fine-tuning strategies
Fine-tuning strategies involve adjusting a pre-trained model on a new, typically smaller dataset to improve its performance on a specific task. This is especially common in transfer learning in natural language processing and computer vision.
- Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning
- FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models
- LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
- Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning
- MolVision: Molecular Property Prediction with Vision Language Models
- Spatial Understanding from Videos: Structured Prompts Meet Simulation Data