robotic manipulation
Robotic manipulation involves the use of robots to perform tasks that require physical interaction with objects in their environment, such as grasping, moving, and placing items, often requiring advanced perception and control strategies.
- $\textit{HiMaCon:}$ Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data
- $\textit{Hyper-GoalNet}$: Goal-Conditioned Manipulation Policy Learning with HyperNetworks
- 3D Equivariant Visuomotor Policy Learning via Spherical Projection
- DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation
- EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data
- Enhancing LLM Planning for Robotics Manipulation through Hierarchical Procedural Knowledge Graphs
- Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization
- Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning
- ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation
- FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
- GoalLadder: Incremental Goal Discovery with Vision-Language Models
- HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning
- Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination
- InstructFlow: Adaptive Symbolic Constraint-Guided Code Generation for Long-Horizon Planning
- PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning
- Predictive Preference Learning from Human Interventions
- RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation
- RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills
- SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding
- SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding
- Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following
- Token Bottleneck: One Token to Remember Dynamics
- Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising
- VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching