← Authors

Yonglong Tian

35 papers · 2014–2025 · 8 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (11) 🐝 Cross-Pollinator (10) 🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (44) πŸ‘‘ Triple Crown 🀝 Dynamic Duo (11) 🧬 Topic Evolution πŸ† Grand Slam πŸ’Ž Century Club (35) ⚑ Prolific Year (7) ❓ The Questioner (3) πŸ—ƒοΈ Keyword Collector (112) πŸ”₯ Unstoppable (8)

Conferences

ICLR (9) CVPR (8) NIPS (7) ECCV (3) ICCV (3) ICML (3) AAAI (1) WACV (1)

Top co-authors

Dilip Krishnan (11) Phillip Isola (11) Dina Katabi (6) Lijie Fan (6) Tianhong Li (5) Xiaoou Tang (4) Chen Sun (4) Ping Luo (4) Xiaogang Wang (4) Hang Zhao (3)

Research topics

Core AI (1)

Keywords

contrastive learning (8) representation learning (6) self-supervised learning (4) pedestrian detection (3) transfer learning (3) synthetic image (3) text-to-image model (3) diffusion model (2) semantic segmentation (2) convolutional neural network (2) vision-language model (2) visual representation (2) object detection (2) knowledge distillation (2) deep learning (2) image retrieval (1) embedding space (1) pose estimation (1) zero-shot learning (1) image generation (1)

Papers

Personalized Representation from Personalized Generation ICLR 2025
Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens ICLR 2025
Vision-Language Models Do Not Understand Negation CVPR 2025
Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency ICLR 2024
Autoregressive Image Generation without Vector Quantization NIPS 2024
Self-Correcting Self-Consuming Loops for Generative Model Training ICML 2024
Scaling Laws of Synthetic Images for Model Training ... for Now CVPR 2024
Learning Vision from Models Rivals Learning Vision from Data CVPR 2024
Denoising Vision Transformers ECCV 2024
Addressing Feature Suppression in Unsupervised Visual Representations WACV 2023
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models ICML 2023
Self-supervision through Random Segments with Autoregressive Coding (RandSAC) ICLR 2023
StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners NIPS 2023
Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision? ICLR 2023
Restart Sampling for Improving Generative Processes NIPS 2023
Improving CLIP Training with Language Rewrites NIPS 2023
Unsupervised Learning of Shape Programs with Repeatable Implicit Parts NIPS 2022
Generative Models as a Data Source for Multiview Representation Learning ICLR 2022
Co-Advise: Cross Inductive Bias Distillation CVPR 2022
Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate AAAI 2022
Divide and Contrast: Self-Supervised Learning From Uncurated Data ICCV 2021
Composable Augmentation Encoding for Video Representation Learning ICCV 2021
Rethinking Few-shot Image Classification: A Good Embedding is All You Need? ECCV 2020
Supervised Contrastive Learning NIPS 2020
Contrastive Multiview Coding ECCV 2020
What Makes for Good Views for Contrastive Learning? NIPS 2020
Contrastive Representation Distillation ICLR 2020
ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees ICLR 2019
Learning to Infer and Execute 3D Shape Programs ICLR 2019
Representation Learning on Graphs with Jumping Knowledge Networks ICML 2018
Through-Wall Human Pose Estimation Using Radio Signals CVPR 2018
Deep Learning Strong Parts for Pedestrian Detection ICCV 2015
Pedestrian Detection Aided by Deep Learning Semantic Tasks CVPR 2015
DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection CVPR 2015
Switchable Deep Network for Pedestrian Detection CVPR 2014