Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch

world modeling challenge for humanoid robots

Inference code for Llama models

Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?

A playbook for systematically maximizing the performance of deep learning models.

[CVPR 2024] TEA: Test-time Energy Adaptation

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

The simplest, fastest repository for training/finetuning medium-sized GPTs.

A curated reading list of research in Adaptive Computation, Inference-Time Computation & Mixture of Experts (MoE).

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation

NeurIPS'24 Learning World Models for Unconstrained Goal Navigation

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

code for the paper Predicting Point Tracks from Internet Videos enables Diverse Zero-Shot Manipulation

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

[ICLR 2025] ControlAR: Controllable Image Generation with Autoregressive Models

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

The ProcTHOR-10K Houses Dataset

Jax implementation of VIT-VQGAN

Taming Transformers for High-Resolution Image Synthesis

Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.