in multi-tenant environments. Existing systems largely handle these jobs independently, which both wastes computation on weak candidates and leaves GPUs underutilized. We present ALTO (Adaptive LoRA Tuning and Orchestration), a co-designed training system that accelerates LoRA hyperparameter tuning while enabling efficient cluster sharing across heterogeneous tasks. The central insight behind ALTO is that when multiple tuning jobs run concurrently over a shared frozen backbone, they expose optimization opportunities that single-job designs cannot exploit. Building on this, ALTO monitors loss trajectories to terminate unpromising configurations early, uses fused grouped GEMM together with a new rank-local adapter parallelism to co-locate surviving adapters and reclaim freed GPU capacity, and combines intra-task and inter-task scheduling to improve multi-task placement by leveraging the predictable duration of LoRA jobs. Extensive evaluation shows that ALTO achieves up to $13.8\times$ speedup over state-of-the-art without sacrificing adapter quality.

cs.LG↗
arXiv2026

GENSERVE: Efficient Co-Serving of Heterogeneous Diffusion Model Workloads

Diffusion models have emerged as the prevailing approach for text-to-image (T2I) and text-to-video (T2V) generation, yet production platforms must increasingly serve both modalities on shared GPU clusters while meeting stringent latency SLOs. Co-serving such heterogeneous workloads is challenging: T2I and T2V requests exhibit vastly different compute demands, parallelism characteristics, and latency requirements, leading to significant SLO violations in existing serving systems. We present GENSERVE, a co-serving system that leverages the inherent predictability of the diffusion process to optimize serving efficiency. A central insight is that diffusion inference proceeds in discrete, predictable steps and is naturally preemptible at step boundaries, opening a new design space for heterogeneity-aware resource management. GENSERVE introduces step-level resource adaptation through three coordinated mechanisms: intelligent video preemption, elastic sequence parallelism with dynamic batching, and an SLO-aware scheduler that jointly optimizes resource allocation across all concurrent requests. Experimental results show that GENSERVE improves the SLO attainment rate by up to 44% over the strongest baseline across diverse configurations.

cs.DC↗
arXiv2026

HII-DPO: Eliminate Hallucination via Accurate Hallucination-Inducing Counterfactual Images

Large Vision-Language Models (VLMs) have achieved remarkable success across diverse multimodal tasks but remain vulnerable to hallucinations rooted in inherent language bias. Despite recent progress, existing hallucination mitigation methods often overlook the underlying hallucination patterns driven by language bias. In this work, we design a novel pipeline to accurately synthesize Hallucination-Inducing Images (HIIs). Using synthesized HIIs, we reveal a consistent scene-conditioned hallucination pattern: models tend to mention objects that are highly typical of the scene even when visual evidence is removed. To quantify the susceptibility of VLMs to this hallucination pattern, we establish the Masked-Object-Hallucination (MOH) benchmark to rigorously evaluate existing state-of-the-art alignment frameworks. Finally, we leverage HIIs to construct high-quality preference datasets for fine-grained alignment. Experimental results demonstrate that our approach effectively mitigates hallucinations while preserving general model capabilities. Specifically, our method achieves up to a 38% improvement over the current state-of-the-art on standard hallucination benchmarks.

cs.CV↗
arXiv2026

iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems

Scheduling precedence-constrained tasks under shared renewable resources is critical to modern computing platforms. It is often modeled as the Resource Investment Problem (RIP) by minimizing the cost of provisioned renewable resources under precedence and timing constraints. Unfortunately, exact mixed-integer programming and constraint programming become impractically slow on large RIP instances, and dynamic updates require schedule revisions under tight latency budgets. To address this, we present iScheduler, a reinforcement-learning-driven iterative scheduling framework for large RIP. Specifically, it formulates RIP solving as a Markov decision process over decomposed subproblems and constructs schedules through sequential process selection. By doing this, the framework accelerates optimization and supports reconfiguration by reusing unchanged process schedules and rescheduling only affected processes. To evaluate this framework, we release L-RIPLIB, an industrial-scale benchmark derived from cloud-platform workloads with 1,000 instances of 2,500-10,000 tasks. Our experiments show that iScheduler attains competitive resource costs while reducing time to feasibility by up to 43$\times$ against leading solver-backed baselines.

cs.DC↗
arXiv2026

SDiT: Semantic Region-Adaptive for Diffusion Transformers

Diffusion Transformers (DiTs) achieve state-of-the-art performance in text-to-image synthesis but remain computationally expensive due to the iterative nature of denoising and the quadratic cost of global attention. In this work, we observe that denoising dynamics are spatially non-uniform-background regions converge rapidly while edges and textured areas evolve much more actively. Building on this insight, we propose SDiT, a Semantic Region-Adaptive Diffusion Transformer that allocates computation according to regional complexity. SDiT introduces a training-free framework combining (1) semantic-aware clustering via fast Quickshift-based segmentation, (2) complexity-driven regional scheduling to selectively update informative areas, and (3) boundary-aware refinement to maintain spatial coherence. Without any model retraining or architectural modification, SDiT achieves up to 3.0x acceleration while preserving nearly identical perceptual and semantic quality to full-attention inference.

cs.CV↗
arXiv2026

Where Do We Poop? City-Wide Simulation of Defecation Behavior for Wastewater-Based Epidemiology

Wastewater surveillance, which regularly measures pathogen biomarkers in wastewater samples, is a valuable tool for monitoring infectious diseases circulating in communities. Yet, most wastewater-based epidemiology methods that use wastewater surveillance results to infer disease trends implicitly assume that individuals excrete only at their residential locations and that the populations contributing to wastewater samples are static. These simplifying assumptions ignore daily mobility, social interactions, and heterogeneous toilet-use patterns, which can bias the interpretation of wastewater results, especially at upstream sampling locations such as neighborhoods, institutions, or buildings. Here, we introduce an agent-based geospatial simulation framework. Building on an established Patterns of Life model, we simulate daily human activities within a realistic urban environment and extend the framework with a physiologically motivated defecation cycle and toilet-use patterns. We couple this behavioral model with an infectious disease model to simulate transmission through spatial and social interactions. When an infected agent defecates, a pathogen-shedding model determines the amount of pathogen released in the feces. By integrating population mobility, disease transmission, toilet-use behavior, and pathogen shedding, the framework can simulate the spatiotemporal dynamics of wastewater pathogen loads. Using a case study of 10,000 simulated agents in Fulton County, Georgia, we examine how varying infection rates alter epidemic trajectories, wastewater pathogen loads, and the spatial distribution of pathogen shedding over time. Our results show that mobility and toilet use can substantially decouple residential disease prevalence from wastewater pathogen loads and demonstrate how behaviorally grounded simulations can support interpretation, scenario analysis, and wastewater surveillance

physics.soc-ph↗
arXiv2025

LeJOT: An Intelligent Job Cost Orchestration Solution for Databricks Platform

With the rapid advancements in big data technologies, the Databricks platform has become a cornerstone for enterprises and research institutions, offering high computational efficiency and a robust ecosystem. However, managing the escalating operational costs associated with job execution remains a critical challenge. Existing solutions rely on static configurations or reactive adjustments, which fail to adapt to the dynamic nature of workloads. To address this, we introduce LeJOT, an intelligent job cost orchestration framework that leverages machine learning for execution time prediction and a solver-based optimization model for real-time resource allocation. Unlike conventional scheduling techniques, LeJOT proactively predicts workload demands, dynamically allocates computing resources, and minimizes costs while ensuring performance requirements are met. Experimental results on real-world Databricks workloads demonstrate that LeJOT achieves an average 20% reduction in cloud computing costs within a minute-level scheduling timeframe, outperforming traditional static allocation strategies. Our approach provides a scalable and adaptive solution for cost-efficient job scheduling in Data Lakehouse environments.

cs.LG↗
arXiv2025

Data-Free Continual Learning of Server Models in Model-Heterogeneous Cloud-Device Collaboration

The rise of cloud-device collaborative computing has enabled intelligent services to be delivered across distributed edge devices while leveraging centralized cloud resources. In this paradigm, federated learning (FL) has become a key enabler for privacy-preserving model training without transferring raw data from edge devices to the cloud. However, with the continuous emergence of new data and increasing model diversity, traditional federated learning faces significant challenges, including inherent issues of data heterogeneity, model heterogeneity and catastrophic forgetting, along with new challenge of knowledge misalignment. In this study, we introduce FedDCL, a novel framework designed to enable data-free continual learning of the server model in a model-heterogeneous federated setting. We leverage pre-trained diffusion models to extract lightweight class-specific prototypes, which confer a threefold data-free advantage, enabling: (1) generation of synthetic data for the current task to augment training and counteract non-IID data distributions; (2) exemplar-free generative replay for retaining knowledge from previous tasks; and (3) data-free dynamic knowledge transfer from heterogeneous devices to the cloud server.Experimental results on various datasets demonstrate the effectiveness of FedDCL, showcasing its potential to enhance the generalizability and practical applicability of federated cloud-device collaboration in dynamic settings.

cs.LG↗
arXiv2025

An Efficient and Adaptive Watermark Detection System with Tile-based Error Correction

Efficient and reliable detection of generated images is critical for the responsible deployment of generative models. Existing approaches primarily focus on improving detection accuracy and robustness under various image transformations and adversarial manipulations, yet they largely overlook the efficiency challenges of watermark detection across large-scale image collections. To address this gap, we propose QRMark, an efficient and adaptive end-to-end method for detecting embedded image watermarks. The core idea of QRMark is to combine QR Code-inspired error correction with tailored tiling techniques to improve detection efficiency while preserving accuracy and robustness. At the algorithmic level, QRMark employs a Reed-Solomon error correction mechanism to mitigate the accuracy degradation introduced by tiling. At the system level, QRMark implements a resource-aware multi-channel horizontal fusion policy that adaptively assigns more streams to GPU-intensive stages of the detection pipeline. It further employs a tile-based workload interleaving strategy to overlap data-loading overhead with computation and schedules kernels across stages to maximize efficiency. End-to-end evaluations show that QRMark achieves an average 2.43x inference speedup over the sequential baseline.

cs.DC↗
arXiv2025

SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling

Diffusion models have recently achieved remarkable success in generative tasks (e.g., image and video generation), and the demand for high-quality content (e.g., 2K/4K videos) is rapidly increasing across various domains. However, generating ultra-high-resolution videos on existing standard-resolution (e.g., 720p) platforms remains challenging due to the excessive re-training requirements and prohibitively high computational and memory costs. To this end, we introduce SUPERGEN, an efficient tile-based framework for ultra-high-resolution video generation. SUPERGEN features a novel training-free algorithmic innovation with tiling to successfully support a wide range of resolutions without additional training efforts while significantly reducing both memory footprint and computational complexity. Moreover, SUPERGEN incorporates a tile-tailored, adaptive, region-aware caching strategy that accelerates video generation by exploiting redundancy across denoising steps and spatial regions. SUPERGEN also integrates cache-guided, communication-minimized tile parallelism for enhanced throughput and minimized latency. Evaluations show that SUPERGEN maximizes performance gains while achieving high output quality across various benchmarks.

cs.LG↗