Model techniques map
Techniquesmodel architecturenormalization & residual

specific method · filed under model architecture

Gated Residual

A residual method that widens the stream into parallel branches and uses dynamic gates to control information read from and written to those branches.

Also called Gated Residual (GR), Gated residual connections.

sources
6
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 8

Documented in

Evidence

8 spans quoted from the sources, strongest treatment first.

The original single residual stream is expanded into 4 parallel branches, allowing the model to decide dynamically, based on the current content, how much information to read from each branch and how much to write back.

coreunclearin Qwen3.8-Flash-NextQwen

The gated residual "modulates information flowing through widened residual streams via an element-wise, data-dependent read gate and per-branch scalar write gate"

coremodel architecturein Qwen3.8-Flash-NextQwen

We describe the concrete design of GR below.

coreunclearin Qwen3.8-Flash-NextQwen

the gate decides how that capacity is spent, while also supplying the rescaling that keeps training stable

coreunclearin Qwen3.8-Flash-NextQwen

GR supplies a rescaling that markedly improves training stability

coremodel architecturein Qwen3.8-Flash-NextQwen

four residual branches dynamically control cross-layer reads and writes.

coremodel architecturein Qwen3.8-Flash-NextQwen

Gated Residual modulates information flowing through widened residual streams via an element-wise, data-dependent read gate and a per-branch scalar write gate.

coreunclearin Qwen3.8-Flash-NextQwen

Gated Residual (GR) widens the residual stream into 4 branches and controls reads and writes with a dynamic gate

coremodel architecturein Qwen3.8-Flash-NextQwen

Filed alongside

Other methods under model architecture :: normalization & residual.