Results for "graph search"

Extension of convolution to graph domains using adjacency structure.

Choosing step size along gradient direction.

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

Search algorithm for generation that keeps top-k partial sequences; can improve likelihood but reduce diversity.

GNN using attention to weight neighbor contributions dynamically.

Directed acyclic graph encoding causal relationships.

Retrieval based on embedding similarity rather than keyword overlap, capturing paraphrases and related concepts.

Optimal pathfinding algorithm.

Directly optimizing control policies.

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

Graphs containing multiple node or edge types with different semantics.

Structured graph encoding facts as entity–relation–entity triples.

Finding routes from start to goal.

A datastore optimized for similarity search over embeddings, enabling semantic retrieval at scale.

Graphical model expressing factorization of a probability distribution.

Computing collision-free trajectories.

Configuration choices not learned directly (or not typically learned) that govern training or architecture.

Methods for breaking goals into steps; can be classical (A*, STRIPS) or LLM-driven with tool calls.

Tracking where data came from and how it was transformed; key for debugging and compliance.

Probabilistic graphical model for structured prediction.

A hidden variable influences both cause and effect, biasing naive estimates of causal impact.

Agents communicate via shared state.

Assigning labels per pixel (semantic) or per instance (instance segmentation) to map object boundaries.

Internal representation of environment layout.

Compromising AI systems via libraries, models, or datasets.

Distributed agents producing emergent intelligence.

Raw model outputs before converting to probabilities; manipulated during decoding and calibration.

Number of steps considered in planning.

Agent reasoning about future outcomes.

Direction of steepest ascent of a function.