Search papers, labs, and topics across Lattice.
LAC enables humanoid robots to maintain compliant control in the face of external forces, revolutionizing how they interact with dynamic environments.
Agents using ParallelWorld can efficiently evaluate multiple future trajectories, leading to superior decision-making in complex environments.
Typed spatial readouts can elevate robotic execution success rates by over 50% while significantly reducing processing time.
Command-inconsistent memory can lead to a 15.6% increase in collision rates during autonomous driving, but MomADv2 effectively filters this noise for safer long-horizon planning.
Achieving a 99.8% success rate in reconnecting initially disconnected convex regions transforms the feasibility of GCS-based motion planning.
DECOWAM achieves a 21.7% reduction in action prediction error while maintaining robust task performance, showcasing the power of embodiment-aware factorization in mobile manipulation.
Policies may succeed in tasks but still violate deformation tolerances, revealing a critical gap in current evaluation methods for deformable-object manipulation.
Separating spatial and temporal modeling in action recognition leads to significant performance gains, challenging the effectiveness of existing implicit coupling methods.
HODAgent's unified architecture enables humanoid robots to adaptively manage service tasks in real-time, achieving up to 92% success rates on physical platforms.
Selectively routed stereo evidence boosts humanoid VLA control success rates, achieving 100% grasp success even under severe occlusion.
A non-invasive framework that enhances pretrained generative policies with force control, achieving remarkable improvements in contact stability and execution speed.
Guiding dexterous grasp generation with arm-aware constraints boosts feasibility in complex environments, outperforming traditional methods reliant on hand-centric models.
Closed-loop learning in embodied agents can lead to a staggering 11.1x speedup in inference while achieving record performance on complex tasks.
SparkVLA redefines task execution in hierarchical VLA systems, achieving over 30% improvement in success rates by integrating stop and action length decisions into a single ranking process.
Vision-based tactile sensors could revolutionize robotic interaction by providing high-resolution tactile data that enhances perception and manipulation capabilities.
HumanScore reveals that traditional kinematic metrics overlook critical failures in humanoid motion tracking, such as unstable support and incorrect contacts.
Robots can now predict not just immediate actions but also the next stages of complex tasks, leading to more efficient manipulation strategies.
JEPA-WAM achieves a remarkable 79.2% on LIBERO-Plus without large-scale pretraining, setting a new benchmark for efficient robot control.
SLIM achieves state-of-the-art performance in robot manipulation with just 0.5B parameters, outperforming larger models while slashing GPU memory usage and inference latency.
OnEvoMemory allows robots to evolve their memory in real-time, leading to improved task performance and reduced redundancy in long-horizon manipulation tasks.
SkillMemo transforms robotic manipulation by enabling models to leverage reusable skill structures, leading to unprecedented compositional generalization in complex tasks.
GeniWorld achieves robust zero-shot generalization in robotic manipulation, outperforming traditional models even with minimal training data.
Trajectory scoring in aerial navigation can be revolutionized by focusing on unexplainable prediction discrepancies, leading to more robust and efficient UAV navigation.
RTCF boosts the success of frozen VLA policies by leveraging past experiences without the need for retraining or extra GPU power.
PhyAI achieves up to 4.65x speedup in Physical AI tasks by unifying disparate inference processes into a single, efficient runtime.
Synthesizing realistic 3D hand-object interactions from just a single image and text instruction could revolutionize AR/VR applications by enabling seamless integration of dynamic human behaviors.
ChainVLA achieves a remarkable 62.8% success rate on long-horizon manipulation tasks by seamlessly chaining vision-language-action queries through a unified execution state.
Tactile supervision can boost robot manipulation success rates by over 37% compared to traditional visual-only models.
Achieving a remarkable 23% increase in navigation success rates across diverse robotic embodiments, X-NavDP redefines the potential of diffusion policies in complex environments.
Shifting the focus from photorealistic rendering to dynamic visual changes, DC-WAM enhances robot policy performance by 20% in challenging environments.
Legacy data is only useful for upgraded robots after reaching a critical competence threshold, revealing a surprising three-phase pattern in transfer learning.
Evolving Cache Schedules can slash action-generation time by over 8x without sacrificing performance, revolutionizing real-time deployment of diffusion policies.
Adaptive routing of perception priors allows PerceptDrive to generate optimal driving trajectories in real-time without complex post-processing.
HCPG-Flow boosts robot manipulation success rates by over 9% by intelligently guiding action selection based on task progress rather than just end-effector positions.
Force-based memory enables VLA models to achieve over 80% success in complex manipulation tasks, outperforming traditional memory methods with minimal computational cost.
Achieving state-of-the-art multi-view hand-object interaction synthesis, HarmoHOI harmonizes 2D appearance and 3D motion in real-time.
Coordinated scaling of Behavior Foundation Models can enhance humanoid robot control performance, achieving up to 82% error reduction in real-world tasks.
DRIFT achieves near real-time trajectory planning with 89.6 PDMS and 90.4 EPDMS by efficiently aggregating multiple driving behavior proposals without requiring extensive quality labels.
LLMs can misinterpret benign text as physically dangerous actions, but a new probing method achieves over 99% accuracy in identifying these risks without relying on explicit unsafe keywords.
Atomic movements enable a new level of control and coherence in dance generation, transforming how machines interpret and produce choreography.
Action-only decoding in GigaWorld-Policy-0.5 slashes inference latency to 85 ms, revolutionizing real-time robot control efficiency.
Language corrections in PhysClaw-0 not only enhance robot autonomy but also boost success rates by over 35% while slashing human oversight time.
Continuous tracking of dynamic object evidence can transform MLLMs' ability to understand and interact with dynamic environments.
Automated synthesis can transform the personalization of animatronic faces, enabling rapid adaptation to diverse facial geometries with minimal manual intervention.
TeleDexter achieves a remarkable 75% success rate in dexterous teleoperation tasks, where existing systems fail, showcasing a leap towards human-level control in robotic manipulation.
Humanoid robots can learn to roller-skate with unprecedented precision by leveraging adversarial motion priors, achieving remarkable gait quality and control.
The Temporal Ratio reveals how attention shifts between future and present frames can predict a model's ability to generalize compositional tasks in video-action contexts.
Achieving a staggering 98.75% success rate in dexterous manipulation tasks, LAMP redefines how we approach real-world learning in robotics.
Outperforming previous methods, UniLM-Nav achieves zero-shot last-mile navigation by effectively integrating multimodal reasoning and task context.
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.
