shi-labs/IMG
Updated
•
1
AI & ML interests
Computer Vision, AI, Machine Learning
Recent Activity
View all activity
Papers
IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
OLA-VLM: Elevating Visual Perception in Multimodal LLMs with Auxiliary Embedding Distillation
shi-labs/slowfast-video-mllm-qwen2-7b-convnext-576-frame64-s1t4
Video-Text-to-Text
•
9B
•
Updated
•
39
shi-labs/slowfast-video-mllm-qwen2-7b-convnext-576-frame96-s1t6
Video-Text-to-Text
•
9B
•
Updated
•
9
shi-labs/slowfast-video-mllm-qwen2-7b-convnext-576-frame128-s2t4
9B
•
Updated
•
5
shi-labs/probe_depth_ola-vlm-pt-ift
Image-Text-to-Text
•
10B
•
Updated
•
9
shi-labs/probe_gen_ola-vlm-pt-ift
Image-Text-to-Text
•
9B
•
Updated
•
10
shi-labs/probe_gen_llava-1.5-pt-vpt-ift
Image-Text-to-Text
•
9B
•
Updated
•
10
shi-labs/probe_gen_llava-1.5-pt
Image-Text-to-Text
•
9B
•
Updated
•
8
shi-labs/probe_gen_llava-1.5-pt-0.5ift
Image-Text-to-Text
•
9B
•
Updated
•
11
shi-labs/probe_gen_llava-1.5-pt-ift
Image-Text-to-Text
•
9B
•
Updated
•
11
shi-labs/probe_depth_llava-1.5-pt-vpt-ift
Image-Text-to-Text
•
10B
•
Updated
•
9
shi-labs/probe_depth_llava-1.5-pt
Image-Text-to-Text
•
10B
•
Updated
•
10
shi-labs/probe_depth_llava-1.5-pt-0.5ift
Image-Text-to-Text
•
10B
•
Updated
•
10
shi-labs/probe_depth_llava-1.5-pt-ift
Image-Text-to-Text
•
10B
•
Updated
•
9
shi-labs/probe_seg_ola-vlm-pt-ift
Image-Text-to-Text
•
9B
•
Updated
•
9
shi-labs/probe_seg_llava-1.5-pt-vpt-ift
Image-Text-to-Text
•
9B
•
Updated
•
11
shi-labs/probe_seg_llava-1.5-pt
Image-Text-to-Text
•
9B
•
Updated
•
11
shi-labs/probe_seg_llava-1.5-pt-ift
Image-Text-to-Text
•
9B
•
Updated
•
11
shi-labs/probe_seg_llava-1.5-pt-0.5ift
Image-Text-to-Text
•
9B
•
Updated
•
10
shi-labs/pretrain_dsg_OLA-VLM-CLIP-ConvNeXT-Llama3-8b
Image-Text-to-Text
•
9B
•
Updated
•
13
shi-labs/pretrain_dsg_OLA-VLM-CLIP-ConvNeXT-Phi3-4k-mini
Image-Text-to-Text
•
5B
•
Updated
•
10
shi-labs/pretrain_dsg_OLA-VLM-CLIP-ViT-Phi3-4k-mini
Image-Text-to-Text
•
4B
•
Updated
•
11
shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b
Image-Text-to-Text
•
9B
•
Updated
•
10
•
2
shi-labs/OLA-VLM-CLIP-ConvNeXT-Phi3-4k-mini
Image-Text-to-Text
•
5B
•
Updated
•
11
•
1
shi-labs/OLA-VLM-CLIP-ConvNeXT-Llama3-8b
Image-Text-to-Text
•
9B
•
Updated
•
11
•
1
shi-labs/OLA-VLM-CLIP-ViT-Phi3-4k-mini
Image-Text-to-Text
•
4B
•
Updated
•
12
•
1
shi-labs/OLA-VLM-CLIP-ViT-Llama3-8b
Image-Text-to-Text
•
8B
•
Updated
•
13
shi-labs/pretrain_dsg_OLA-VLM-CLIP-ViT-Llama3-8b
Image-Text-to-Text
•
9B
•
Updated
•
20
shi-labs/CuMo-misc
Updated
shi-labs/CuMo-mixtral-8x7b
Text Generation
•
48B
•
Updated
•
9
•
3