Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

INTACT: A Search-Free JEPA That Maps Intent Directly to Actions

AI By Crimson AI Hugging Face Papers 31 July 2026 · 00:00 18 views
Share: X Telegram

Hugging Face researchers introduce INTACT, an end-to-end JEPA that learns intent-to-action mapping without test-time search, achieving 95.33% direct macro success across four control tasks with 2.9–5.5 ms inference.

INTACT: A Search-Free JEPA That Maps Intent Directly to Actions

Key points

Forward latent world models predict how actions change a scene, but recovering actions for a desired change typically requires expensive test-time search. Researchers from Hugging Face introduce INTACT (INtent-To-ACTion), an end-to-end JEPA that turns action-labeled, reward-free trajectories into a deployable intent-to-action interface.

INTACT learns the missing intent-to-action correspondence end to end. A shared conditional operator maps both realized local transitions and deployable goal intents to their induced action distributions. The two intent instances share the same predictor and action supervision, while using deliberately asymmetric gradient paths. This grounds goal-conditioned control in observed physical transitions without forcing pointwise latent alignment or globally linear dynamics.

After only one training epoch, INTACT achieves 95.33% Direct macro success rate across four visual-control tasks, with zero candidate search and 2.9–5.5 ms inference latency. This reduces planning latency by approximately 300× relative to broad CEM control. INTACT also supports joint four-task training with a shared visual encoder and lightweight task-specific heads.

Optional local verification with CEM centered on the Direct plan reaches 96.86% macro success using only 384 candidate sequences instead of 9,000, reducing sampling by 23.44× while improving pure CEM by 16.00 points. A shared four-task encoder reaches 89.39% E5 Direct macro and improves every task over jointly trained LeWM, while predicted–expert action-family kNN tracks Direct success at r=0.954.

The architecture is isomorphic between local and goal motion-intent backbone-input graphs through an identical four-slot grammar and shared parameters, and between supported intent families through action-law semantics induced by the same predictor. INTACT provides intact transfer from RGB evidence to action-effective latent intent coordinates and from intent families to their corresponding action-law families.

MetricValue
Direct macro success (4 tasks, 1 epoch)95.33%
Inference latency2.9–5.5 ms
Planning latency reduction vs CEM~300×
Local CEM macro success (384 candidates)96.86%
Sampling reduction vs 9,000 candidates23.44×
Shared encoder E5 Direct macro89.39%
Predicted–expert kNN correlationr=0.954
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1