finetuning
The process of taking a pre-trained model and further training it on a specific task or dataset to adapt its parameters, improving performance for that particular application.
- Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Expansion
- Activated LoRA: Fine-tuned LLMs for Intrinsics
- Ascent Fails to Forget
- Composition and Alignment of Diffusion Models using Constrained Learning
- Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models
- Curvature Tuning: Provable Training-free Model Steering From a Single Parameter
- DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering
- Distillation Robustifies Unlearning
- EuroSpeech: A Multilingual Speech Corpus
- FlySearch: Exploring how vision-language models explore
- From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning
- Multi-Scale Finetuning for Encoder-based Time Series Foundation Models
- Pay Attention to Small Weights
- RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks
- Shape it Up! Restoring LLM Safety during Finetuning
- Towards A Translative Model of Sperm Whale Vocalization
- VLMs can Aggregate Scattered Training Patches
- Value Gradient Guidance for Flow Matching Alignment
- VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models