11 papers
Unlocking LLM Code Correction with Iterative Feedback Loops
Le Zhang, Suresh Kothari
Large Language Models have shown remarkable capabilities in code generation. However, most existing evaluations focus only on single-attempt accuracy and overlook the iterative ref…
Trustworthy Longitudinal Brain MRI Completion: A Deformation-Based Approach with KAN-Enhanced Diffusion Model
Tianli Tao, Ziyang Wang, Delong Yang +2
Longitudinal brain MRI is essential for lifespan study, yet high attrition rates often lead to missing data, complicating analysis. Deep generative models have been explored, but m…
Grounding Large Language Models as Generalizable Policies in Network Control
Duo Wu, Linjia Kang, Zhimin Wang +9
Designing generalizable control policies that operate reliably under changing conditions is essential for robust network services in modern digital infrastructure. Yet network cont…
A Comprehensive Survey on World Models for Embodied AI
Xinqing Li, Xin He, Le Zhang +3
Embodied AI requires agents that perceive, act, and anticipate how actions reshape future world states. World models serve as internal simulators that capture environment dynamics,…
UltraUPConvNet: A UPerNet- and ConvNeXt-Based Multi-Task Network for Ultrasound Tissue Segmentation and Disease Prediction
Zhi Chen, Le Zhang
Ultrasound imaging is widely used in clinical practice due to its cost-effectiveness, mobility, and safety. However, current AI research often treats disease prediction and tissue…
ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation
Chenchen Zhang, Yuhang Li, Can Xu +17
The generative capabilities of Large Language Models (LLMs) are rapidly expanding from static code to dynamic, interactive visual artifacts. This progress is bottlenecked by a crit…
Semantically-Aware Game Image Quality Assessment
Kai Zhu, Vignesh Edithal, Le Zhang +2
Assessing the visual quality of video game graphics presents unique challenges due to the absence of reference images and the distinct types of distortions, such as aliasing, textu…
Gameplay Highlights Generation
Vignesh Edithal, Le Zhang, Ilia Blank +1
In this work, we enable gamers to share their gaming experience on social media by automatically generating eye-catching highlight reels from their gameplay session Our automation…
Introducing Milabench: Benchmarking Accelerators for AI
Pierre Delaunay, Xavier Bouthillier, Olivier Breuleux +12
AI workloads, particularly those driven by deep learning, are introducing novel usage patterns to high-performance computing (HPC) systems that are not comprehensively captured by…
Deep Feature Surgery: Towards Accurate and Efficient Multi-Exit Networks
Cheng Gong, Yao Chen, Qiuyang Luo +5
Multi-exit network is a promising architecture for efficient model inference by sharing backbone networks and weights among multiple exits. However, the gradient conflict of the sh…
Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation
Zhengyuan Xie, Haiquan Lu, Jia-wen Xiao +3
Class incremental semantic segmentation aims to preserve old knowledge while learning new tasks, however, it is impeded by catastrophic forgetting and background shift issues. Prio…