baseline models
Baseline models are simple or standard models against which new algorithms are compared to measure significance and improvement in performance for a specific task.
- Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integration
- ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization
- IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios
- Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
- OmniBench: Towards The Future of Universal Omni-Language Models
- Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients
- Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards