OpenAI is rolling out the full, limited-release version of GPT-5.5-Cyber—a specialized AI model that outperforms its ...
Abstract: In the field of hyperspectral unmixing (HU), to decompose mixed pixels into pure substances and their corresponding fractional abundances, the (hyper)graph constrained (D) nonnegative matrix ...
Abstract: Deep learning models based on the independent identically distributed assumption perform poorly once the assumption cannot be satisfied under two challenges of synthetic aperture radar (SAR) ...
Research project on LLM activation steering for MBTI personality. The goal is to steer Gemma-2-2b's expressed personality along the four MBTI axes (E/I, S/N, T/F, J/P) by selecting Gemma Scope SAE ...
Official repository of the paper Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees. All experiments were conducted using a single Tesla V100 GPU unit. The torch ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results