Search papers, labs, and topics across Lattice.
12
0
9
10
RoboInter1.5 reimagines intermediate representations as a powerful interface that enhances robotic reasoning and execution, bridging the gap between low-level actions and high-level world dynamics.
Coordinated scaling of Behavior Foundation Models can enhance humanoid robot control performance, achieving up to 82% error reduction in real-world tasks.
Achieving a 78.3% success rate in real-world mobile manipulation, this framework bridges the reality gap with zero-shot transferability to unseen tasks.
Cortex outperforms traditional models by enabling zero-shot execution of complex long-horizon tasks, bridging the gap between high-level planning and low-level execution.
By preserving the semantics of pretrained models while achieving superior compositional generalization, InternVLA-A1.5 redefines how robots can learn and execute complex tasks.
Imagined visual evidence can dramatically enhance spatial reasoning in VLMs, leading to significant performance gains on complex reasoning tasks.
Robots can now learn flexible, geometry-free interactions with objects directly from video, sidestepping the need for laborious 3D modeling or complex retargeting.
Decoupling high-level VLM planning from low-level diffusion-based control lets robots reason like foundation models *and* execute precisely, outperforming end-to-end approaches in complex manipulation tasks.
By decoupling visual and motor information during pretraining, FutureVLA unlocks more effective visuomotor prediction for vision-language-action models, boosting performance without modifying downstream architectures.
Unlock human-like dexterity in robotic manipulation by combining RL-assisted teleoperation with a novel VLA architecture that leverages force and tactile feedback.
Bimanual robots can now achieve robust dexterous grasping in the real world, thanks to a massive 20M-frame synthetic dataset and a simple attention-based policy that transfers surprisingly well.
Stop guessing about action spaces for robot manipulation: a massive empirical study reveals that predicting delta actions boosts performance, while joint vs. task space offers a stability vs. generalization tradeoff.
