Cambrian-S: Towards Spatial Supersensing in Video

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

股票接口 | 韭菜小猪 | A股 | 美股 | 港股 | 股票 | 基金 | JavaScript

Official PyTorch implementation for "Large Language Diffusion Models"

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

A curated list for awesome discrete diffusion models resources.

Ultra-high definition benchmark for zero-shot image reconstruction evaluation, including 2293 images at 2k resolution sourced from the ground-truth test sets of HRSOD, LIU4k, UAVid, UHDM, and UHRSD…

🌐 3D and 4D World Modeling: A Survey

[Arxiv'25] MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization

A sparse attention kernel supporting mix sparse patterns

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.

Reference PyTorch implementation and models for DINOv3

Cameras as Relative Positional Encoding

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Experts via Clustering

Wan: Open and Advanced Large-Scale Video Generative Models

PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning

讨贼王云鹤檄文

Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, i…

Official repository for "RLVR-World: Training World Models with Reinforcement Learning" (NeurIPS 2025), https://arxiv.org/abs/2505.13934

诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

Official Code for Epona: Autoregressive Diffusion World Model for Autonomous Driving (ICCV 2025)

健康学习到150岁 - 人体系统调优不完全指南

[ICLR 2024 spotlight] Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI

PyTorch code and models for VJEPA2 self-supervised learning from video.

Official implementation of BLIP3o-Series

Official code for the CVPR 2025 paper "Navigation World Models".

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models. CVPR Oral 2025.