Nonlinearity as Rank: Generative Low-Rank Adapter with Radial Basis Functions
cs.AI
Submitted: 2026-02-05
Updated: 2026-09-29
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- InternLM2 Technical Report
- BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- DeepSeek-V3 Technical Report
- AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping
- Parameter-Efficient Fine-Tuning with Discrete Fourier Transform
- LoRA+: Efficient Low Rank Adaptation of Large Models
- Efficient Learning With Sine-Activated Low-rank Matrices
- NOLA: Compressing LoRA using Linear Combination of Random Basis
- The Power of Scale for Parameter-Efficient Prompt Tuning
- Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
- Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems
- KAN: Kolmogorov-Arnold Networks
- Decoupled Weight Decay Regularization
- WizardCoder: Empowering Code Large Language Models with Evol-Instruct
- Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
- MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning
- Solving General Arithmetic Word Problems
- SocialIQA: Commonsense Reasoning about Social Interactions
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems