HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs Paper • 2605.28398 • Published May 27 • 15
🚀 Qwen-MTP Collection ⚡ MTP (Multi Token Prediction) speculative decoding enables models like Qwen3.6 to have ~1.4-2.2x faster generation with no change in accuracy. • 9 items • Updated Jun 29 • 36