@ylecun 오늘의 포스팅 - 2025-12-26
📌 오늘의 포스팅
🔁 [RT] If you took the time to read the SAM 2 paper, you ...
If you took the time to read the SAM 2 paper, you learned that in SAM 2, a user clicks a point on an object or draws a bounding box around it, and the model returns a segmentation mask for that particular object. To segment five similar objects in a scene, five separate prompts
The original Segment Anything Model (SAM) paper published in 2023 revolutionized image segmentation, but segmenting video remained hard. Existing solutions required combining SAM with separate video trackers, leading to error propagation and no way to interactively refine
— @burkov
🔁 [RT] "I doubt that anything resembling genuine "artific...
"I doubt that anything resembling genuine "artificial general intelligence" is within reach of current AI tools. However, I think a weaker, but still quite valuable, type of "artificial general cleverness" is becoming a reality in various ways." ~ Terence Tao Even if the
🔁 [RT] Dear USA. What about asking your President about f...
Dear USA. What about asking your President about freedom of speech instead of lecturing us Europeans? I mean seems you have a much bigger problem than we have.
#뉴스 #트렌드
@ylecun | 2025-12-27