TriAttention: Efficient Long Reasoning with Trigonometric KV Compression Paper • 2604.04921 • Published 3 days ago • 82
SecureCode v2.0: A Production-Grade Dataset for Training Security-Aware Code Generation Models Paper • 2512.18542 • Published Dec 20, 2025 • 5
MegaVul: A C/C++ Vulnerability Dataset with Comprehensive Code Representation Paper • 2406.12415 • Published Jun 18, 2024 • 1
view article Article Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective Jan 27 • 70
DeepSeek R1 (All Versions) Collection DeepSeek-R1-0528 is here! The most powerful reasoning open LLM, available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 37 items • Updated 5 days ago • 266