collaborators

6 papers

cs.LG2026

PACT: Preserving Anchored Cores in Task-vectors for Model Merging

Ningyuan Shi, Zhipeng Zhou, Hao Wang +2

Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model. Most exi…

cs.AI2026

MOSAIC: Modality-Specific Adaptation for Incremental Continual Learning in Parkinson's Disease Gait Assessment

Minlin Zeng, Zhipeng Zhou, Yang Qiu +2

Gait-based Parkinson's disease assessment increasingly relies on heterogeneous sensors, but clinical systems rarely collect all modalities simultaneously. New sensors may arrive th…

cs.CV2025

PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction

Ziqiao Meng, Qichao Wang, Zhiyang Dou +4

Autoregressive point cloud generation has long lagged behind diffusion-based approaches in quality. The performance gap stems from the fact that autoregressive models impose an art…

cs.CV2025

PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction

Ziqiao Meng, Qichao Wang, Zhiyang Dou +4

Autoregressive point cloud generation has long lagged behind diffusion-based approaches in quality. The performance gap stems from the fact that autoregressive models impose an art…

cs.LG2025

Injecting Imbalance Sensitivity for Multi-Task Learning

Zhipeng Zhou, Liu Liu, Peilin Zhao +1

Multi-task learning (MTL) has emerged as a promising approach for deploying deep learning models in real-life applications. Recent studies have proposed optimization-based learning…

cs.LG2025

Continual Optimization with Symmetry Teleportation for Multi-Task Learning

Zhipeng Zhou, Ziqiao Meng, Pengcheng Wu +2

Multi-task learning (MTL) is a widely explored paradigm that enables the simultaneous learning of multiple tasks using a single model. Despite numerous solutions, the key issues of…