Channels - RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data :: FRELIP Discovery

Similar Items: RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data

Quick Look
EvoGround: Self-Evolving Video Agents for Video Temporal Grounding
Quick Look
OmniRobotHome: A Multi-Camera Platform for Real-Time Multiadic Human-Robot Interaction
Quick Look
Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation
Quick Look
Temporally Consistent Object 6D Pose Estimation for Robot Control
Quick Look
StateVLM: A State-Aware Vision-Language Model for Robotic Affordance Reasoning
Quick Look
Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
Quick Look
RoboKA: KAN Informed Multimodal Learning for RoboCall Surveillance System
Quick Look
Task-Aware Scanning Parameter Configuration for Robotic Inspection Using Vision Language Embeddings and Hyperdimensional Computing
Quick Look
Exploring the Limits of End-to-End Feature-Affinity Propagation for Single-Point Supervised Infrared Small Target Detection
Quick Look
LychSim: A Controllable and Interactive Simulation Framework for Vision Research
Quick Look
Reduced-order Neural Modeling with Differentiable Simulation for High-Detail Tactile Perception
Quick Look
Rebalancing gradient to improve self-supervised co-training of depth, odometry and optical flow predictions
Quick Look
MoCoTalk: Multi-Conditional Diffusion with Adaptive Router for Controllable Talking Head Generation
Quick Look
Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration
Quick Look
123D: Unifying Multi-Modal Autonomous Driving Data at Scale
Quick Look
Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
Quick Look
Foundation AI Models for Aerosol Optical Depth Estimation from PACE Satellite Data
Quick Look
Aligning Network Equivariance with Data Symmetry: A Theoretical Framework and Adaptive Approach for Image Restoration
Quick Look
Continuous-tone Simple Points: An $ell_0$-Norm of Cyclic Gradient for Topology-Preserving Data-Driven Image Segmentation
Quick Look
RD-ViT: Recurrent-Depth Vision Transformer for Semantic Segmentation with Reduced Data Dependence Extending the Recurrent-Depth Transformer Architecture to Dense Prediction
Quick Look
Agentic-imodels: Evolving agentic interpretability tools via autoresearch
Quick Look
SkillOS: Learning Skill Curation for Self-Evolving Agents
Quick Look
Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems
Quick Look
ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss