Function-Preserving Audits of Visual Weight Readers
cs.AI
Submitted: 2026-11-04
Updated: 2026-11-13
Terminology
Sources
- Git Re-Basin: Merging Models modulo Permutation Symmetries
- SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
- The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks
- DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights
- A Survey of Weight Space Learning: Understanding, Representation, and Generation
- Weight Oracles: Reading Neural Network Weights with Language Models
- Adam: A Method for Stochastic Optimization
- Graph Neural Networks for Learning Equivariant Representations of Neural Networks
- Path-SGD: Path-Normalized Optimization in Deep Neural Networks
- Qwen2.5 Technical Report
- Predicting Neural Network Accuracy from Weights
- Equivariant Polynomial Functional Networks
- Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think
- Graph Metanetworks for Transformer Based Language Models
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