Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought — mentioned by gglon

Sun, 10 Aug 2025 20:34:16 GMT

> At the time of writing, the highest-ranking non-purely-transformer-based model on the LM Arena is Jamba, which is a transformer–state space model hybrid, at rank 96.) Tencent's hunyuan-turbos, another hybrid, is currently ranked at 22. https://arxiv.org/abs/2505.15431

Paper and discussion history. A mention is not an endorsement.

Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought · HackerPapers discussions

Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought — mentioned by gglon