Antonio Torralba
MIT EECS professor; pioneer in computer vision, scene understanding, and multimodal representation learning.
- Role
- professor
- Currently at
- MIT CSAIL
- Scholar
- scholar.google.com/citations
- Papers
- 29
Cite
Notes
Only stored in your browser.
Authored papers
29MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
arXiv 2026
Ambient Diffusion Omni: Training Good Models with Bad Data
arXiv 2025
SketchAgent: Language-Driven Sequential Sketch Generation
CVPR 2025 1
MMToM-QA: Multimodal Theory of Mind Question Answering
arXiv 2024
A Multimodal Automated Interpretability Agent
arXiv 2024
Improving Factuality and Reasoning in Language Models through Multiagent Debate
arXiv 2023
Follow Anything: Open-set detection, tracking, and following in real-time
arXiv 2023
Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning
arXiv 2023
Debiasing Vision-Language Models via Biased Prompts
arXiv 2023
Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models
arXiv 2023
FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation
arXiv 2023
FIND: A Function Description Benchmark for Evaluating Interpretability Methods
find-a-function-description-benchmark-for
Dataset Distillation by Matching Training Trajectories
CVPR 2022 1
Compositional Visual Generation with Composable Diffusion Models
arXiv 2022
Incidents1M: a large-scale dataset of images with natural disasters, damage, and incidents
arXiv 2022
Denoised MDPs: Learning World Models Better Than the World Itself
arXiv 2022
Procedural Image Programs for Representation Learning
arXiv 2022
$BT^2$: Backward-compatible Training with Basis Transformation
arXiv 2022
Ego4D: Around the World in 3,000 Hours of Egocentric Video
CVPR 2022 1
Learning to See by Looking at Noise
NeurIPS 2021 12
Toward a Visual Concept Vocabulary for GAN Latent Space
toward-a-visual-concept-vocabulary-for-gan
Debiased Contrastive Learning
NeurIPS 2020 12
Understanding the Role of Individual Units in a Deep Neural Network
arXiv 2020
Rewriting a Deep Generative Model
ECCV 2020 8
Diverse Image Generation via Self-Conditioned GANs
diverse-image-generation-via-self-conditioned
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
gan-dissection-visualizing-and-understanding-1
Dataset Distillation
arXiv 2018
Network Dissection: Quantifying Interpretability of Deep Visual Representations
network-dissection-quantifying-1
Semantic Understanding of Scenes through the ADE20K Dataset
arXiv 2016
Affiliations
Frequent co-authors
10from 29 papers