SkyJEPA learns long-horizon latent dynamics for quadrotors via JEPA plus a physics prober, enabling zero-shot sim-to-real control with sampling-based MPC and automated sim data generation.
Temporal straightening for latent planning
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 11roles
background 2polarities
background 2representative citing papers
Neural events compress event camera streams into fewer informative tokens via discrete asynchronous autoencoders, achieving on-par or better performance on detection and classification with 2x lower event rate.
IWR improves CRL sample efficiency and performance in interaction-rich manipulation by interaction-aware resampling that preserves mode boundaries, yielding 19.8% average gains and a real-world air-hockey agent.
JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampling than pixel diffusion baselines.
STEP embeds progressive time series into a manifold between orthogonal prototypes so that polar angle tracks irreversible state progression and radius tracks mode via self-supervised contrastive learning.
Slot-MPC learns slot representations to build a differentiable object-centric dynamics model that supports efficient gradient-based MPC for robotic manipulation in novel situations.
RC-aux corrects spatiotemporal mismatch in reconstruction-free latent world models by adding multi-horizon prediction and reachability supervision, improving planning performance on goal-conditioned pixel-control tasks.
The work derives the optimal ratio of dynamics-to-reward samples that minimizes a bound on return error and characterizes the tradeoff between noisy but cheap rewards versus accurate but expensive ones in imagination-based policy optimization.
A vision-language-aligned world model turns visuomotor MPC into a language-following planner that reaches 87% success on 288 unseen semantic tasks where standard VLAs drop to 22%.
An empirical audit of 22 JEPA-style training auxiliaries on Llama-3.2-1B fine-tuning for regex generation finds no statistically significant task improvement after multiple-testing correction, even when auxiliaries visibly alter hidden-state geometry.
citing papers explorer
-
SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors
SkyJEPA learns long-horizon latent dynamics for quadrotors via JEPA plus a physics prober, enabling zero-shot sim-to-real control with sampling-based MPC and automated sim data generation.
-
Neural Events: Discrete Asynchronous Autoencoders for Event-Based Vision
Neural events compress event camera streams into fewer informative tokens via discrete asynchronous autoencoders, achieving on-par or better performance on detection and classification with 2x lower event rate.
-
Learning Object Manipulation from Scratch via Contrastive Interaction
IWR improves CRL sample efficiency and performance in interaction-rich manipulation by interaction-aware resampling that preserves mode boundaries, yielding 19.8% average gains and a real-world air-hockey agent.
-
JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning
JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampling than pixel diffusion baselines.
-
STEP: Learning STructured Embeddings for Progressive Time Series
STEP embeds progressive time series into a manifold between orthogonal prototypes so that polar angle tracks irreversible state progression and radius tracks mode via self-supervised contrastive learning.
-
Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations
Slot-MPC learns slot representations to build a differentiable object-centric dynamics model that supports efficient gradient-based MPC for robotic manipulation in novel situations.
-
Predictive but Not Plannable: RC-aux for Latent World Models
RC-aux corrects spatiotemporal mismatch in reconstruction-free latent world models by adding multi-horizon prediction and reachability supervision, improving planning performance on goal-conditioned pixel-control tasks.
-
On Training in Imagination
The work derives the optimal ratio of dynamics-to-reward samples that minimizes a bound on return error and characterizes the tradeoff between noisy but cheap rewards versus accurate but expensive ones in imagination-based policy optimization.