Search papers, labs, and topics across Lattice.
16
0
12
17
Leveraging SMT conflict counts, SMTrap achieves unprecedented denial-of-service effects against large reasoning models without the need for model feedback or GPU resources.
A unified policy enables humanoid robots to robustly interact with complex environments, achieving record-breaking success rates in dynamic terrain and command scenarios.
GigaBrain-0.7 achieves unprecedented task adaptability and completion rates, outperforming previous models in both home and industrial settings.
Current AI-generated videos that mislead viewers are also the most challenging for existing detection systems to identify, revealing a critical vulnerability in misinformation defenses.
Integration of diverse robot policies can be streamlined from hours to minutes, revolutionizing how we deploy and evaluate robotic systems.
StereoFlow shatters the regression-to-mean bias in stereo matching, achieving state-of-the-art results even in the most ambiguous scenarios.
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.
HALO-WA boosts robotic manipulation success rates from 26.4% to 87.1% by effectively adapting to real-world errors in just over an hour of training.
Evaluator quality for robotic policies hinges more on long-horizon consistency than on short-term visual fidelity, reshaping our approach to world model design.
Disentangling dynamics from visual synthesis allows robotic systems to generate high-quality videos up to four times faster without losing critical interaction details.
STORM recovers up to 63.3% accuracy in visual state space models by enforcing spatial awareness in token reduction, transforming how we approach model efficiency.
R2RDreamer achieves spatial generalization improvements in manipulation tasks by leveraging 3D-aware data augmentation without the pitfalls of complex scene setups or sim-to-real gaps.
Treating raw visual images as action representations revolutionizes embodied control, outperforming traditional methods in accuracy and generalization.
Robots can now better assemble boxes in the real world thanks to a video-generative value model that anticipates future states, moving beyond static snapshots for more reliable task progress assessment.
Get simulation-ready assets for robotics and graphics in under a second, without any manual annotation, using a new feedforward approach that jointly learns physical attributes and 3D Gaussian Splatting reconstruction from a single video.
