Parallel Complex Diffusion for Scalable Time Series Generation Paper • 2602.17706 • Published Feb 10 • 8
ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World Paper • 2605.15081 • Published 16 days ago • 11
Beyond Retrieval: A Multitask Benchmark and Model for Code Search Paper • 2605.04615 • Published 24 days ago • 23
TingIS: Real-time Risk Event Discovery from Noisy Customer Incidents at Enterprise Scale Paper • 2604.21889 • Published Apr 23 • 12
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 • 33
LLM as Graph Kernel: Rethinking Message Passing on Text-Rich Graphs Paper • 2603.14937 • Published Mar 16
Paths of A Million People: Extracting Life Trajectories from Wikipedia Paper • 2406.00032 • Published May 25, 2024
C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling Paper • 2512.21332 • Published Dec 24, 2025 • 17
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data Paper • 2510.02294 • Published Oct 2, 2025 • 48
Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions Paper • 2410.06577 • Published Oct 9, 2024 • 14