Cite
Notes
Only stored in your browser.
Attribution
Promote, Suppress, Iterate: How Language Models Answer One-to-Many Factual Queries
arXiv 2025
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
arXiv 2024
Contrastive Instruction Tuning
from 3 papers
Fei Wang
James Y. Huang
Muhao Chen
Wenxuan Zhou
Aram Galstyan
Chaowei Xiao
Chunyuan Li
Dan Roth
Fan Yin
Hoifung Poon