collaborators

6 papers

cs.CV2026

When Few Steps Are Enough: Training-Free Acceleration of Identity-Preserved Generation

Dongqi Zheng

Identity-preserved image generation is typically built on many-step diffusion backbones, making personalized generation expensive at deployment time. We show that this cost is ofte…

cs.CV2025

ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation

Lingfeng Wang, Hualing Lin, Senda Chen +5

While humans effortlessly draw visual objects and shapes by adaptively allocating attention based on their complexity, existing multimodal large language models (MLLMs) remain cons…

cs.LG2025

CAFL-L: Constraint-Aware Federated Learning with Lagrangian Dual Optimization for On-Device Language Models

Dongqi Zheng, Wenjin Fu

We introduce Constraint-Aware Federated Learning with Lagrangian Dual Optimization (CAFL-L), a principled extension of FedAvg that explicitly incorporates device-level resource con…

cs.AI2025

ARS: Adaptive Reasoning Suppression for Efficient Large Reasoning Language Models

Dongqi Zheng

Large Reasoning Language Models (LRLMs or LRMs) demonstrate remarkable capabilities in complex reasoning tasks, but suffer from significant computational inefficiencies due to over…

cs.CV2025

A Real-Time On-Device Defect Detection Framework for Laser Power-Meter Sensors via Unsupervised Learning

Dongqi Zheng, Wenjin Fu, Guangzong Chen

We present an automated vision-based system for defect detection and classification of laser power meter sensor coatings. Our approach addresses the critical challenge of identifyi…

cs.DC2025

Diffusion Models on the Edge: Challenges, Optimizations, and Applications

Dongqi Zheng

Diffusion models have shown remarkable capabilities in generating high-fidelity data across modalities such as images, audio, and video. However, their computational intensity make…