2 papers
cs.CR2026
How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE
Yi Shi, Tanyu Chen, Kai Shen
Directional ablation removes an aligned language model's ability to refuse by projecting a single "refusal direction" out of the weights that write the residual stream. It needs no…
cs.SD2026
FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning
Tanyu Chen, Tairan Chen, Kai Shen +4
Recent end-to-end spoken dialogue systems leverage speech tokenizers and neural audio codecs to enable LLMs to operate directly on discrete speech representations. However, these m…