Sifei Liu

Nvidia (United States) — United States

Computer Science · Physical Sciences

31h-index6.3kcitations130works6.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Vision and Imaging(35), Advanced Image and Video Retrieval Techniques(25), Advanced Image Processing Techniques(22), Generative Adversarial Networks and Image Synthesis(21), Human Pose and Action Recognition(21)

Publications130 total

Temporal Prompting Matters: Rethinking Referring Video Object Segmentation
arXiv (Cornell University)·2025Open Access
3D Aware Region Prompted Vision Language Model
arXiv (Cornell University)·2025Open Access
Scaling RL to Long Videos
arXiv (Cornell University)·2025Open Access
NaVILA: Legged Robot Vision-Language-Action Model for Navigation
2025· 8 citedOpen Access
NVILA: Efficient Frontier Visual Language Models
2025· 8 cited
Scaling Vision Pre-Training to 4K Resolution
2025· 1 cited
Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks
2025· 1 cited
BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations
2025· 2 cited
Parallel Sequence Modeling via Generalized Spatial Propagation Network
2025
Describe Anything: Detailed Localized Image and Video Captioning
arXiv (Cornell University)·2025Open Access
SSE: Multimodal Semantic Data Selection and Enrichment for Industrial-scale Data Assimilation
2025Open Access
Synthesizing Consistent Novel Views Via 3D Epipolar Attention Without Re-Training
2025
Synthesizing Consistent Novel Views via 3D Epipolar Attention without Re-Training
arXiv (Cornell University)·2025Open Access
Parallel Sequence Modeling via Generalized Spatial Propagation Network
arXiv (Cornell University)·2025Open Access
Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks
arXiv (Cornell University)·2025Open Access
BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations
arXiv (Cornell University)·2025Open Access
Compositional Text-to-Image Generation with Feedforward Layout Generation
Lecture notes in computer science·2025
NaVILA: Legged Robot Vision-Language-Action Model for Navigation
arXiv (Cornell University)·2024· 1 citedOpen Access
NVILA: Efficient Frontier Visual Language Models
arXiv (Cornell University)·2024· 1 citedOpen Access
BlobGEN-3D: Compositional 3D-Consistent Freeview Image Generation with 3D Blobs
2024· 2 citedOpen Access
page 1 of 7Next →

Frequent Co-authors

Ming–Hsuan Yang(28), Jan Kautz(17), Shalini De Mello(15), Xiaolong Wang(8), Xueting Li(7), Xiaolong Wang(6), Xueting Li(4), Jinshan Pan(4), Jinwei Gu(4), Shuicheng Yan(3), Wenqi Ren(3), Wonmin Byeon(3), Deqing Sun(3), Jiawei Zhang(3), Jimmy Ren(3), Yang Fu(3), Guangyu Zhong(3), An-Chieh Cheng(3), Zhiding Yu(3), Yi Dong(2)