Stars
A benchmark for evaluating LLMs on open-ended CS problems. Exploring the Next Frontier of Computer Science.
Hierarchical Reasoning Model Official Release
Official Implemenation for RAEv2: Improved Baselines with Representation Autoencoders
Cambrian-P: Pose-Grounded Video Understanding
Claude code environment for laywers
Accompanying code for "Discovering State-of-the-art Reinforcement Algorithms" Nature publication
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
JoyAI-Image is the unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing.
Project website for "Beyond Language Modeling: An Exploration of Multimodal Pretraining" paper.
The first multiplayer video world model in Minecraft
Sample LaTex file for HKU PhD thesis.
LaTeX Template for HKU MPhil and PhD Thesis
Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
[CVPR 2026] Pixio: a capable vision encoder dedicated to dense prediction, simply by pixel reconstruction
Official code of "LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer"
Sudoku4LLM is a Sudoku dataset generator for training and evaluating reasoning in Large Language Models (LLMs). It offers customizable puzzles, difficulty levels, and 11 serialization formats to su…
PyTorch implementation of JiT https://arxiv.org/abs/2511.13720
Official implementation of "Continuous Autoregressive Language Models"
Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
A Walsh Hadamard Derived Linear Vector Symbolic Architecture 🔥
[NeurIPS'25] Official repository of Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
[ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.