Trevor Darrell
Graph View
Backlinks
- A ConvNet for the 2020s
- Chain-of-Visual-Thought - Teaching VLMs to See and Think Better with Continuous Visual Tokens
- Curiosity-driven Exploration by Self-supervised Prediction
- Early Convolutions Help Transformers See Better
- Rethinking patch dependence for masked autoencoders
- Stochastic positional embeddings improve masked image modeling
- xT - Nested Tokenization for Larger Context in Large Images