Zifan Shi

Adobe Research

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Computer Vision (2)Multimodal Models (1)World Models & Planning (1)Architecture Design (Transformers, SSMs, MoE) (1)

Frequent co-authors

Xin Lin (1)Xindai Lin (1)Xinke Li (1)Baihan Yang (1)

Papers (2)

Mar 31, 2026

Mar 31, 2026·also Adobe Research, HKU, UCI, UPenn

OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation

Explore new worlds with unprecedented fidelity: OmniRoam lets you wander through long-horizon, high-resolution panoramic videos generated from a single image or video.

Xin Lin, Xindai Lin, Xinke Li +8

Computer Vision Multimodal Models World Models & Planning

Mar 18, 2026

Mar 18, 2026·also Adobe Research

LoST: Level of Semantics Tokenization for 3D Shapes

Forget geometric LODs: tokenizing 3D shapes by semantic salience unlocks SOTA reconstruction and efficient autoregressive generation with 10x-1000x fewer tokens.

Niladri Shekhar Dutt, Niladri Shekhar Dutt, Zifan Shi +10

Architecture Design (Transformers, SSMs, MoE)Computer Vision

Search

Zifan Shi

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)