5 papers
3D-DefectBench: A Controlled Factorial Study of Vision-Language Model Evaluation Pipelines for Fine-Grained 3D Generation Defects
Zhenyu Zhao, Nanshan Jia, Jihyeon Je +7
Automated evaluation is essential for scaling generative 3D systems, where exhaustive human review is costly and slow. However, the reliability of an automated judge depends on the…
Experimentation for Different Scheduling Policies on Queues: Mixed Differences-in-Q Estimators Based on Little's Law
Nanshan Jia, Ramesh Johari, Nian Si +1
In data centers, tasks are dispatched to various servers to evenly distribute the workload. When a data center considers implementing a new scheduling algorithm, it typically condu…
DB-3DME: From Dataset to Benchmark for Human-aligned Automatic 3D Mesh Evaluation
Nanshan Jia, Zhenyu Zhao, Sui Huang +2
Recent advances in 3D generation have led to substantial improvements in realism, controllability, and efficiency, yet the evaluation of 3D assets remains underexplored. Existing e…
Controllable Coupled Image Generation via Diffusion Models
Chenfei Yuan, Nanshan Jia, Hangqi Li +2
We provide an attention-level control method for the task of coupled image generation, where "coupled" means that multiple simultaneously generated images are expected to have the…
Improving LLM Interpretability and Performance via Guided Embedding Refinement for Sequential Recommendation
Nanshan Jia, Chenfei Yuan, Yuhang Wu +1
The fast development of Large Language Models (LLMs) offers growing opportunities to further improve sequential recommendation systems. Yet for some practitioners, integrating LLMs…