5arXiv cs.LG (Machine Learning)·
ARDY: NVIDIA's streaming autoregressive diffusion framework for real-time controllable 3D human motion generation
NVIDIA researchers introduce ARDY, a streaming motion generation framework that combines autoregressive transformers with diffusion-based denoising to produce high-fidelity 3D human motions in real-time. The system uses a hybrid representation pairing explicit root features with latent body embeddings, enabling online text prompting and flexible long-horizon kinematic constraints simultaneously. ARDY is evaluated on HumanML3D and a large-scale proprietary dataset (Bones Rigplay), with an interactive demo showing dynamic text control, keyframe constraints, and locomotion. The work targets animation, simulation, and humanoid robotics applications where both controllability and inference speed are required.
Related guides (3)
Related events (8)
Towards Speed-of-Light Text Generation with Nemotron-Labs Diffusion Language Models
NVIDIA's Nemotron-Labs introduces diffusion-based language models targeting extremely fast text generation, published as a Hugging Face blog post. The piece covers the approach of using diffusion processes for language modeling as an alternative to autoregressive generation, with a focus on inference speed. This represents a continued push by NVIDIA's research arm into non-autoregressive generation paradigms.
NVlabs/ProtoMotions: GPU-accelerated framework for physically simulated humanoid motion learning
NVIDIA Labs released ProtoMotions, an open-source Python framework for GPU-accelerated simulation and reinforcement learning of physically simulated digital humans and humanoid robots. The project is trending on GitHub with 1,916 stars and 63 new stars today. It sits at the intersection of physics simulation, embodied AI, and robotics training infrastructure.
First multiplayer world model for dynamic environments using latent diffusion on Rocket League gameplay
Researchers introduce the first multiplayer world model capable of conditioning on action streams from multiple agents simultaneously, trained on 10,000 hours of Rocket League gameplay. The 5-billion-parameter latent diffusion model generates four-player matches in real time at 20 FPS on a single Nvidia B200 GPU, with rollouts remaining stable far beyond the training horizon (tested to five minutes, observed for hours). The paper systematically investigates codec design, generative objectives, and multiplayer conditioning, and releases the dataset, codebase, and a live demo. The work advances world model research by addressing multi-agent attribution and coherence under complex physical dynamics.
D4RT: DeepMind's Unified 4D Reconstruction and Tracking System, Up to 300x Faster
DeepMind has announced D4RT, a system for unified four-dimensional (spatial + temporal) scene reconstruction and tracking. The method claims up to 300x speed improvements over prior approaches. The announcement positions D4RT as a significant efficiency advance in dynamic 3D scene understanding, with potential applications in robotics, video understanding, and embodied AI.
DreamForge-World 0.1 Preview: real-time controllable world model on consumer GPUs
Researchers present DreamForge-World 0.1 Preview, a world model for real-time interactive simulation that runs on a single RTX 4090 at 14-15 FPS at 480p resolution. The system adapts the LongLive 1 autoregressive video stack (derived from Wan2.1-T2V-1.3B) with a residual action pathway from the Matrix-Game family, supporting keyboard/mouse control, multimodal initialization, mid-stream reprompting, and dual-view operation. The work targets a low-compute niche distinct from frontier-scale world simulators, demonstrating a cost-efficient route to consumer-GPU-deployable interactive world models.
AdaSR: Adaptive streaming reasoning framework with Hierarchical Relative Policy Optimization
Researchers introduce AdaSR, a framework enabling large reasoning models to reason incrementally during streaming input (e.g., audio/video) rather than waiting for complete context, then perform final deliberation once the stream ends. The core contribution is Hierarchical Relative Policy Optimization (HRPO), which decomposes policy optimization into streaming and deep reasoning phases with fine-grained per-phase advantage assignment, integrating format, accuracy, and latency-aware rewards. Experiments show AdaSR improves the tradeoff among reasoning accuracy, computational efficiency, and streaming latency over supervised fine-tuning baselines. Code is publicly released.
TunerDiT: Training-free Progressive Steering of Diffusion Transformers for Multi-Event Video Generation
TunerDiT is a training-free method for steering video diffusion transformers (DiTs) to generate long-horizon videos containing multiple sequential events. The approach identifies intrinsic turning points in the DiT denoising trajectory where text conditioning shifts from global layout to fine-grained detail, then applies two steering mechanisms: Event-Partitioned Masking and Cross-Event Prompt Fusion. The authors also introduce Meve, a benchmark prompt suite for multi-event video generation, and report state-of-the-art results across 8 metrics with improved text alignment scaling with event count.
MolmoMotion: Language-guided 3D motion forecasting from Allen AI
Allen AI published a blog post on Hugging Face introducing MolmoMotion, a system for language-guided 3D motion forecasting. The work extends the Molmo model family into motion prediction tasks, combining natural language conditioning with 3D spatial reasoning. The post appears to be an announcement or demonstration of the capability, though the body content was not available for detailed review.