AMAP-ML

Let Skills Evolve Collectively with Agentic Evolver

The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features...

Implementation of "FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing"

DreamX-World: A General-Purpose Interactive World Model

[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning

Democratizing Native Audio-Video Generation at 2K Resolution

[NeurIPS2026] Code2World: A GUI World Model via Renderable Code Generation

[CVPR 2026] Beyond Generation: Advancing Image Editing Priors for Depth and Normal Estimation

[ICLR2026] Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools

[ICLR2026] AutoDrive-R2: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving

[ECCV 2026] RL3DEdit

[ICLR26]GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning

This repository collects a series of generative recommendation models from DreamX-Rec.

[ICLR 26] Official implementation of the paper "Urban Socio-Semantic Segmentation with Vision-Language Reasoning"

[ACL 2026 Findings] Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization

[AAAI2026] Implementation Code for Omni-Effects

UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning

[KDD 2026 Oral] MobilityBench: A Scalable Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios

[ICLR2026] Implementation of "S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models"

[ICLR2026] There is No VAE: End-To-End Pixel-Space Generative Modeling Via Self-Supervised Pre-Training

Benchmarking models as runtime Controllers for Loop Engineering

[ICLR2026] Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models

[CVPR 26] From Scale to Speed: Adaptive Test-Time Scaling for Image Editing

[ICLR 2026] Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation

[CVPR 2026] Elucidating the SNR-t Bias of Diffusion Probabilistic Models

[SIGGRAPH 2026] MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation

[NeurIPS 26] Official implementation of the paper "Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes"

[ICLR26] NarrLV: Towards a Comprehensive Narrative-Centric Evaluation for Long Video Generation Models

[2026 CVPR]Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation

A comprehensive benchmark specifically designed to evaluate the interactive response capabilities of world models in 4D settings.

[ICCV25] USP: Unified Self-Supervised Pretraining for Image Generation and Understanding

[CVPR 2026 Findings] Eevee: Towards Close-up High-resolution Video-based Virtual Try-on

[ICCV 25] VMBench: A Benchmark for Perception-Aligned Video Motion Generation

DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation

OmniDance

[AAAI2026] ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints