EmbeddingGemma 2: Unified and Efficient Multimodal Representations Paper • 2610.37364 • Published 15 days ago • 36
Running Featured 369 Kokoro Text-to-Speech (WebGPU) 🗣 369 High-quality speech synthesis powered by Kokoro TTS
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding Paper • 2410.17434 • Published Oct 22, 2024 • 27
Running Agents 1.53k Big Code Models Leaderboard 📈 1.53k Explore code model leaderboard and submit evaluations