Search Results for author:
Found 12 papers, 9 papers with code
Data-Centric AI in the Age of Large Language Models
This position paper proposes a data-centric viewpoint of AI research, focusing on large language models (LLMs).
Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
The increasing complexity of foundational models underscores the necessity for explainability, particularly for fine-tuning, the most widely used training method for adapting models to downstream tasks.
Cross-Domain Feature Augmentation for Domain Generalization
Existing methods focus on learning invariance across domains to enhance model robustness, and data augmentation has been widely used to learn invariant predictors, with most methods performing augmentation in the input space.
Understanding Domain Generalization: A Noise Robustness Perspective
Despite the rapid development of machine learning algorithms for domain generalization (DG), there is no clear empirical evidence that the existing DG algorithms outperform the classic empirical risk minimization (ERM) across standard benchmarks.
On Orderings of Probability Vectors and Unsupervised Performance Estimation
We conduct numerous experiments on well-known NLP data sets and rigorously explore the performance of different score functions.
Uncovering Main Causalities for Long-tailed Information Extraction
Information Extraction (IE) aims to extract structural information from unstructured texts.
Interventional Video Grounding with Dual Contrastive Learning
2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations.
Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices
De novo peptide sequencing is the key technology for finding novel peptides from mass spectra.
Counterfactual Thinking for Long-tailed Information Extraction
However, in practice, the long-tailed and imbalanced data may lead to severe bias issues for deep learning models, due to very few training instances available for the tail classes.
End-to-End Neural Context Reconstruction in Chinese Dialogue
We tackle the problem of context reconstruction in Chinese dialogue, where the task is to replace pronouns, zero pronouns, and other referring expressions with their referent nouns so that sentences can be processed in isolation without context.
DeepNovoV2: Better de novo peptide sequencing with deep learning
Personalized cancer vaccines are envisioned as the next generation rational cancer immunotherapy.
Deep learning enables de novo peptide sequencing from data-independent-acquisition mass spectrometry
We present DeepNovo-DIA, a de novo peptide-sequencing method for data-independent acquisition (DIA) mass spectrometry data.
