Multimodal Diffusion Forcing trains a diffusion model on partially masked multimodal robot trajectories to learn temporal and cross-modal dependencies for forceful manipulation.
Spot: Se (3) pose trajectory diffusion for object-centric manipulation
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.RO 7verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
UMA treats object motion and robot actions as co-evolving variables under a masked generative objective with hindsight relabeling and contrastive disentanglement to support multi-task pretraining and deployment across heterogeneous robot data.
AFFORD2ACT distills a minimal set of affordance-guided 2D keypoints from text and a single image to train a 38-dimensional gated transformer policy that achieves 82% success on unseen objects and scenes.
RIGVid shows that filtered AI-generated videos can serve as effective supervision for complex robotic manipulation tasks without any real demonstrations.
UniVLA trains cross-embodiment vision-language-action policies from unlabeled videos via a latent action model in DINO space, beating OpenVLA on benchmarks with 1/20th pretraining compute and 1/10th downstream data.
HumanEgo reports 92.5% average success on four real robot tasks using only 15-30 minutes of human video per task and zero robot data, with zero-shot transfer to new robots and cameras.
FunCanon introduces functional object canonicalization with VLM affordances to create pose-aware action primitives for generalizable imitation learning in robotic manipulation.
citing papers explorer
-
Unified Motion-Action Modeling for Heterogeneous Robot Learning
UMA treats object motion and robot actions as co-evolving variables under a masked generative objective with hindsight relabeling and contrastive disentanglement to support multi-task pretraining and deployment across heterogeneous robot data.
-
HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos
HumanEgo reports 92.5% average success on four real robot tasks using only 15-30 minutes of human video per task and zero robot data, with zero-shot transfer to new robots and cameras.