DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale Paper • 2609.22978 • Published 4 days ago • 2
Cactus Needle Collection Automation Foundation Models For Tiny Devices • 3 items • Updated 5 days ago • 9
Primed Hybrid Models Collection Collection Collection of primed Hybrid language models for Reasoning and Instruction following. • 9 items • Updated Apr 9 • 8
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 6 days ago • 170
pplx-pii Collection PII-TRACE (Tracing Recurring PII Across Conversational Exchanges) benchmark and models • 6 items • Updated about 12 hours ago • 3
ACE Collection Ai2 Climate Emulator (ACE) is a family of fast ML models that simulate weather and climate variability over time scales from hours to centuries. • 14 items • Updated 4 days ago • 18
Xiaomi-Robotics-U0 Collection Unified embodied synthesis model that bridges foundation image generation and embodied world modeling • 5 items • Updated 14 days ago • 12
Spark-X2.5 Collection Spark-X2.5 is a compact, general-purpose language model for conversation, writing, translation, reasoning, coding, tool use, and agentic workflows. • 10 items • Updated 7 days ago • 44