Results for "ungrounded output"

Methods to set starting weights to preserve signal/gradient scales across layers.

Nonlinear functions enabling networks to approximate complex mappings; ReLU variants dominate modern DL.

Techniques that stabilize and speed training by normalizing activations; LayerNorm is common in Transformers.

Randomly zeroing activations during training to reduce co-adaptation and overfitting.

Stepwise reasoning patterns that can improve multi-step tasks; often handled implicitly or summarized for safety/privacy.

An RNN variant using gates to mitigate vanishing gradients and capture longer context.

Architecture that retrieves relevant documents (e.g., from a vector DB) and conditions generation on them to reduce hallucinations.

Updating a pretrained model’s weights on task-specific data to improve performance or adapt style/behavior.

A preference-based training method optimizing policies directly from pairwise comparisons without explicit RL loops.

Model trained to predict human preferences (or utility) for candidate outputs; used in RLHF-style pipelines.

Converts logits to probabilities by exponentiation and normalization; common in classification and LMs.

Attacks that infer whether specific records were in training data, or reconstruct sensitive training examples.

Coordinating tools, models, and steps (retrieval, calls, validation) to deliver reliable end-to-end behavior.

Generating speech audio from text, with control over prosody, speaker identity, and style.

Neural networks can approximate any continuous function under certain conditions.

Allows gradients to bypass layers, enabling very deep networks.

The range of functions a model can represent.

Allows model to attend to information from different subspaces simultaneously.

Routes inputs to subsets of parameters for scalable capacity.

Models trained to decide when to call tools.

Diffusion model trained to remove noise step by step.

Diffusion performed in latent space for efficiency.

Model that compresses input into latent space and reconstructs it.

Two-network setup where generator fools a discriminator.

Generator produces limited variety of outputs.

Pixel-wise classification of image regions.

Generates audio waveforms from spectrograms.

Attention between different modalities.

CNNs applied to time series.

Model execution path in production.