Models and training data for Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture
Longxiang Zhang
zhanglx
AI & ML interests
None yet
Recent Activity
upvoted a paper 24 days ago
StepAudio 3 Realtime Technical Report upvoted a paper about 2 months ago
InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter published a dataset 5 months ago
zhanglx/TWN-training-dataOrganizations
None yet