Sergey Tulyakov
~Sergey_Tulyakov1
25
论文总数
12.5
年均投稿
平均评分
接收情况17/25
会议分布
ICLR
14
NeurIPS
9
ICML
2
发表论文 (25 篇)
202516 篇
4
Scalable Ranked Preference Optimization for Text-to-Image Generation
ICLR 2025Rejected
4
Improving Progressive Generation with Decomposable Flow Matching
NeurIPS 2025Poster
4
DELTA: DENSE EFFICIENT LONG-RANGE 3D TRACKING FOR ANY VIDEO
ICLR 2025Poster
4
Taming Data and Transformers for Audio Generation
ICLR 2025Rejected
3
VIA: Unified Spatiotemporal Video Adaptation for Global and Local Video Editing
ICLR 2025withdrawn
4
I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models
ICML 2025Poster
4
Improving the Diffusability of Autoencoders
ICML 2025Poster
4
DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
NeurIPS 2025Spotlight
4
Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach
NeurIPS 2025Poster
3
Lightweight Predictive 3D Gaussian Splats
ICLR 2025Poster
4
Preventing Shortcuts in Adapter Training via Providing the Shortcuts
NeurIPS 2025Poster
4
VideoAlchemy: Open-set Personalization in Video Generation
ICLR 2025withdrawn
5
GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement
ICLR 2025Poster
5
ControlMM: Controllable Masked Motion Generation
ICLR 2025Rejected
4
Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation
NeurIPS 2025Poster
5
VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control
ICLR 2025Poster
20249 篇
4
UpFusion: Novel View Diffusion from Unposed Sparse View Observations
ICLR 2024Rejected
5
AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
NeurIPS 2024Poster
5
4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models
NeurIPS 2024Poster
4
Towards Text-guided 3D Scene Composition
ICLR 2024withdrawn
4
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
NeurIPS 2024Poster
4
HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion
ICLR 2024Poster
4
E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation
ICLR 2024withdrawn
4
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
ICLR 2024Poster
4
SF-V: Single Forward Video Generation Model
NeurIPS 2024Poster