Results for "shortcut learning"

Detecting unauthorized model outputs or data leaks.

Neural networks that operate on graph-structured data by propagating information along edges.

Graphs containing multiple node or edge types with different semantics.

Extension of convolution to graph domains using adjacency structure.

Probabilistic graphical model for structured prediction.

GNN using attention to weight neighbor contributions dynamically.

Graphical model expressing factorization of a probability distribution.

Diffusion performed in latent space for efficiency.

Model that compresses input into latent space and reconstructs it.

Exact likelihood generative models using invertible transforms.

Combining signals from multiple modalities.

Generating human-like speech from text.

Changing speaker characteristics while preserving content.

Maps audio signals to linguistic units.

Identifying speakers in audio.

Generates audio waveforms from spectrograms.

Model execution path in production.

Maintaining two environments for instant rollback.

Shift in feature distribution over time.

System that independently pursues goals over time.

Number of steps considered in planning.

Simple agent responding directly to inputs.

Increasing model capacity via compute.

Cost to run models in production.

Cost of model training.

Competitive advantage from proprietary models/data.

Models whose weights are publicly available.

Models accessible only via service APIs.

Set of vectors closed under addition and scalar multiplication.

Decomposes a matrix into orthogonal components; used in embeddings and compression.