visual perception
The capability of AI systems to interpret and understand visual information from the environment, mimicking human sensory and cognitive processes.
- AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark
- Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
- Multi-step Visual Reasoning with Visual Tokens Scaling and Verification
- NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
- Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
- Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start
- The Underappreciated Power of Vision Models for Graph Structural Understanding
- UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?
- ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
- When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding