arxiv:2503.11315
Jeonghun
jh-y
AI & ML interests
Multimodal learning
Recent Activity
updated a model about 8 hours ago
jh-y/dllm-vsr published a model about 23 hours ago
jh-y/dllm-vsr authored a paper about 1 year ago
MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with
Minimal Multimodal Speech TokensOrganizations
None yet
datasets 0
None public yet