quantitative evaluation
Quantitative evaluation involves using statistical measures and metrics to assess the performance of models, providing objective criteria to compare models against benchmarks and understand their effectiveness.
- 3DOT: Texture Transfer for 3DGS Objects from a Single Reference Image
- Crucible: Quantifying the Potential of Control Algorithms through LLM Agents
- Discrete Spatial Diffusion: Intensity-Preserving Diffusion Modeling
- Free-Lunch Color-Texture Disentanglement for Stylized Image Generation
- GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents
- GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer
- MMCSBench: A Fine-Grained Benchmark for Large Vision-Language Models in Camouflage Scenes
- RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis