AutoRubric-T2I learns and selects explicit rubrics from preference pairs to guide VLM judges, producing high-quality interpretable rewards for T2I alignment with far less data than traditional Bradley-Terry models.
Alon Jacovi and Yoav Goldberg
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
other 2
citation-polarity summary
roles
other 1polarities
unclear 1representative citing papers
GAIA benchmark shows humans at 92% accuracy on simple real-world questions far outperform current AI systems at 15%, proposing this gap as a key milestone for general AI.
Safety-aligned T2I diffusion models exhibit semantic collapse in text embeddings causing TIFA drops; SAGE regularization restores structured utility while retaining safety.
QEVA is a new reference-free evaluation metric for narrative video summarization that uses multimodal question answering to measure coverage, factuality, and chronology, achieving higher correlation with human judgments than prior methods on the introduced MLVU(VS)-Eval benchmark.
The Faithful-First RPA framework improves perceptual faithfulness in multimodal LLMs by up to 24% via step-wise supervision and faithfulness-aware actions without reducing task accuracy.
BLINK benchmark shows multimodal LLMs reach only 45-51 percent accuracy on core visual perception tasks where humans achieve 95 percent, indicating these abilities have not emerged.
Case studies with blind UK residents and people from Kerala and Tamil Nadu demonstrate that community input at the systematization stage produces culturally grounded definitions of appropriateness for text-to-image model outputs.
citing papers explorer
-
AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment
AutoRubric-T2I learns and selects explicit rubrics from preference pairs to guide VLM judges, producing high-quality interpretable rewards for T2I alignment with far less data than traditional Bradley-Terry models.
-
GAIA: a benchmark for General AI Assistants
GAIA benchmark shows humans at 92% accuracy on simple real-world questions far outperform current AI systems at 15%, proposing this gap as a key milestone for general AI.
-
The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models
Safety-aligned T2I diffusion models exhibit semantic collapse in text embeddings causing TIFA drops; SAGE regularization restores structured utility while retaining safety.
-
QEVA: A Reference-Free Evaluation Metric for Narrative Video Summarization with Multimodal Question Answering
QEVA is a new reference-free evaluation metric for narrative video summarization that uses multimodal question answering to measure coverage, factuality, and chronology, achieving higher correlation with human judgments than prior methods on the introduced MLVU(VS)-Eval benchmark.
-
Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs
The Faithful-First RPA framework improves perceptual faithfulness in multimodal LLMs by up to 24% via step-wise supervision and faithfulness-aware actions without reducing task accuracy.
-
BLINK: Multimodal Large Language Models Can See but Not Perceive
BLINK benchmark shows multimodal LLMs reach only 45-51 percent accuracy on core visual perception tasks where humans achieve 95 percent, indicating these abilities have not emerged.
-
Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics
Case studies with blind UK residents and people from Kerala and Tamil Nadu demonstrate that community input at the systematization stage produces culturally grounded definitions of appropriateness for text-to-image model outputs.