Linking Rapid Learning to Compositional Structure in Neural Networks: Evidence from Additive Analogies in Meta-Learned Parameter Spaces
cs.LG, cs.CL
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- DeepSeek-V3 Technical Report
- The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
- Relational inductive biases, deep learning, and graph networks
- Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
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