Prior Action Control Causally Alters Language-Model Plasticity
cs.LG, q-bio.NC
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- On Warm-Starting Neural Network Training
- Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
- Sharp Minima Can Generalize For Deep Nets
- Neural Tangent Kernel: Convergence and Generalization in Neural Networks
- Adam: A Method for Stochastic Optimization
- Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
- Understanding plasticity in neural networks
- A Kernel-Based View of Language Model Fine-Tuning
- Path-SGD: Path-Normalized Optimization in Deep Neural Networks
- The Difficulty of Passive Learning in Deep Reinforcement Learning
- RL's Razor: Why Online Reinforcement Learning Forgets Less
- Qwen3 Technical Report
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