2 papers
cs.LG2026
Behavioral Steering in a 35B MoE Language Model via SAE-Decoded Probe Vectors: One Agency Axis, Not Five Traits
Jia Qing Yap
We train nine sparse autoencoders (SAEs) on the residual stream of Qwen 3.5-35B-A3B, a 35-billion-parameter Mixture-of-Experts model with a hybrid GatedDeltaNet/attention architect…
cs.CV2025
INFELM: In-depth Fairness Evaluation of Large Text-To-Image Models
Di Jin, Xing Liu, Yu Liu +7
The rapid development of large language models (LLMs) and large vision models (LVMs) have propelled the evolution of multi-modal AI systems, which have demonstrated the remarkable…