REVIEW 18 cited by
RVT-2: Learning Precise Manipulation from Few Demonstrations
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In this work, we study how to build a robotic system that can solve multiple 3D manipulation tasks given language instructions. To be useful in industrial and household domains, such a system should be capable of learning new tasks with few demonstrations and solving them precisely. Prior works, like PerAct and RVT, have studied this problem, however, they often struggle with tasks requiring high precision. We study how to make them more effective, precise, and fast. Using a combination of architectural and system-level improvements, we propose RVT-2, a multitask 3D manipulation model that is 6X faster in training and 2X faster in inference than its predecessor RVT. RVT-2 achieves a new state-of-the-art on RLBench, improving the success rate from 65% to 82%. RVT-2 is also effective in the real world, where it can learn tasks requiring high precision, like picking up and inserting plugs, with just 10 demonstrations. Visual results, code, and trained model are provided at: https://robotic-view-transformer-2.github.io/.
Forward citations
Cited by 18 Pith papers
-
PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulation
PartInstruct is a new large-scale simulated benchmark with part-level language instructions and training demonstrations; current robot policies achieve at most 31.72% average success on it.
-
Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Models
Aligning a VLA's latent features with instruction-selected target-object tri-views (VAE and VGGT) improves manipulation success, especially under target occlusion, with a compact 345M backbone.
-
Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills
A taxonomy of robot learning on a weights-versus-skills axis, with a five-rung self-improvement ladder whose top cell (feedback plus memory plus search) holds only a few recent systems.
-
RoboInter1.5: A Holistic Intermediate Representation Suite for Embodied World Modeling and Robotic Manipulation
Dense per-frame intermediate representations (traces, masks, grasp poses, subtasks) improve embodied VQA, VLA action generation, and world-model video prediction in the new 230k-episode RoboInter-Data suite.
-
Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentation
Continuous multi-view image-space keypoint trajectories plus per-camera equivariant augmentation beat strong 3D and image baselines on MimicGen and real UR5 tasks.
-
SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation
SeedPolicy introduces self-evolving gated attention to extend the temporal horizon of diffusion policies, yielding 36.8% and 169% relative gains over standard DP on clean and randomized RoboTwin 2.0 tasks.
-
LLaDA-VLA: Vision Language Diffusion Action Models
LLaDA-VLA applies a masked diffusion vision-language model to robot control with localized action-token classification and hierarchical decoding, achieving SOTA success rates on SimplerEnv, CALVIN, and real-robot tasks.
-
RwoR: Generating Robot Demonstrations from Human Hand Collection for Policy Learning without Robot
A generative model and wrist camera turn human hand videos into robot gripper demonstrations that train manipulation policies at success rates close to those trained on real gripper data.
-
LMPVC and Policy Bank: Adaptive voice control for industrial robots with code generating LLMs and reusable Pythonic policies
LMPVC and the Policy Bank let users control an industrial robot by voice, teach it reusable Python policies, and have a local code-generating LLM call those policies automatically.
-
ROSA: Harnessing Robot States for Vision-Language and Action Alignment
ROSA trains a VLA model jointly on expert actions and automatically recorded robot states, improving success rates and generalization, particularly with few demonstrations.
-
GENMANIP: LLM-driven Simulation for Generalizable Instruction-Following Manipulation
GenManip is a benchmark and simulation platform with LLM-generated scene graphs for testing how robot policies generalize to new instructions, layouts, and objects.
-
UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation
UAD distills affordance knowledge from vision-language models and DINOv2 features into a lightweight task-conditioned model that predicts pixel-level manipulation regions and improves few-shot imitation learning gener...
-
Differential Amplifier-Inspired AmpAttention for Multi-View Robotic Manipulation
AmpAttention and RVAF raise multi-view robotic manipulation success and cut training time by suppressing attention noise with a differential-amplifier-style mechanism plus a CMRR loss.
-
QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models
Adding an auxiliary quantized-depth-token prediction task to a VLA policy improves manipulation success rates on LIBERO, Simpler, and real-robot pick-and-place tasks versus the open-pi-zero baseline.
-
Language-Conditioned Open-Vocabulary Mobile Manipulation with Pretrained Models
A robot system that combines GPT-4, vision-language maps, and a CLIPort-style network follows free-form household commands across rooms in simulation, reaching 10.2% average success on unseen tasks and beating two bas...
-
RoboPearls: Editable Video Simulation for Robot Manipulation
RoboPearls is a 3D Gaussian Splatting based framework that edits demonstration videos into varied photorealistic simulations, and training on them improves robot manipulation success rates on RLBench and COLOSSEUM.
-
Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulation
TUDP removes timestep conditioning from diffusion policies and adds an action-discrimination signal to learn a time-unified velocity field, achieving SOTA RLBench success rates (82.6% multi-view, 83.8% single-view) an...
-
SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping
SR3D combines an off-the-shelf single-view 3D reconstruction model with view and keypoint matching to place the reconstructed mesh into the scene, enabling single-view grasping of transparent objects.
Discussion (0). Sign in to comment.