Search Results for author:
Found 5 papers, 5 papers with code
Curvature Tuning: Provable Training-free Model Steering From a Single Parameter
Additionally, we apply CT to ReLU-based Swin-T/S, improving their generalization on nine downstream datasets by 2. 43\%/3. 33\%.
Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization
However, relying solely on such feedback can be limited when the adjustments made in response to this feedback are either too small or fluctuate irregularly, potentially slowing down or even stalling the optimization process.
DROJ: A Prompt-Driven Attack against Large Language Models
Here, we introduce a novel approach, Directed Rrepresentation Optimization Jailbreak (DROJ), which optimizes jailbreak prompts at the embedding level to shift the hidden representations of harmful queries towards directions that are more likely to elicit affirmative responses from the model.
JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models
The rapid evolution of artificial intelligence (AI) through developments in Large Language Models (LLMs) and Vision-Language Models (VLMs) has brought significant advancements across various technological domains.
Robustar: Interactive Toolbox Supporting Precise Data Annotation for Robust Vision Learning
We introduce the initial release of our software Robustar, which aims to improve the robustness of vision classification machine learning models through a data-driven perspective.
