影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
75.31/100
前 1.8%
全站排名 #1,187
发表论文18 篇
平均评分
年均产出6.0 篇/年
Hangjie Yuan
研究方向
Video generation/editing · Vision-language models · Relation detection · human-object interaction detection · Video understanding
17
LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation
ICLR 2026Poster
三作24
CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
ICLR 2026Poster
通讯20
Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective
ICLR 2026Poster
一作16
Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance
ICLR 2026Poster
三作6
C-Flat Turbo: A Faster Path to Continual Learning
ICLR 2026Withdrawn
三作6
DFVEdit: Conditional Delta Flow Vector for Zero-shot Video Editing
ICLR 2026Rejected
三作6
Frequency Autoregressive Image Generation with Continuous Tokens
ICLR 2026Withdrawn
三作13
Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
ICML 2025Poster
二作27
UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback
NeurIPS 2025Poster
二作17
VideoMAR: Autoregressive Video Generation with Continuous Tokens
NeurIPS 2025Poster
三作13
ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
ICML 2025Poster
18
DFVEdit: Conditional Delta Flow Vector for Zero-shot Video Editing
NeurIPS 2025Rejected
三作26
Zero-Shot Subject-Driven Video Customization with Precise Motion Control
ICLR 2025Rejected
三作34
Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
ICLR 2025Rejected
三作