Fanhu Zeng
AuroraZengfh
AI & ML interests
None yet
Recent Activity
authored a paper about 3 hours ago
PaLoRA: Paced Low-Rank Adaptation for Continual Learning upvoted a paper about 8 hours ago
PaLoRA: Paced Low-Rank Adaptation for Continual Learning upvoted a paper 4 days ago
UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation ModelsOrganizations
models 9
AuroraZengfh/MambaIC
Updated • 61 • 6
AuroraZengfh/LLaVA_7B_lora_r16_ImageNet
Updated • 64
AuroraZengfh/LLaVA_7B_lora_r16_IconQA
Updated • 67
AuroraZengfh/LLaVA_7B_lora_r16_REC
Updated • 66
AuroraZengfh/LLaVA_7B_lora_r16_VQAv2
Updated • 62
AuroraZengfh/LLaVA_7B_lora_r16_flickr30k
Updated • 63
AuroraZengfh/LLaVA_7B_lora_r16_VizWiz
Updated • 67
AuroraZengfh/LLaVA_7B_lora_r16_OCRVQA
Updated • 65
AuroraZengfh/LLaVA_7B_lora_r16_ScienceQA
Updated • 69 • 1