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
50.59/100
前 8.3%
全站排名 #5,348
发表论文17 篇
平均评分
年均产出5.7 篇/年
Tianyu He
研究方向
machine learning · multimodal learning · generative learning
16
Quotient-Space Diffusion Models
ICLR 2026Oral
19
CP4D: Compositional physics-aware 4D scene generation
ICLR 2026Rejected
三作5
AR4D: Autoregressive 4D Generation from Monocular Videos
ICLR 2026Withdrawn
二作19
Reinforcement Learning with Inverse Rewards for World Model Post-training
ICLR 2026Rejected
二作5
Playing with Transformer at 30+ FPS via Next-Frame Diffusion
ICLR 2026Withdrawn
二作14
Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
ICLR 2026Poster
三作5
Fast Autoregressive Video Generation with Diagonal Decoding
ICLR 2026Withdrawn
7
Luminark: Training-free, Reliable Watermarking for General Vision Generative Models
ICLR 2026Rejected
5
Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft
ICLR 2026Withdrawn
5
LatentBit: Discrete Visual Tokenization with Preserved Continuous Structure
ICLR 2026Withdrawn
23
Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators
ICLR 2025Poster
三作31
UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing
ICLR 2025Rejected
二作19
IGOR: Image-GOal Representations are the Atomic Building Blocks for Next-Level Generalization in Embodied AI
ICLR 2025Rejected
三作6
VideoDiT: Bridging Image Diffusion Transformers for Streamlined Video Generation
ICLR 2025Rejected
三作