Fanhu Zeng
AuroraZengfh
AI & ML interests
None yet
Recent Activity
authored a paper 24 days ago
PaLoRA: Paced Low-Rank Adaptation for Continual Learning upvoted a paper 24 days ago
PaLoRA: Paced Low-Rank Adaptation for Continual Learning upvoted a paper 28 days ago
UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation ModelsOrganizations
models 9
AuroraZengfh/MambaIC
Updated • 23 • 6
AuroraZengfh/LLaVA_7B_lora_r16_ImageNet
Updated • 46
AuroraZengfh/LLaVA_7B_lora_r16_IconQA
Updated • 44
AuroraZengfh/LLaVA_7B_lora_r16_REC
Updated • 37
AuroraZengfh/LLaVA_7B_lora_r16_VQAv2
Updated • 37
AuroraZengfh/LLaVA_7B_lora_r16_flickr30k
Updated • 33
AuroraZengfh/LLaVA_7B_lora_r16_VizWiz
Updated • 41
AuroraZengfh/LLaVA_7B_lora_r16_OCRVQA
Updated • 36
AuroraZengfh/LLaVA_7B_lora_r16_ScienceQA
Updated • 43 • 1