Elin Bergström
elinberg-01
·
AI & ML interests
multimodal rag, image captioning
Recent Activity
liked a Space about 6 hours ago
JBDef/VisualQuestionAnswering upvoted a paper about 6 hours ago
CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models upvoted a paper 2 days ago
How Far Can Coding Agents Go in Visual Generation?Organizations
None yet