huggyllama/llama-7b
Text Generation
•
7B
•
Updated
•
68.6k
•
352
Hanxun Yu
JonnyYu828
·
AI & ML interests
Multimodal LLMs, Spatial Intelligence, Embodied AI
Recent Activity
authored
a paper
1 day ago
N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models
authored
a paper
1 day ago
StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
authored
a paper
2 days ago
Physical Adversarial Attack meets Computer Vision: A Decade Survey
Organizations
liked
a
model
almost 2 years ago