model adaptation
Model adaptation involves modifying an existing machine learning model to better fit new tasks or domains, often using techniques such as fine-tuning on new datasets, domain adaptation strategies, or transfer learning.
- A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics
- BrainEC-LLM: Brain Effective Connectivity Estimation by Multiscale Mixing LLM
- Democratizing Clinical Risk Prediction with Cross-Cohort Cross-Modal Knowledge Transfer
- DevFD : Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces
- EMLoC: Emulator-based Memory-efficient Fine-tuning with LoRA Correction
- Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data
- FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing
- Gated Integration of Low-Rank Adaptation for Continual Learning of Large Language Models
- Linearization Explains Fine-Tuning in Large Language Models
- LoRA vs Full Fine-tuning: An Illusion of Equivalence
- LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades
- Time-Masked Transformers with Lightweight Test-Time Adaptation for Neural Speech Decoding
- VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models