[ICML 2025 Spotlight] Direct Discriminative Optimization: Supercharging Diffusion/Autoregressive with GAN-type Discrimination

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Official implementation of Rethinking Training Dynamics in Scale-wise Autoregressive Generation

EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models

[NeurIPS 2025] The official repository of "Sekai: A Video Dataset towards World Exploration"

🎯 告别信息过载，AI 助你看懂新闻资讯热点，简单的舆情监控分析 - 多平台热点聚合+基于 MCP 的AI分析工具。监控35个平台（抖音、知乎、B站、华尔街见闻、财联社等），智能筛选+自动推送+AI对话分析（用自然语言深度挖掘新闻：趋势追踪、情感分析、相似检索等13种工具）。支持企业微信/个人微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 推送，1分钟手机通知，无需…

Native Multimodal Models are World Learners

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

A simple state update rule to enhance length generalization for CUT3R

[CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

Tongyi Deep Research, the Leading Open-source Deep Research Agent

InternRobotics' open platform for building generalized navigation foundation models.

[TMLR 2024] repository for VLN with foundation models

🚀 Efficient implementations of state-of-the-art linear attention models

Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

TradingAgents: Multi-Agents LLM Financial Trading Framework

[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Dream 7B, a large diffusion language model

🔥 Official impl. of "DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction"

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

Code release for paper "Test-Time Training Done Right"

Official implementation of EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance

Awesome habitat top down map work 🤩

Official Implementation of Diffusion Step Annealing (DiSA) in Autoregressive Image Generation

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL