3 papers
cs.LG2026
dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning
Arnav Shah, Junzhe Li, Parsa Idehpour +7
Genomic foundation models have the potential to decode DNA syntax, yet face a fundamental tradeoff in their input representation. Standard fixed-vocabulary tokenizers fragment biol…
cs.CV2025
Autoregressive Universal Video Segmentation Model
Miran Heo, Sukjun Hwang, Min-Hung Chen +4
Recent video foundation models such as SAM2 excel at prompted video segmentation by treating masks as a general-purpose primitive. However, many real-world settings require unpromp…
cs.LG2025
Dynamic Chunking for End-to-End Hierarchical Sequence Modeling
Sukjun Hwang, Brandon Wang, Albert Gu
Major progress on language models (LMs) in recent years has largely resulted from moving away from specialized models designed for specific tasks, to general models based on powerf…