collaborators

5 papers

cs.LG2026

Stagnant Neuron: Towards Understanding the Plasticity Loss in Multi-Agent Reinforcement Learning Value Factorization Methods

Zhengzhu Liu, Zeming Gao, Haoyuan Qin +7

Multi-Agent Reinforcement Learning (MARL) value factorization methods can suffer from a loss of plasticity, gradually failing to adapt when transferring to new task instances. We t…

cs.CV2026

Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V

Junhao Wu, Dezhong Yao, Hai Jin

W4A4 quantization of large video diffusion Transformers offers substantial memory savings but is hindered by two main challenges: sparse large-magnitude activation outliers, and st…

cs.CV2026

FlashCap: Millisecond-Accurate Human Motion Capture via Flashing LEDs and Event-Based Vision

Zekai Wu, Shuqi Fan, Mengyin Liu +10

Precise motion timing (PMT) is crucial for swift motion analysis. A millisecond difference may determine victory or defeat in sports competitions. Despite substantial progress in h…

cs.CV2025

HieroAction: Hierarchically Guided VLM for Fine-Grained Action Analysis

Junhao Wu, Xiuer Gu, Zhiying Li +6

Evaluating human actions with clear and detailed feedback is important in areas such as sports, healthcare, and robotics, where decisions rely not only on final outcomes but also o…

cs.CV2025

Undress to Redress: A Training-Free Framework for Virtual Try-On

Zhiying Li, Junhao Wu, Yeying Jin +9

Virtual try-on (VTON) is a crucial task for enhancing user experience in online shopping by generating realistic garment previews on personal photos. Although existing methods have…