970 citations · 2.8k across the 29 of their papers we have counts for
29 papers
Visual General Intelligence: A White Paper
Hirokatsu Kataoka, Yoshihiro Fukuhara, Yonglong Tian +18
This paper reconsiders intelligence from a vision-centered perspective and examines whether intelligence emerging from visual experience and learning may provide a pathway toward A…
Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs
Xinming Wang, Weinong Wang, Hongming Yang +13
Hybrid-thinking multimodal large language models (MLLMs) allow a single model to alternate between deliberative thinking and latency-efficient non-thinking inference. Although thes…
Vision-Language Models Do Not Understand Negation
Kumail Alhamoud, Shaden Alshammari, Yonglong Tian +4
Many practical vision-language applications require models that understand negation, e.g., when using natural language to retrieve images which contain certain objects but not othe…
Learning Vision from Models Rivals Learning Vision from Data
Yonglong Tian, Lijie Fan, Kaifeng Chen +3
We introduce SynCLR, a novel approach for learning visual representations exclusively from synthetic images and synthetic captions, without any real data. We synthesize a large dat…
Scaling Laws of Synthetic Images for Model Training ... for Now
Lijie Fan, Kaifeng Chen, Dilip Krishnan +3
Recent significant advances in text-to-image models unlock the possibility of training vision systems using synthetic images, potentially overcoming the difficulty of collecting cu…
Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency
Tianhong Li, Sangnie Bhardwaj, Yonglong Tian +6
Current vision-language generative models rely on expansive corpora of paired image-text data to attain optimal performance and generalization capabilities. However, automatically…
Restart Sampling for Improving Generative Processes
Yilun Xu, Mingyang Deng, Xiang Cheng +3
Generative processes that involve solving differential equations, such as diffusion models, frequently necessitate balancing speed and quality. ODE-based samplers are fast but plat…
StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners
Yonglong Tian, Lijie Fan, Phillip Isola +2
We investigate the potential of learning visual representations using synthetic images generated by text-to-image models. This is a natural question in the light of the excellent p…
Improving CLIP Training with Language Rewrites
Lijie Fan, Dilip Krishnan, Phillip Isola +2
Contrastive Language-Image Pre-training (CLIP) stands as one of the most effective and scalable methods for training transferable vision models using paired image and text data. CL…
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
Yilun Xu, Ziming Liu, Yonglong Tian +3
We introduce a new family of physics-inspired generative models termed PFGM++ that unifies diffusion models and Poisson Flow Generative Models (PFGM). These models realize generati…
Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?
Lirui Wang, Kaiqing Zhang, Yunzhu Li +2
Decentralized learning has been advocated and widely deployed to make efficient use of distributed datasets, with an extensive focus on supervised learning (SL) problems. Unfortuna…
Self-supervision through Random Segments with Autoregressive Coding (RandSAC)
Tianyu Hua, Yonglong Tian, Sucheng Ren +3
Inspired by the success of self-supervised autoregressive representation learning in natural language (GPT and its variants), and advances in recent visual architecture design with…
Co-advise: Cross Inductive Bias Distillation
Sucheng Ren, Zhengqi Gao, Tianyu Hua +4
Transformers recently are adapted from the community of natural language processing as a promising substitute of convolution-based neural networks for visual learning tasks. Howeve…
Simple Distillation Baselines for Improving Small Self-supervised Models
Jindong Gu, Wei Liu, Yonglong Tian
While large self-supervised models have rivalled the performance of their supervised counterparts, small models still struggle. In this report, we explore simple baselines for impr…
Generative Models as a Data Source for Multiview Representation Learning
Ali Jahanian, Xavier Puig, Yonglong Tian +1
Generative models are now capable of producing highly realistic images that look nearly indistinguishable from the data on which they are trained. This raises the question: if we h…
Divide and Contrast: Self-supervised Learning from Uncurated Data
Yonglong Tian, Olivier J. Henaff, Aaron van den Oord
Self-supervised learning holds promise in leveraging large amounts of unlabeled data, however much of its progress has thus far been limited to highly curated pre-training data suc…
Composable Augmentation Encoding for Video Representation Learning
Chen Sun, Arsha Nagrani, Yonglong Tian +1
We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different da…
Addressing Feature Suppression in Unsupervised Visual Representations
Tianhong Li, Lijie Fan, Yuan Yuan +5
Contrastive learning is one of the fastest growing research areas in machine learning due to its ability to learn useful representations without labeled data. However, contrastive…
What Makes for Good Views for Contrastive Learning?
Yonglong Tian, Chen Sun, Ben Poole +3
Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning. Despite its succ…
Supervised Contrastive Learning
Prannay Khosla, Piotr Teterwak, Chen Wang +6
Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training…
Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?
Yonglong Tian, Yue Wang, Dilip Krishnan +2
The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost…
Contrastive Representation Distillation
Yonglong Tian, Dilip Krishnan, Phillip Isola
Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from…
Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate
Lu Mi, Hao Wang, Yonglong Tian +2
Uncertainty estimation is an essential step in the evaluation of the robustness for deep learning models in computer vision, especially when applied in risk-sensitive areas. Howeve…
Contrastive Multiview Coding
Yonglong Tian, Dilip Krishnan, Phillip Isola
Humans view the world through many sensory channels, e.g., the long-wavelength light channel, viewed by the left eye, or the high-frequency vibrations channel, heard by the right e…