Search Results for author:
Found 7 papers, 5 papers with code
If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions
EX2 uses reinforcement learning to align a large language model with VLM preferences and generates descriptions that incorporate the important features for the VLM.
LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons
We show that conditioning on bilingual lexicons is the key component of LexC-Gen. LexC-Gen is also practical -- it only needs a single GPU to generate data at scale.
Low-Resource Languages Jailbreak GPT-4
AI safety training and red-teaming of large language models (LLMs) are measures to mitigate the generation of unsafe content.
Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning
We find that (1) unexplored prompt tuning strategies that iteratively refine pseudolabels consistently improve CLIP accuracy, by 19. 5 points in semi-supervised learning, by 28. 4 points in transductive zero-shot learning, and by 15. 2 points in unsupervised learning, and (2) unlike conventional semi-supervised pseudolabeling, which exacerbates model biases toward classes with higher-quality pseudolabels, prompt tuning leads to a more equitable distribution of per-class accuracy.
Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes
We develop the first non-trivial lower bound on the worst-case error of the best map from attributes to classes for this setting, even with perfect attribute detectors.
TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary Data
Machine learning practitioners often have access to a spectrum of data: labeled data for the target task (which is often limited), unlabeled data, and auxiliary data, the many available labeled datasets for other tasks.
Principal Fairness: Removing Bias via Projections
Reducing hidden bias in the data and ensuring fairness in algorithmic data analysis has recently received significant attention.
