This is your work, valued

Alexander Sax (Sasha)

Advanced
@alexsax

MTS @ Anthropic | Prev: FAIR, Berkeley, Stanford

alexsax.github.io

2D-3D-Semantics. The data skeleton from Joint 2D-3D-Semantic Data for Indoor Scene Understanding

535

midlevel-reps. Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies

108

pytorch-visdom. Support powerful visual logging in PyTorch.

104

taskonomy-sample-model-1. Model, selected at random, from the training set of the paper "Taskonomy: Disentangling Task Transfer Learning"

50

robust-policies-via-midlevel-vision. Python

17

visual-prior. Code for Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies. Arxiv preprint 2018. Alexander Sax, Bradley Emi, Amir R. Zamir, Silvio Savarese, Leonidas Guibas, Jitendra Malik.

8

omnidata_models. Python

5

Locality-Prior. Implementation and analysis of adding a wiring cost to FC layers

3

abusive-comment-detection. TeX

2

testing_rlpyt. Python

2

3DSceneGraph. The data skeleton from "3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera" http://3dscenegraph.stanford.edu

2

soda. Augmentation library. When your model is not exactly SotA, and you need some empty calories.

1

alexsax.github.io. HTML

1

OpenLRM. An open-source impl. of Large Reconstruction Models

1

AdversarialExamplesNLP. Extending adversarial examples to natural language

1