Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUs

DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model

arXiv:2606. 30292v1 Announce Type: new Abstract: We present DreamForge-World 0.

Introducing Waypoint-1: Real-time interactive video diffusion from Overworld

Bringing serverless GPU inference to Hugging Face users

Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication

3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated regions, causing global inconsistency, or rely on global Gaussian-level exchanges, which lead to substantial growth in inter-GPU communication and quickly dominate iteration time.

STAR-NT: Spatiotemporal Acceleration of Real-Time Neural Transparency Rendering

arXiv:2606. 16747v1 Announce Type: cross Abstract: Neural order-independent transparency delivers high-quality rendering of overlapping transparent surfaces, but its geometry passes and network input generation remain costly, particularly on mobile and legacy hardware.

Beyond Pixel Histories: World Models with Persistent 3D State

arXiv:2603. 03482v2 Announce Type: replace-cross Abstract: Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities.

A Scalable PyTorch Abstraction for Multi-GPU Gaussian Splatting

arXiv:2606. 11390v1 Announce Type: cross Abstract: Gaussian splatting methods have become increasingly popular for neural reconstruction of the real world.

WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis

arXiv:2606. 01869v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly asked not only to write static interfaces, but to construct executable interactive worlds from natural language.

AnythingReality: Robust Online Gaussian Splatting SLAM for Open-Vocabulary VR Scene Exploration

We present a novel integrated architecture for robust online 3D Gaussian splatting, real-time VR exploration, and speech-driven Vision-Language-Model interaction. Unlike methods assuming clean depth or external poses, our system combines ORB-SLAM3-based pose estimation with online Gaussian reconstruction for noisy real-world data.

Easily Train Models with H100 GPUs on NVIDIA DGX Cloud

EgoSim: Egocentric World Simulator for Embodied Interaction Generation

arXiv:2604. 01001v2 Announce Type: replace-cross Abstract: We introduce EgoSim, a closed-loop egocentric world simulator that generates spatially consistent interaction videos and persistently updates the underlying 3D scene state for continuous simulation.

FBLayout: Optimizing Memory Layout for Efficient LLM Finetuning on Mobile GPUs

arXiv:2607. 21624v1 Announce Type: cross Abstract: Transformer-based models have enabled unprecedented capabilities across language, vision, and multimodal tasks.