Glyph: An Interpretability Engine for AI-Driven Scientific Discovery from Clinical Data
cs.AI
Submitted: 2026-11-06
Updated: 2026-11-18
Code: https://github.com/StanfordMIMI/Glyph
Project page: https://stanfordmimi.github.io/Glyph-research
Terminology
Sources
- Accelerating scientific discovery with Co-Scientist
- Scaling and evaluating sparse autoencoders
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- Learning Multi-Level Features with Matryoshka Sparse Autoencoders
- Double/Debiased Machine Learning for Logistic Partially Linear Model
- Insights into a radiology-specialised multimodal large language model with sparse autoencoders
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