papers

Publications (9)

cs.AR2025

E2ATST: A Temporal-Spatial Optimized Energy-Efficient Architecture for Training Spiking Transformer

Yunhao Ma, Yanyu Lin, Mingjing Li +9

(1) Pengcheng Laboratory, (2) Southern University of Science and Technology, (3) Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, (4) University of Chinese…

cs.AI2026

GameUIAgent: An LLM-Powered Framework for Automated Game UI Design with Structured Intermediate Representation

Wei Zeng, Fengwei An, Zhen Liu +1

Game UI design requires consistent visual assets across rarity tiers yet remains a predominantly manual process. We present GameUIAgent, an LLM-powered agentic framework that trans…

cs.AI2026

Scalable Generative Game Engine: Breaking the Resolution Wall via Hardware-Algorithm Co-Design

Wei Zeng, Xuchen Li, Ruili Feng +3

Real-time generative game engines represent a paradigm shift in interactive simulation, promising to replace traditional graphics pipelines with neural world models. However, exist…

cs.CV2024

Gait Patterns as Biomarkers: A Video-Based Approach for Classifying Scoliosis

Zirui Zhou, Junhao Liang, Zizhao Peng +3

Scoliosis presents significant diagnostic challenges, particularly in adolescents, where early detection is crucial for effective treatment. Traditional diagnostic and follow-up me…

cs.CV2025

Pose as Clinical Prior: Learning Dual Representations for Scoliosis Screening

Zirui Zhou, Zizhao Peng, Dongyang Jin +3

Recent AI-based scoliosis screening methods primarily rely on large-scale silhouette datasets, often neglecting clinically relevant postural asymmetries-key indicators in tradition…

cs.LG2024

Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers

Pingcheng Dong, Yonghao Tan, Dong Zhang +11

Non-linear functions are prevalent in Transformers and their lightweight variants, incurring substantial and frequently underestimated hardware costs. Previous state-of-the-art wor…

cs.AR2025

Energy-Oriented Computing Architecture Simulator for SNN Training

Yunhao Ma, Wanyi Jia, Yanyu Lin +4

With the growing demand for intelligent computing, neuromorphic computing, a paradigm that mimics the structure and functionality of the human brain, offers a promising approach to…

cs.LG2024

BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation

Peng Xu, Wenqi Shao, Mengzhao Chen +6

Large language models (LLMs) have demonstrated outstanding performance in various tasks, such as text summarization, text question-answering, and etc. While their performance is im…

cs.LG2026

The limits of bio-molecular modeling with large language models : a cross-scale evaluation

Yaxin Xu, Yue Zhou, Tianyu Zhao +2

The modeling of bio-molecular system across molecular scales remains a central challenge in scientific research. Large language models (LLMs) are increasingly applied to bio-molecu…