Zixuan Hu

papers

105

total citations

papers (11)

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models

ICML 2024arXiv

citations

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

ICML 2024arXiv

citations

LEAD: Exploring Logit Space Evolution for Model Selection

CVPR 2024arXiv

citations

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

NEURIPS 2025arXiv

citations

LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents

NEURIPS 2025arXiv

citations

LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs

CVPR 2025

citations

Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts

ICCV 2025arXiv

citations

Zixuan Hu

papers (11)

Mc-BEiT: Multi-Choice Discretization for Image BERT Pre-training

Exploring Model Transferability through the Lens of Potential Energy

Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning

FREE: Faster and Better Data-Free Meta-Learning

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models

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

LEAD: Exploring Logit Space Evolution for Model Selection

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

LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents

LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs

Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts

papers (11)

Mc-BEiT: Multi-Choice Discretization for Image BERT Pre-training

Exploring Model Transferability through the Lens of Potential Energy

Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning

FREE: Faster and Better Data-Free Meta-Learning

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models

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

LEAD: Exploring Logit Space Evolution for Model Selection

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

LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents

LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs

Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts