Projects on DR. PEIKE LI

Gemma

Wed, 01 Apr 2026 00:00:00 +0000

Gemma is Google’s family of open models built from the same research and technology behind the Gemini models. Gemma 4 features advanced reasoning with multi-step planning, native multimodal understanding (video, image, and audio), agentic capabilities with function-calling and structured JSON output, and 256K context windows — all under the Apache 2.0 license. Models range from edge-optimized E2B/E4B for mobile and IoT to 26B MoE and 31B dense variants for research and production workloads.

VEO

Sun, 01 Mar 2026 00:00:00 +0000

Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.

JEN-1

Thu, 01 Jun 2023 00:00:00 +0000

JEN-1 is a cutting-edge AI-powered music generation framework that redefines how music is created, customized, and composed. It combines state-of-the-art diffusion models with advanced learning techniques to enable high-fidelity text-to-music generation, personalized musical concept adaptation, and controllable multi-track composition. JEN-1 excels in producing expressive music from text prompts, capturing unique musical styles from reference tracks, and facilitating human-AI co-composition workflows. With innovations like omnidirectional diffusion modeling, pivotal parameter tuning, and curriculum training for multi-track synthesis, JEN-1 sets a new benchmark for interactive and customizable AI-driven music creation. Experience the future of AI-driven music creation at JEN Music AI https://www.jenmusic.ai/.