From the 1 of 10 linked papers with an AI index.
10 papers
Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning
Dongyue Li, Zhenshuo Zhang, Minxuan Duan +2
The paper proposes branching neural networks that automatically partition multiple algorithmic reasoning tasks into a hierarchical tree structure, enabling efficient multitask lear…
WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points
Dongyue Li, Zechun Liu, Kai Yi +6
Quantization-aware training (QAT) is widely adopted to quantize language models by training full-precision weights using gradients from the quantized model. The main bottleneck is…
Not All Pixels Are Equal: Confidence-Guided Attention for Feature Matching
Dongyue Li
Semi-dense feature matching methods have been significantly advanced by leveraging attention mechanisms to extract discriminative descriptors. However, most existing approaches tre…
Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimation
Ziniu Zhang, Zhenshuo Zhang, Dongyue Li +3
This paper introduces an algorithm to select demonstration examples for in-context learning of a query set. Given a set of examples, how can we quickly select out of to…
Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis
Abhinav Nippani, Dongyue Li, Haotian Ju +2
We consider the problem of traffic accident analysis on a road network based on road network connections and traffic volume. Previous works have designed various deep-learning meth…
Split Matching for Inductive Zero-shot Semantic Segmentation
Jialei Chen, Xu Zheng, Dongyue Li +6
Zero-shot Semantic Segmentation (ZSS) aims to segment categories that are not annotated during training. While fine-tuning vision-language models has achieved promising results, th…