Large Language Model
PaCE: Parsimonious Concept Engineering for Large Language Models
Large Language Models (LLMs) are being used for a wide variety of tasks.
PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models
Models (LLMs) can sometimes surpass those annotated by experts, such as journalists, according to human evaluations. However, there is limited research on whether these generic summaries meet the individual needs of ordinary people.
ALI-Agent: Assessing LLMs'Alignment with Human Values via Agent-based Evaluation
ALI-Agent operates through two principal stages: Emulation and Refinement. During the Emulation stage, ALI-Agent automates the generation of realistic test scenarios.
Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression
Transformers learn to approximate second-order optimization methods for ICL.
Membership Inference Attacks against Large Vision-Language Models
We believe that our work can deepen the understanding and methodology of MIAs in the context of VLLMs.
TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration
Unfortunately, these models are "isolated agents" with heterogeneous
AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models
However, most APO methods are trained assuming a fixed text-to-image model, which is impractical given the emergence of new models.
