Search Results for author:
Found 8 papers, 3 papers with code
A Framework to Implement 1+N Multi-task Fine-tuning Pattern in LLMs Using the CGC-LORA Algorithm
In practice, there are two prevailing ways, in which the adaptation can be achieved: (i) Multiple Independent Models: Pre-trained LLMs are fine-tuned a few times independently using the corresponding training samples from each task.
AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking
Specifically, we adopt a multiple pairwise ranking loss which trains the user model to capture the similarity orders between the implicitly augmented view, the explicitly augmented view, and views from other users.
G2PTL: A Pre-trained Model for Delivery Address and its Applications in Logistics System
How to effectively encode the delivery address is a core task to boost the performance of downstream tasks in the logistics system.
HSE: Hybrid Species Embedding for Deep Metric Learning
Deep metric learning is crucial for finding an embedding function that can generalize to training and testing data, including unknown test classes.
Siamese Encoder-based Spatial-Temporal Mixer for Growth Trend Prediction of Lung Nodules on CT Scans
In the management of lung nodules, we are desirable to predict nodule evolution in terms of its diameter variation on Computed Tomography (CT) scans and then provide a follow-up recommendation according to the predicted result of the growing trend of the nodule.
Experimental quantum adversarial learning with programmable superconducting qubits
Our results reveal experimentally a crucial vulnerability aspect of quantum learning systems under adversarial scenarios and demonstrate an effective defense strategy against adversarial attacks, which provide a valuable guide for quantum artificial intelligence applications with both near-term and future quantum devices.
PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic
In this setting with multiple and constrained goals, this paper discovers that a probabilistic strategic parameter regime can achieve better value compared to the standard regime of finding a single deterministic parameter.
Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting
Spatial-temporal network data forecasting is of great importance in a huge amount of applications for traffic management and urban planning.
Ranked #3 on
Traffic Prediction
on BJTaxi
