SWAM studies how action learning affects language-video alignment
Authors report 88.10% easy and 61.56% hard RoboTwin success, and 40.00% versus 23.33% on three real tasks.
Stories per day · 30 days
3 RSS
Relatedrobotics3video-diffusion2autonomous-driving1causal-inference1embodied-control1fred1imagination-free1language-video-alignment1latent-variables1model-weights1reinforcement-learning1representation-distillation1robot-control1robotwin1self-distillation1
12 stories, newest first · one card per story
Stories tagged #world-action-models
DreamFree Repurposes Video Diffusion for World Action Models
DreamFree enables real-time robot control at 11Hz without generating future videos.
CausalWAM Separates Action Causes in World Action Models
Sparsity constraint enables causal WAMs to identify action-relevant latent variables, improving closed-loop robotic control efficiency.
OSWAM achieves one-step action generation for driving
OSWAM generates high-quality actions for autonomous driving and control in a single diffusion step using imagination tokens.
FRED improves future video representations for world action models
On tasks shown only in human videos, FRED reaches 50.0% success versus 19.4% for the best rival.
BridgeWAM links video and action experts with latent queries
The 5.06B model reports 98.25% LIBERO success and 28.72% fewer inference FLOPs than Fast-WAM.
Long-WAM: Scaling the Context of World-Action Models
Long-WAM raises robot task success by scaling causal world-action context with autoregressive video pretraining.
AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models
AnyStep-WAM cuts world-action denoising steps by up to 85% while holding RoboTwin success rates.
Rolling-WAM: World Action Models with Rolling Imagination
Rolling-WAM speeds robotic replanning 4.5x by spreading joint denoising across successive cycles.
Rolling-WAM: World Action Models with Rolling Imagination
Rolling-WAM speeds robot replanning 4.5x by staggering joint video-action denoising across cycles.
DeltaWAM: Delta World Action Models for Bimanual Manipulation
DeltaWAM predicts visual deltas and robot actions, raising RoboTwin success while cutting training and inference cost.
Modality-Autoregressive World-Action Models
ModAR autoregressively denoises multiple future modalities (point tracks, DINO features, depth) before predicting actions, beating prior world-action models at all data scales.