LA-Pose achieves over 10% higher pose accuracy than recent feed-forward methods on Waymo and PandaSet benchmarks by repurposing latent actions from self-supervised inverse-dynamics pretraining while using orders of magnitude less labeled 3D data.
Scaling 4d representations
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
A new evaluation framework using latent diffusion on frozen vision backbones shows video-pretrained models consistently outperform image-based ones in forecasting entire trajectories across abstraction levels.
V-JEPA 2 pre-trained on massive unlabeled video achieves strong results on motion understanding and action anticipation, SOTA video QA at 8B scale, and enables zero-shot robotic planning on Franka arms using only 62 hours of unlabeled robot video.
Systematic empirical comparison of temporal context placement across backbone, PEFT modules, and probes for low-resource video task adaptation on appearance, motion, and dense tasks.
Freezing an image foundation model and training only a recurrent temporal module yields strong temporal performance on video tasks without large-scale video pre-training.
citing papers explorer
-
LA-Pose: Latent Action Pretraining Meets Pose Estimation
LA-Pose achieves over 10% higher pose accuracy than recent feed-forward methods on Waymo and PandaSet benchmarks by repurposing latent actions from self-supervised inverse-dynamics pretraining while using orders of magnitude less labeled 3D data.
-
Frozen Forecasting: A Unified Evaluation
A new evaluation framework using latent diffusion on frozen vision backbones shows video-pretrained models consistently outperform image-based ones in forecasting entire trajectories across abstraction levels.
-
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
V-JEPA 2 pre-trained on massive unlabeled video achieves strong results on motion understanding and action anticipation, SOTA video QA at 8B scale, and enables zero-shot robotic planning on Franka arms using only 62 hours of unlabeled robot video.
-
Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?
Systematic empirical comparison of temporal context placement across backbone, PEFT modules, and probes for low-resource video task adaptation on appearance, motion, and dense tasks.
-
Towards Data-Efficient Video Pre-training with Frozen Image Foundation Models
Freezing an image foundation model and training only a recurrent temporal module yields strong temporal performance on video tasks without large-scale video pre-training.