Qwen3 Voice Embedding Collection Standalone ECAPA-TDNN x-vector speaker encoders extracted from Qwen3-TTS. 1024-dim (0.6B) and 2048-dim (1.7B). • 4 items • Updated 3 days ago • 24
view article Article DeepMath: A lightweight math reasoning Agent with smolagents +1 Dec 4, 2025 • 40
view article Article Community Evals: Because we're done trusting black-box leaderboards over the community +5 22 days ago • 80
view article Article Welcome EmbeddingGemma, Google's new efficient embedding model +4 Sep 4, 2025 • 273
MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding Paper • 2505.20298 • Published May 26, 2025 • 9
SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models Paper • 2506.04180 • Published Jun 4, 2025 • 34
MangaliCa Train / Eval Dataset 🐗 Collection Collection of MangaliCa's pre-training datasets • 8 items • Updated May 22, 2025 • 2