2 papers
cs.CR2026
Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse Autoencoders
Yizhe Zeng, Chenxu Niu, Wei Zhang +7
Backdoor attacks pose a serious threat to large language models (LLMs), but existing defenses remain fragmented, failing to pro?vide unified defense against both dirty-label and cl…
cs.CL2026
On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability
Zihan Qiu, Zekun Wang, Xiao Li +33
We describe the architecture and ablations of Qwen3.8-Flash-Next, a sparse mixture-of-experts model with 125B parameters, 6B activated per token, and additional 51B parameters of n…