| ▲ | SoftTalker 5 hours ago | |
LLMs are trained on text. Why would we expect them to understand a visual and tactile 3D world? | ||
| ▲ | azinman2 5 hours ago | parent [-] | |
Because they’re also multimodal vLLMs. | ||
| ▲ | SoftTalker 5 hours ago | |
LLMs are trained on text. Why would we expect them to understand a visual and tactile 3D world? | ||
| ▲ | azinman2 5 hours ago | parent [-] | |
Because they’re also multimodal vLLMs. | ||