HuggingFace
CoDA: Co-Evolution of Data Engines and Action Policies
Generative simulation can automate robot environment construction, but physically valid environments are not necessar...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use
Computer use has reached a turning point: the focus is expanding from GUI-only interaction to systems that complete t...
HuggingFace
CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness
As Vision-Language Models (VLMs) advance, they are increasingly expected to perform spatiotemporal reasoning over mot...
HuggingFace
SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models
Action-conditioned robot world models must respond precisely to robot trajectories while preserving realistic visual ...
HuggingFace
SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning
Long-horizon agentic RL is constrained by the futures visited by the current policy. When rollouts fail to reach usef...
HuggingFace
MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments
Online reinforcement learning (RL) with verifiable rewards has driven rapid progress in mathematics, coding, and tool...
HuggingFace
OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling
Generative visual verifiers play a crucial role in advancing multimodal intelligence. To enhance the robustness of vi...
HuggingFace
Data World: Scaling Data Environments from Scratch
Data agents use code to process heterogeneous files and derive analytical insights. Scaling their training faces cost...
HuggingFace
ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion
Autoregressive video diffusion models have become a leading approach to real-time interactive video generation and vi...
HuggingFace
FDE-Gym: The Last Mile of AI Delivery
Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications,...
HuggingFace
Can World and Action Modeling Benefit Each Other under Unified Causal Training?
World and action modeling are closely related, yet their reciprocal benefits under unified causal training remain unc...
HuggingFace
SUPRA-TEX: 3D Generation with Super-Aligned Texture
Single image 3D generation aims to dress a given 3D mesh with relightable materials while faithfully preserving the v...