MuirBench is a new benchmark showing that top multimodal LLMs struggle with robust multi-image understanding, with GPT-4o at 68% and open-source models below 33% accuracy.
Visual spatial reasoning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3representative citing papers
VILASR integrates visual drawing operations with reasoning in LVLMs via cold-start synthetic training, reflective rejection sampling, and reinforcement learning, yielding an 18.4% average gain on spatial reasoning benchmarks.
MiniGPT-v2 adds unique task identifiers to a large language model so one system can perform image description, visual question answering, and visual grounding after three-stage training.
citing papers explorer
-
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
MuirBench is a new benchmark showing that top multimodal LLMs struggle with robust multi-image understanding, with GPT-4o at 68% and open-source models below 33% accuracy.
-
Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
VILASR integrates visual drawing operations with reasoning in LVLMs via cold-start synthetic training, reflective rejection sampling, and reinforcement learning, yielding an 18.4% average gain on spatial reasoning benchmarks.
-
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
MiniGPT-v2 adds unique task identifiers to a large language model so one system can perform image description, visual question answering, and visual grounding after three-stage training.