Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning Paper • 2605.30039 • Published May 29 • 21
ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World Paper • 2605.15081 • Published May 14 • 11
Beyond Retrieval: A Multitask Benchmark and Model for Code Search Paper • 2605.04615 • Published May 6 • 24
QuitoBench: A High-Quality Open Time Series Forecasting Benchmark Paper • 2603.26017 • Published Mar 27 • 31
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World Paper • 2603.19223 • Published Mar 19 • 39