Results for "demonstration-based"

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

GNN framework where nodes iteratively exchange and aggregate messages from neighbors.

Extension of convolution to graph domains using adjacency structure.

Diffusion model trained to remove noise step by step.

GNN using attention to weight neighbor contributions dynamically.

Assigning category labels to images.

Pixel-level separation of individual object instances.

Joint vision-language model aligning images and text.

Pixel motion estimation between frames.

Predicting future values from past observations.

Optimal estimator for linear dynamic systems.

Repeating temporal patterns.

Maintaining two environments for instant rollback.

System that independently pursues goals over time.

Using production outcomes to improve models.

Interleaving reasoning and tool use.

Agent reasoning about future outcomes.

Sum of independent variables converges to normal distribution.

Updated belief after observing data.

Belief before observing data.

Optimization under uncertainty.

Multiple examples included in prompt.

Assigning a role or identity to the model.

Explicit output constraints (format, tone).

Using markers to isolate context segments.

Asking model to review and improve output.

Temporary reasoning space (often hidden).

Differences between training and inference conditions.

Model relies on irrelevant signals.

Probabilities do not reflect true correctness.