The paper creates FISD, a controlled benchmark for composed image retrieval that removes query ambiguity via generative models, and proposes a multi-round agentic evaluation to assess models in interactive settings.
Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5representative citing papers
DBAC is a new directional metric for bias amplification in image captions that is less sensitive to sentence encoders and more accurate than LIC, validated on COCO gender and race attributes.
SSL-R1 reformulates visual SSL tasks into verifiable puzzles to supply rewards for RL post-training of MLLMs, yielding gains on multimodal benchmarks without external supervision.
R-CoV is a six-step region-aware chain-of-verification technique that elicits coordinate and description outputs from LVLMs themselves to detect and reduce object hallucinations without external models or retraining.
Decoupled Guidance (DeGu) uses two independent guidance streams plus spatial mixing to disentangle subject fidelity from context editability in text-to-image personalization methods.
citing papers explorer
-
A Sanity Check on Composed Image Retrieval
The paper creates FISD, a controlled benchmark for composed image retrieval that removes query ambiguity via generative models, and proposes a multi-round agentic evaluation to assess models in interactive settings.
-
A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions
DBAC is a new directional metric for bias amplification in image captions that is less sensitive to sentence encoders and more accurate than LIC, validated on COCO gender and race attributes.
-
SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models
SSL-R1 reformulates visual SSL tasks into verifiable puzzles to supply rewards for RL post-training of MLLMs, yielding gains on multimodal benchmarks without external supervision.
-
R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs
R-CoV is a six-step region-aware chain-of-verification technique that elicits coordinate and description outputs from LVLMs themselves to detect and reduce object hallucinations without external models or retraining.
-
Decoupled Guidance: Disentangling Subject and Context Pathways in Text-to-Image Personalization
Decoupled Guidance (DeGu) uses two independent guidance streams plus spatial mixing to disentangle subject fidelity from context editability in text-to-image personalization methods.