phillipi
Follow
Stars
Code for Words That Make Language Models Perceive
Supporting code for the blog post on modular manifolds.
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Don't just regulate gradients like in Muon, regulate the weights too
Single-pass Adaptive Image Tokenization for Minimum Program Search | What's the Kolmogorov Complexity of an Image?
A unified Python package that standardizes existing implementations of similarity measures to faciliate comparisons across studies.
Official implementation of the paper "What Makes for a Good Stereoscopic Image" CVPRW 2025
CycleReward is a reward model trained on cycle consistency preferences to measure image-text alignment.
Code for the Fractured Entangled Representation Hypothesis position paper!
A curated list of awesome papers on the platonic representation hypothesis.
Muon is an optimizer for hidden layers in neural networks
Automating the Search for Artificial Life with Foundation Models!
Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?
Official Repo for the paper "Learning Visual Parkour from Generated Images" (CoRL 2024).
Vuer is a 3D visualization tool for robotics and VR applications.
Simplifying reinforcement learning for complex game environments
Learning from synthetic data - code and models
F3RM: Feature Fields for Robotic Manipulation. Official repo for the paper "Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation" (CoRL 2023).
Open source code for paper "Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning" ICML 2023
DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (NeurIPS 2023 Spotlight) / / / / When Does Perceptual Alignment Benefit Vision Representations? (NeurIPS 2024)
Repository for the MultiEarth 2023 public challenge.
[NeurIPS 2023] Text data, code and pre-trained models for paper "Improving CLIP Training with Language Rewrites"
Zero-shot Image-to-Image Translation [SIGGRAPH 2023]