Repro: Must All Negatives Be Pushed Away Equally?
Collection
Independent reproduction of ICML 2026 #3010 (OpenReview cCHiqfnZen). Verdict: the 18% zero-shot R@1 claim does not reproduce at reduced scale. • 4 items • Updated
Nishka
Nish228
·
AI & ML interests
Computer Vision, Generative Models, Medical Imaging, Reinforcement Learning
Recent Activity
updated a collection about 15 hours ago
Repro: Must All Negatives Be Pushed Away Equally? updated a collection about 15 hours ago
Repro: Must All Negatives Be Pushed Away Equally? updated a collection about 15 hours ago
Repro: Must All Negatives Be Pushed Away Equally?Organizations
updated a
collection about 15 hours ago
updated a
dataset about 15 hours ago
published a
dataset about 15 hours ago
updated a
bucket about 15 hours ago
published a
bucket about 15 hours ago
updated a
Space about 15 hours ago
published a
Space about 15 hours ago
updated a
Space 4 days ago
published a
Space 4 days ago
updated a
bucket 4 days ago
published a
bucket 4 days ago
updated a
bucket 4 days ago
published a
bucket 4 days ago
updated a
dataset 4 days ago
published a
dataset 4 days ago
updated a
collection 4 days ago