MVI-Bench supplies the first taxonomy and dataset focused on misleading visual inputs to measure LVLM robustness, with tests on 18 models revealing clear weaknesses.
Sail-vl2 technical report
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 5roles
baseline 1polarities
baseline 1representative citing papers
VISTA-Bench shows vision-language models degrade on visualized text in images compared to equivalent pure text, with larger gaps under increased perceptual difficulty.
POINTS-Long is a dual-mode multimodal large language model that uses dynamic visual token scaling to retain 97.7-99.7% accuracy on long-form tasks with 1/40 to 1/10th the tokens and supports streaming via detachable KV-cache.
TPSNet combines CLIP text prompts and phase features as dual priors to deliver better semantic supervision and domain alignment than pseudo-label clustering in unsupervised cross-domain image retrieval.
OmniFysics is an omni-modal network using a dynamic physical data engine and evolutive tuning to improve performance on multimodal benchmarks and physics-oriented tasks.
citing papers explorer
-
MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs
MVI-Bench supplies the first taxonomy and dataset focused on misleading visual inputs to measure LVLM robustness, with tests on 18 models revealing clear weaknesses.
-
VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?
VISTA-Bench shows vision-language models degrade on visualized text in images compared to equivalent pure text, with larger gaps under increased perceptual difficulty.
-
POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs
POINTS-Long is a dual-mode multimodal large language model that uses dynamic visual token scaling to retain 97.7-99.7% accuracy on long-form tasks with 1/40 to 1/10th the tokens and supports streaming via detachable KV-cache.
-
Text-Phase Synergy Network with Dual Priors for Unsupervised Cross-Domain Image Retrieval
TPSNet combines CLIP text prompts and phase features as dual priors to deliver better semantic supervision and domain alignment than pseudo-label clustering in unsupervised cross-domain image retrieval.
-
OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization
OmniFysics is an omni-modal network using a dynamic physical data engine and evolutive tuning to improve performance on multimodal benchmarks and physics-oriented tasks.