Type a name, or just describe what you need. Results blend keyword and meaning-based search. 12 matches, each with an EU availability status.
Research
Simulated-user platform with 8.3 billion persona agents for evaluating personal agents, plus RL environments and SFT data.
Library · Z.ai
Open-source LLM RL post-training framework connecting Megatron training with SGLang rollout, used for Z.ai's GLM models.
Model
Speech recognition model trained for noisy, reverberant and distorted real-world audio, with RL post-training.
Monocular video motion capture that combines flow matching with physics-based RL for plausible 3D human motion.
Research method that retargets human hand-object demonstrations to dexterous robot hands using one multi-reference RL policy.
Open-weights family of agentic coding models (9B to 397B) that learns to generate its own task-specific scaffolds.
Research · Stability AI
Stability AI research method that fine-tunes Qwen-Image-Layered for image layer decomposition using VLM-scored RL.
Library · World Labs
World Labs tooling that turns a single image into an editable 3D environment with meshes, splats, physics and lighting.
Research model for video relighting that jointly generates relit video and per-frame environment maps, no camera poses needed.
Real-time multiplayer world model that generates four-player Rocket League-style gameplay, playable online.
14B autoregressive world model that generates interactive, camera-controlled video worlds in 3 denoising steps.
Research game world model that assigns player or NPC roles per character and generates reactive NPC behavior from rules.
