LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection
cs.LG, stat.ML
Submitted: 2026-05-12
Updated: 2026-11-10
Code: https://github.com/Kris-camp/loft
Terminology
Sources
- LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters
- Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method
- Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey
- DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
- LoRA: Low-Rank Adaptation of Large Language Models
- PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
- HOFT: Householder Orthogonal Fine-tuning
- Orthogonal Finetuning Made Scalable
- DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation
- GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
- A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis