Search papers, labs, and topics across Lattice.
13
0
10
2
Future tactile states can be predicted more effectively from intermediate action features, transforming how we approach tactile supervision in robotic manipulation.
Action-only decoding in GigaWorld-Policy-0.5 slashes inference latency to 85 ms, revolutionizing real-time robot control efficiency.
Evaluator quality for robotic policies hinges more on long-horizon consistency than on short-term visual fidelity, reshaping our approach to world model design.
Spatial-semantic prompting outperforms traditional text-only methods in embodied visual tracking, especially in complex environments with similar distractors.
ATHENA accelerates influence computation for billion-parameter models, achieving a staggering 313.4x speedup while maintaining or improving task performance with significantly less data.
EM-Fall's embodied sensing approach enables humanoid robots to maintain effective fall detection even in challenging environments, outperforming traditional systems.
CoT fine-tuning can slash long-range recall by over 57% in hybrid LLMs, but a simple parameter restoration method can reverse this trend without additional training.
Robots can now understand and act on your gaze while following language commands, enabling more intuitive and precise human-robot collaboration.
Robots can now plan 9x faster and achieve significantly higher success rates by decoupling action prediction from video generation in World-Action Models.
Forget fixed residual connections: Attention Residuals let each layer selectively attend to previous layers, boosting performance and gradient flow in deep LLMs.
Forget difficulty-based heuristics: InSight leverages weighted mutual information to select RL training data, boosting LLM reasoning and alignment with up to 2.2x speedup.
Forget end-to-end VLAs: GigaBrain-0.5M* leverages world models and reinforcement learning to achieve a 30% performance boost on complex robotic manipulation tasks, showcasing reliable long-horizon execution.
Current robot learning benchmarks may be too simplistic: GM-100 offers 100 new, challenging tasks designed to expose the long-tail behaviors that existing benchmarks miss.
