Stochastic Dynamics of Generative AI: From Autoregressive Models to Interacting LLM Networks and Neural SDEs
cs.LG, cs.SY, eess.SP, eess.SY
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/aditj/llm_network_tmlr
Terminology
Sources
- LLMs as High-Dimensional Nonlinear Autoregressive Models with Attention: Training, Alignment and Inference
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Emergence of Preferential Attachment and Glass-Ceiling Effects in Autonomous Networks of LLMs
- Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
- Universal approximation property of neural stochastic differential equations
- Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions
- Efficient Neural SDE Training using Wiener-Space Cubature
- A Comparison of Automatic Differentiation and Continuous Sensitivity Analysis for Derivatives of Differential Equation Solutions
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