Weight-Space Programming of Policies and Their Verification via Model Checking
cs.AI, cs.LG
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/LAVA-LAB/COOL-MC
Terminology
Sources
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Kimi K3: Open Frontier Intelligence
- A Survey of Weight Space Learning: Understanding, Representation, and Generation
- HyperNetworks
- Learning to Learn with Generative Models of Neural Network Checkpoints
- Text-to-LoRA: Instant Transformer Adaption
- Editing Models with Task Arithmetic
- Weight-Space Programming for Improving Image-Restoration Diffusion Models: Technical Conjectures and a Recursive Improvement Loop
- Function-Preserving Audits of Visual Weight Readers
- Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC
- Verifying Memoryless Sequential Decision-making of Large Language Models
- Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications
- Safety-Oriented Pruning and Interpretation of Reinforcement Learning Policies
- Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents