Hansen-Estruch, P., Chen, J., Ramanujan, V., Zohar, O., Ping, Y., Sinha, A., . . . Thabet, A. (2026). ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters.
Chicago Style (17th ed.) CitationHansen-Estruch, Philippe, et al. ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters. 2026.
MLA (9th ed.) CitationHansen-Estruch, Philippe, et al. ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters. 2026.
Warning: These citations may not always be 100% accurate.