Evaluating Small Object Understanding in Multimodal LLMs
Discover how SOUBench benchmarks multimodal large language models' ability to understand small objects and improve performance with SOU-Train.
NeuroAPS-Net: Efficient Alzheimer’s Classification with Point Clouds
Discover NeuroAPS-Net, a lightweight model using neuro-anatomical point clouds for accurate and efficient Alzheimer's disease classification from MRI data.
MTServe: Fast Serving for Generative Recommendation Models
Discover MTServe's hierarchical caching to boost generative recommendation models with faster inference and optimized GPU memory usage.
Preventing Context-Fragmented Violations in Multi-Agent AI
Discover how Distributed Sentinel and STT Protocol prevent context-fragmented violations in multi-agent systems, enhancing AI security and compliance.
SketchVLM: Advanced Vision-Language Model for Image Annotation
Discover SketchVLM, a training-free vision-language model that annotates images to enhance visual reasoning and user interaction.