Can an LLM Actually Reason and Program about Neural Network's Weights or is it just memorization on steroids? Exploring "Weight-Space Programming"
cs.LG, cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/anadim/AdderBoard
Terminology
Sources
- Refusal in Language Models Is Mediated by a Single Direction
- DeepSat - A Learning framework for Satellite Imagery
- Mechanistic Interpretability for AI Safety -- A Review
- Extracting Training Data from Large Language Models
- Quantifying Memorization Across Neural Language Models
- Deep Learning for Classical Japanese Literature
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- Learning to Interpret Weight Differences in Language Models
- HyperNetworks
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Weight Oracles: Reading Neural Network Weights with Language Models
- Language Models (Mostly) Know What They Know
- Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
- Adam: A Method for Stochastic Optimization
- Dataset Inference: Ownership Resolution in Machine Learning
- Fine-Tuning Language Models with Just Forward Passes
- Locating and Editing Factual Associations in GPT
- Mass-Editing Memory in a Transformer
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Learning to Learn with Generative Models of Neural Network Checkpoints
Related papers
- 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
- (Mis)generalization of Helpful-Only Fine-tuning