Continuous Function

Knowledge Graph

Ask the map what to learn next.

Use the graph as a research-learning instrument: map papers to concepts, inspect typed edges, find prerequisite repairs, and attach equations, labs, claims, and discussion to the exact idea.

100 nodes336 edges7 topic groups
Map a PaperOpen Serving ModuleSearch AtlasBrowse Domains
A learner question moving along one highlighted path through a larger concept graph.
RouteKeep the learner's question visible while the graph chooses the next concept.

Graph Reading

A graph is useful only when it explains the next move.

The point is not to admire complexity; it is to find the shortest honest path from confusion to a concept you can test.
LearnerFind the missing prerequisite.

When a page feels too hard, use incoming edges to locate the idea that should be repaired first.

Try a bridge
ResearcherSpot reusable mechanisms.

Follow shared neighborhoods to see when optimization, probability, or representation ideas are doing the same job.

Search mechanisms
ProfessorTurn edges into a lecture route.

Use the graph to choose the minimum sequence that makes a derivation or demo feel earned.

Open pillars

Learning Route

Ask the graph what to learn next.

Pick a question and the graph turns it into prerequisites, equations, labs, and honest links between ideas. When you arrive from the mapper, your current paper route stays visible.

Answer

I know transformers and Adam. What do I need for Mamba-2?

Repair the long-context pressure first, then cross the bridge from attention memory to fixed-state recurrence.

Search this routePreview only; your saved route is unchanged.
01Attentionknown transformer mechanism02Efficient Attentionwhy KV memory hurts03Long Contextsystems pressure04Linear Transformationsstate update language
05SSM Hybridsrecurrence bridgeplanned
06Parallel Scanimplementation trickplanned
07State-Space Dualitypaper-specific bridgeplanned

Route Engine

Compute the honest next path.

Choose what the learner already knows and a frontier target. The engine runs a weighted shortest-path query over typed concept edges, then names the first missing repair instead of hand-waving across the gap.

Known concepts

Research target

6 nodesRepair Efficient Attention next
weighted cost5.50
Preview only; changing chips does not overwrite your saved route.
01Attentionweighted copying02Efficient Attentionmemory pressure03Long Contextstress regime04SSM Hybridsfixed-state sequence models
05Parallel Scantrainable recurrenceplanned
06State-Space DualityMamba-style bridgeplanned
prerequisiteAttention -> Efficient Attention

You need Q/K/V weighted copying before cache and memory optimizations are meaningful.

invented to fixEfficient Attention -> Long Context

Long context exposes the cost of storing and repeatedly reading all prior keys and values.

same pressureLong Context -> SSM Hybrids

Fixed-state sequence models become attractive when KV memory grows with sequence length.

implementation dependencySSM Hybrids -> Parallel Scan

Recurrent-looking models need parallel sequence computation to train at scale.

paper-specific bridgeParallel Scan -> State-Space Duality

Modern Mamba-style papers often connect recurrence, convolution, and attention-like views.

Typed Edges

Why the route is honest

prerequisiteAttention -> Efficient Attention

You need weighted copying before memory optimization makes sense.

invented to fixEfficient Attention -> Long Context

Long contexts expose the cost of storing and reading all prior keys and values.

same pressureLong Context -> SSM Hybrids

Fixed-size states are attractive because KV memory grows with sequence length.

implementation dependencySSM Hybrids -> Parallel Scan

Training recurrent-looking models at scale requires parallelizable sequence computation.

Learning Objects

What anchors this route

paperMamba-2 / state-space duality

mapper candidate

equationh_t = A(x_t)h_{t-1} + B(x_t)x_t

needs explainer

toy-experimentfixed state vs KV memory simulator

planned

claimrecurrence, attention, or control theory?

object question

Research Room

Resolve the route object before moving on

Pick a paper, equation, lab, claim, or misconception. The selected object becomes the saved route focus for the next companion prompt.
papermapper candidate

Mamba-2 / state-space duality

Anchored question

What should we inspect about Mamba-2 / state-space duality before treating this route object as understood?

Local action draftDraft unavailableNeeds a canonical object key
Local action draft

This object needs a content object key before local action drafts can attach to it.

No local draft saved.
Evidence to inspect
  • Paper metadata, abstract claim, and any pasted source spans
  • Mapped concepts, equations, and prerequisite repairs
  • Which claims are source-checked and which remain local-preview only
What would resolve this
  • The paper contribution is mapped to a concrete mechanism
  • Unverified author, date, benchmark, and novelty claims are separated from learning claims
  • The next concept or lab action is specific enough to resume later
Grounded AI handoff

I am working in Continuous Function's research reading room. Object: paper - Mamba-2 / state-space duality Context: mapper candidate Anchor id: paper/graph/mamba/mamba-state-space-duality Open question: What should we inspect about Mamba-2 / state-space duality before treating this route object as understood? Evidence to inspect: - Paper metadata, abstract claim, and any pasted source spans - Mapped concepts, equations, and prerequisite repairs - Which claims are source-checked and which remain local-preview only What would resolve this: - The paper contribution is mapped to a concrete mechanism - Unverified author, date, benchmark, and novelty claims are separated from learning claims - The next concept or lab action is specific enough to resume later Answer as a careful research tutor: stay source-grounded, separate verified evidence from assumptions, name the relevant math objects, and end with one next action.

paper/graph/mamba/mamba-state-space-duality