arxiv:2509.24317
xhl PRO
Xianhang
·
AI & ML interests
Computer Vision
Recent Activity
authored
a paper
about 1 month ago
Unleashing the Power of Visual Prompting At the Pixel Level
authored
a paper
about 1 month ago
CLIPS: An Enhanced CLIP Framework for Learning with Synthetic Captions
authored
a paper
about 1 month ago
OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision
Encoders for Multimodal Learning
Organizations
models
6
Xianhang/openailclip_llava_llm_fp32
8B
•
Updated
Xianhang/clips_llava15_head_fp32
8B
•
Updated
Xianhang/clips_clip_fp32_llm_bf16
8B
•
Updated
•
1
Xianhang/clips_llava_llama3_8b_ft_256_lr1e5_from_bf16_llm
Updated
Xianhang/clips_llava_llama3_8b_ft_256_lr1e5
8B
•
Updated
Xianhang/openai_clip_llava15_llama3_8b_baseline_256_lr1e5
8B
•
Updated
datasets
0
None public yet