When Do Biological Reasoning Models Use Their Biological Inputs?
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/mims-harvard/bio-mirage
Project page: https://zitniklab.hms.harvard.edu/biomirage
Sources
- MIRAGE: The Illusion of Visual Understanding
- How Post-Training Shapes Biological Reasoning Models
- The Platonic Representation Hypothesis
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks