Tag
Dream4ACT introduces a shared visual action interface ("action views") rendered via URDF-based forward kinematics to enable joint video-action modeling across multiple robot embodiments, combining observations and actions in a single diffusion world model with masked flow matching. It achieves 88.98% success on RoboTwin 2.0 and 65.66 on TriWorldBench using a training-free URDF-constrained recovery mechanism for executable actions.
This paper proposes Intention Distillation (INDI) to distill behavior intent into the action decoder of Vision-Language-Action models, improving performance on benchmarks like SimplerEnv-Bridge and real-world tasks.
This paper introduces Complementary Action Modeling (CAM), a task that identifies or generates procedural counterparts of automotive maintenance instructions by modifying the action phrase while preserving context. Using a German automotive dataset, the authors examine candidate matching and controlled Seq2Seq generation to model these complementary instructions.
RepWAM introduces a world action modeling approach using representation visual-action tokenizers, aiming to learn unified visual and action representations for planning and control.