collaborators

9 papers

cs.CV2025

VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction

Sinan Du, Jiahao Guo, Bo Li +8

Unifying multimodal understanding, generation and reconstruction representation in a single tokenizer remains a key challenge in building unified models. Previous research predomin…

cs.CV2025

Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications

Zixuan Hu, Yongxian Wei, Li Shen +4

Model inversion, which aims to reconstruct the original training data from pre-trained discriminative models, is especially useful when the original training data is unavailable du…

cs.LG2025

Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler

Zixuan Hu, Li Shen, Zhenyi Wang +2

Harmful fine-tuning poses critical safety risks to fine-tuning-as-a-service for large language models. Existing defense strategies preemptively build robustness via attack simulati…

cs.CL2025

Mixture of Neuron Experts

Runxi Cheng, Yuchen Guan, Yucheng Ding +6

In this work, we first explore whether the parameters activated by the MoE layer remain highly sparse at inference. We perform a sparsification study on several representative MoE…

cs.CL2025

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation

Xinrui Chen, Hongxing Zhang, Fanyi Zeng +5

Layer pruning has emerged as a promising technique for compressing large language models (LLMs) while achieving acceleration proportional to the pruning ratio. In this work, we ide…

cs.LG2025

Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors

Runxi Cheng, Feng Xiong, Yongxian Wei +2

Model merging seeks to integrate task-specific expert models into a unified architecture while preserving multi-task generalization capabilities, yet parameter interference between…