An Approach to Hinton's Mother-Child Proposal: Neural Networks Learning and Preserving Care in a Finite World
cs.LG, cs.AI, cs.NE
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- Distilling the Knowledge in a Neural Network
- Towards Understanding Sycophancy in Language Models
- Supervising strong learners by amplifying weak experts
- Concrete Problems in AI Safety
- Gradient Episodic Memory for Continual Learning
- Efficient Lifelong Learning with A-GEM
- Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors
- Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer
- Subliminal Learning Is Steering Vector Distillation
- Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation
- On Mitigation of Subliminal Learning in Large Language Models
- ROSARL: Reward-Only Safe Reinforcement Learning
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