Results for "multi-type nodes"
Diffusion model trained to remove noise step by step.
Model that compresses input into latent space and reconstructs it.
Generates audio waveforms from spectrograms.
Sequential data indexed by time.
Simple agent responding directly to inputs.
Agent reasoning about future outcomes.
Devices measuring physical quantities (vision, lidar, force, IMU, etc.).
Predicting case success probabilities.
Credit models with interpretable logic.
Finding mathematical equations from data.
Truthful bidding is optimal strategy.
AI capable of performing most intellectual tasks humans can.
Training one model on multiple tasks simultaneously to improve generalization through shared structure.
Converts logits to probabilities by exponentiation and normalization; common in classification and LMs.
Architecture based on self-attention and feedforward layers; foundation of modern LLMs and many multimodal models.
Attacks that infer whether specific records were in training data, or reconstruct sensitive training examples.
Methods to protect model/data during inference (e.g., trusted execution environments) from operators/attackers.
Transformer applied to image patches.
Recovering 3D structure from images.
Identifying speakers in audio.
System that independently pursues goals over time.
Decomposing goals into sub-tasks.
Distributed agents producing emergent intelligence.
Agents communicate via shared state.
Temporary reasoning space (often hidden).
Optimizes future actions using a model of dynamics.
No agent benefits from unilateral deviation.
No agent can improve without hurting another.
System-level behavior arising from interactions.
Groups adopting extreme positions.