4 citations · 6 across the 13 of their papers we have counts for
14 papers
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…
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…
UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios
Haotian Luo, Huaisong Zhang, Xuelin Zhang +15
Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical…
Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
Yongxian Wei, Anke Tang, Li Shen +3
Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data. Existing methods attempt to alleviate task conf…
Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
Zixuan Hu, Yongxian Wei, Li Shen +2
Large Language Models (LLMs) such as ChatGPT demonstrate strong few-shot adaptability without requiring fine-tuning, positioning them ideal for data-limited and real-time applicati…
Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models
Yongxian Wei, Zixuan Hu, Li Shen +4
Data-Free Meta-Learning (DFML) aims to derive knowledge from a collection of pre-trained models without accessing their original data, enabling the rapid adaptation to new unseen t…
FREE: Faster and Better Data-Free Meta-Learning
Yongxian Wei, Zixuan Hu, Zhenyi Wang +3
Data-Free Meta-Learning (DFML) aims to extract knowledge from a collection of pre-trained models without requiring the original data, presenting practical benefits in contexts cons…
Task-Distributionally Robust Data-Free Meta-Learning
Zixuan Hu, Yongxian Wei, Li Shen +4
Data-Free Meta-Learning (DFML) aims to enable efficient learning of unseen few-shot tasks, by meta-learning from multiple pre-trained models without accessing their original traini…
Exploring Model Transferability through the Lens of Potential Energy
Xiaotong Li, Zixuan Hu, Yixiao Ge +2
Transfer learning has become crucial in computer vision tasks due to the vast availability of pre-trained deep learning models. However, selecting the optimal pre-trained model fro…
Learning to Learn from APIs: Black-Box Data-Free Meta-Learning
Zixuan Hu, Li Shen, Zhenyi Wang +3
Data-free meta-learning (DFML) aims to enable efficient learning of new tasks by meta-learning from a collection of pre-trained models without access to the training data. Existing…
Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning
Zixuan Hu, Li Shen, Zhenyi Wang +3
The goal of data-free meta-learning is to learn useful prior knowledge from a collection of pre-trained models without accessing their training data. However, existing works only s…
Modeling Uncertain Feature Representation for Domain Generalization
Xiaotong Li, Zixuan Hu, Jun Liu +3
Though deep neural networks have achieved impressive success on various vision tasks, obvious performance degradation still exists when models are tested in out-of-distribution sce…
mc-BEiT: Multi-choice Discretization for Image BERT Pre-training
Xiaotong Li, Yixiao Ge, Kun Yi +3
Image BERT pre-training with masked image modeling (MIM) becomes a popular practice to cope with self-supervised representation learning. A seminal work, BEiT, casts MIM as a class…
Developable B-spline surface generation from control rulings
Zixuan Hu, Pengbo Bo
An intuitive design method is proposed for generating developable ruled B-spline surfaces from a sequence of straight line segments indicating the surface shape. The first and last…