Fanhu Zeng

AuroraZengfh's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 3 papers 4 days ago

Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection

Paper • 2409.04796 • Published Sep 7, 2024

DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning

Paper • 2411.19154 • Published Nov 28, 2024

EventVAD: Training-Free Event-Aware Video Anomaly Detection

Paper • 2504.13092 • Published Apr 17

authored 6 papers 6 days ago

MambaIC: State Space Models for High-Performance Learned Image Compression

Paper • 2503.12461 • Published Mar 16

PPT: Token Pruning and Pooling for Efficient Vision Transformers

Paper • 2310.01812 • Published Oct 3, 2023

ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt

Paper • 2410.05849 • Published Oct 8, 2024

Towards Efficient and General-Purpose Few-Shot Misclassification Detection for Vision-Language Models

Paper • 2503.20492 • Published Mar 26

TR-DQ: Time-Rotation Diffusion Quantization

Paper • 2503.06564 • Published Mar 9

Federated Continual Instruction Tuning

Paper • 2503.12897 • Published Mar 17

upvoted 2 papers 6 days ago

Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality

Paper • 2505.18227 • Published May 23 • 15

MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark

Paper • 2508.07307 • Published Aug 10 • 1

New activity in AuroraZengfh/MambaIC 8 days ago

Access request for AuroraZengfh/MambaIC (submitted Oct 24)

1

#1 opened 8 days ago by

rubio02

authored 7 papers 21 days ago

Parameter Efficient Merging for Multimodal Large Language Models with Complementary Parameter Adaptation

Paper • 2502.17159 • Published Feb 24 • 1

HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model

Paper • 2503.12941 • Published Mar 17

Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality

Paper • 2505.18227 • Published May 23 • 15

ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing

Paper • 2505.11935 • Published May 17

A Comprehensive Survey on Continual Learning in Generative Models

Paper • 2506.13045 • Published Jun 16

Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration

Paper • 2506.05709 • Published Jun 6

MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark

Paper • 2508.07307 • Published Aug 10 • 1

updated a model 22 days ago

AuroraZengfh/LLaVA_7B_lora_r16_ImageNet

Updated 22 days ago • 15