Industry
Fetch and Forge: Efficient Dataset Condensation for Object Detection Ding Qi1 Jian Li
It is crucial for accelerating network training and reducing data storage requirements.
Optimal Transport-based Labor-free Text Prompt Modeling for Sketch Re-identification
Specifically, multiple target attributes are flexibly obtained by a pre-trained visual question answering (VQA) model.
Autoregressive Policy Optimization for Constrained Allocation Tasks
Continuous allocation tasks are a class of problems where an agent needs to distribute a limited amount of resources over a set of entities at each time step.
Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlists
Our findings reveal that even small collectives (controlling less than 0.01% of the training data) can achieve up to
STL: Still Tricky Logic (for System Validation, Even When Showing Y our Work) Isabelle Hurley
Previous work showed that despite claims of interpretability, humans are unable to use formal specifications presented in a variety of ways to validate even simple robot behaviors.
Mixture of Experts Meets Prompt-Based Continual Learning Minh Le3 An Nguyen 2 Huy Nguyen 1 Trang Nguyen
However, current AI models often fail to retain this ability.