Scholar

Haoyang Huang

Google Scholar ID: nIS66toAAAAJ

JD Explore Academy (present) | StepFun | Microsoft Research

Multimodal & Multilingual Foundation Model

Homepage↗Google Scholar↗

Citations & Impact

All-time

Citations

2,384

H-index

19

i10-index

25

Publications

20

Co-authors

0

Contact

No contact links provided.

Publications

49 items

Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video Generation

2026

Cited

0

Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning

2026

Cited

0

ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training

2026

Cited

0

Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds

2026

Cited

0

TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts

2026

Cited

0

EchoWM: Open and Enterable Omnimodal World Models

2026

Cited

0

JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion

2026

Cited

0

Role-Break in Attention Heads: Understanding and Detecting Hallucinations in VLMs

2026

Cited

0

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)