AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Joint-Embedding Predictive Learning of Latent Market States in U.S. Equities

Simon Mahns, Randall Balestriero, Mido Assran

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Equivariant and disentangled latent representations

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use JEPA latent prediction instead of MAE reconstruction (ablation)market-state embedding · kNN retrieval, structure descriptorsR2: 0.25 -> 0.34Improved
use JEPA instead of MAE (ablation)market-state embedding · kNN retrieval, PC1 shareR2: 0.12 -> 0.29Improved
use JEPA instead of MAE (ablation)market-state embedding · kNN retrieval, direction descriptorsR2: 0.04 -> 0.05No clear effect
use structured contiguous-time masking instead of random i.i.d. masking (ablation)JEPA · kNN retrieval, direction descriptorsSpearman rho: 0.19 -> 0.14Improved
use structured masking instead of random i.i.d. masking (ablation)JEPA · kNN retrieval, structure descriptorsSpearman rho: 0.55 -> 0.56No clear effect
keep explicit volatility input channels (ablation)JEPA · Mantel geometry alignmentMantel rho: 0.32 -> 0.35Improved
keep explicit volatility input channels (ablation)JEPA · Recovery prediction (eff rank up)delta AUC: +0.14 -> +0.24Improved
add JEPA embedding to geometry-scalar logistic regressionlogistic regression · Recovery prediction (eff rank up)ROC-AUC: 0.690 -> 0.800Improved
add JEPA embedding to geometry scalars for stress-onset predictionlogistic regression · Stress-onset predictiondelta AUC: +0.11, +0.02No clear effect
compare JEPA with volatility-only representation for news alignmentJEPA · GDELT news alignment W=63 (train+val)Delta(W): 0.0024 -> 0.0053Improved
remove explicit volatility channels for news alignment (ablation)JEPA · GDELT news alignment W=63 (train+val)Delta(W): 0.0053 -> 0.0080No clear effect
evaluate FOMC announcement daysembedding displacement · Embedding displacementCohen's d: d = 0.06, p = .63No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy