arXiv
DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training
We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physi...
HABERLER
Tüm Haberler
Yapay zekâ dünyasından son haberler, derinlikli analizler, teknik incelemeler.
115Yazı
1Yazar
5.2KOkuma · 30g
5Bu Hafta
arXiv
Never Look Back: Understanding Persistence in 3D Object Memory from Egocentric Videos
As we move through the world and carry out everyday tasks, we encounter objects that may become rele...
arXiv
Long-WAM: Scaling the Context of World-Action Models
Real-time robot control demands enough visual history to infer motion and task progress, but process...
arXiv
Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models
Vision-language-action models (VLAs) are strikingly sensitive to instruction phrasing and do not inh...
arXiv
RoboJEPA: Scaling Robotic Latent World Models
Latent world models have shown a remarkable ability to predict future states and to plan in the real...
arXiv
QF3: Fast Flow RL with Filtered Q-Gradients
Flow policies have become a standard policy class for learning robot behaviors from demonstrations, ...
arXiv
DepthWorld: 3D World Model for Robot Manipulation
World models offer a data-driven alternative to traditional simulators for robotics, with applicatio...
arXiv
VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning
Self-improving policies continually expose new failure patterns, changing what their judges must be ...
arXiv
InterMimicGen: Scaling Humanoid Loco-Manipulation through Self-Evolving Motion Imitation
Captured human-object interactions provide rich supervision for humanoid loco-manipulation, but they...
arXiv
Recursive Video In-Context Learning for Agentic Robot
LLM agents that orchestrate frozen vision-language-action (VLA) policies improve across episodes thr...
arXiv
TAPDreamer: Transferable Adversarial Patches for World Action Models
World models learn to predict how their environment will evolve, making them an important foundation...
arXiv
H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning
Long-horizon planning with latent world models requires reasoning across timescales and levels of ab...
arXiv
Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis
This paper examines the role of Novel View Synthesis (NVS) in geometric representation learning.
arXiv
EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras
Inspired by human vision, we introduce a framework using active gaze to enable fine-grained bimanual...
arXiv
Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents
Building reliable robot capabilities across diverse tasks requires substantial human effort to devel...