-
Taming LLMs by Scaling Learning Rates with Gradient Grouping
Paper • 2506.01049 • Published • 40 -
Switch EMA: A Free Lunch for Better Flatness and Sharpness
Paper • 2402.09240 • Published • 5 -
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Paper • 2410.06373 • Published • 36 -
OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
Paper • 2209.04851 • Published • 3
🤝 Open to Collab
Juanxi Tian
Juanxi
AI & ML interests
Efficient AI & Gen AI
Recent Activity
reacted to theirpost with ❤️ 1 day ago
🚀WorldFoundry | Unified World Model Inference & Evaluation Infrastructure
WorldFoundry is an open-source infrastructure that unifies inference and evaluation for generative world models. It supports video generation, interactive worlds, 3D/4D representations, and embodied models through a unified workflow with TUI, CLI, and Studio interfaces. The framework integrates a growing collection of state-of-the-art models and currently includes 58 benchmarks, including VBench, VideoScore, WorldScore, WorldModelBench, Physics-IQ, and T2V-CompBench.
We welcome the community to ⭐ star the repository, submit pull requests, open issues, and contribute new models and benchmarks.
🔗 GitHub：https://github.com/OpenEnvision/WorldFoundry
📖 Project & Docs：https://openenvision.github.io/WorldFoundry reacted to theirpost with 🚀 1 day ago
🚀WorldFoundry | Unified World Model Inference & Evaluation Infrastructure
WorldFoundry is an open-source infrastructure that unifies inference and evaluation for generative world models. It supports video generation, interactive worlds, 3D/4D representations, and embodied models through a unified workflow with TUI, CLI, and Studio interfaces. The framework integrates a growing collection of state-of-the-art models and currently includes 58 benchmarks, including VBench, VideoScore, WorldScore, WorldModelBench, Physics-IQ, and T2V-CompBench.
We welcome the community to ⭐ star the repository, submit pull requests, open issues, and contribute new models and benchmarks.
🔗 GitHub：https://github.com/OpenEnvision/WorldFoundry
📖 Project & Docs：https://openenvision.github.io/WorldFoundry reacted to theirpost with 🤗 1 day ago
🚀WorldFoundry | Unified World Model Inference & Evaluation Infrastructure
WorldFoundry is an open-source infrastructure that unifies inference and evaluation for generative world models. It supports video generation, interactive worlds, 3D/4D representations, and embodied models through a unified workflow with TUI, CLI, and Studio interfaces. The framework integrates a growing collection of state-of-the-art models and currently includes 58 benchmarks, including VBench, VideoScore, WorldScore, WorldModelBench, Physics-IQ, and T2V-CompBench.
We welcome the community to ⭐ star the repository, submit pull requests, open issues, and contribute new models and benchmarks.
🔗 GitHub：https://github.com/OpenEnvision/WorldFoundry
📖 Project & Docs：https://openenvision.github.io/WorldFoundryOrganizations
