3 papers
cs.CL2026
When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models
Ziyu Liu, Tao Li, Tianjie Ni +5
Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token level and lack deeper semantic…
cs.CL2026
Continuous Latent Diffusion Language Model
Hongcan Guo, Qinyu Zhao, Yian Zhao +8
Large language models have achieved remarkable success under the autoregressive paradigm, yet high-quality text generation need not be tied to a fixed left-to-right order. Existing…
cs.LG2025
ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models
Chenyang Song, Xu Han, Zhengyan Zhang +8
Activation sparsity refers to the existence of considerable weakly-contributed elements among activation outputs. As a prevalent property of the models using the ReLU activation fu…