Education
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
Machine unlearning is a promising solution for efficiently removing specific knowledge by post hoc modifying models.
MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures
Evaluating large language models (LLMs) is challenging.
Recasting Continual Learning as Sequence Modeling
That is, we propose to formulate continual learning as a sequence modeling problem, allowing advanced sequence models to be utilized for continual learning.
Extracting Training Data from Molecular Pre-trained Models
This work, for the first time, explores the risks of extracting private training molecular data from molecular pre-trained models. This task is nontrivial as the molecular pre-trained models are non-generative and exhibit a diversity of model architectures, which differs significantly from language and image models.
Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network
Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real haze distributions and the scarcity of paired real-world data.
Dueling Over Dessert, Mastering the Art of Repeated Cake Cutting
We consider two versions: sequential, where Bob observes Alice's cut