A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts
cs.AI, astro-ph.IM
Submitted: 2026-08-23
Updated: 2026-08-23
Terminology
Sources
- Discovering Symbolic Models from Deep Learning with Inductive Biases
- The DESI Survey Validation: Results from Visual Inspection of Bright Galaxies, Luminous Red Galaxies, and Emission Line Galaxies
- A ConvNet for the 2020s
- Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
- Walrus: A Cross-Domain Foundation Model for Continuum Dynamics
- Locating and Editing Factual Associations in GPT
- The Linear Representation Hypothesis and the Geometry of Large Language Models
- AION-1: Omnimodal Foundation Model for Astronomical Sciences
- Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
- Vector-quantized Image Modeling with Improved VQGAN
- Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
- Interpreting CLIP with Hierarchical Sparse Autoencoders
- Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
Related papers
- 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
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection