Search papers, labs, and topics across Lattice.
Humanoid robots can now traverse complex terrains with human-like gaits, thanks to a surprisingly simple and efficient framework that eschews adversarial training.
Robots can now manipulate objects with greater dexterity and adaptability thanks to a new world model that leverages both vision and high-frequency tactile feedback to predict and react to contact dynamics.
Ditch fixed compute budgets: this new flow-matching method for robotic control adaptively allocates computation, speeding up simple tasks and focusing on complex ones.
Forget expensive real-world data collection: a massive, diverse synthetic dataset enables surprisingly effective zero-shot transfer for robotic manipulation.
World Action Models can ditch the slow, iterative "imagine-then-execute" loop at test time without sacrificing performance, achieving a 4x speedup.
Humanoid robots can now handle heavy, unknown payloads in the real world thanks to a system that identifies mass distribution via differentiable simulation.
Achieve a 40% jump in success rates on real-world contact-rich manipulation by intelligently scheduling force feedback into visual-motor policies.
Forget predefined areas of interest: this multi-agent exploration framework uses Gaussian belief mapping to adaptively balance scientific discovery and safety in hazardous off-world environments.
Human-robot teams can slash interaction costs by 50% and task times by 25% when robots actively resolve uncertainty about tasks and infer human intent using LLMs and spatial reasoning.
LLMs can orchestrate human input to UAVs, dramatically improving mission success rates while minimizing human interaction.
By combining video generation and vision-language models, EmboAlign achieves a 43% boost in real-world robot manipulation success without any task-specific training.
Training generalist robots just got a whole lot easier: RoboCasa365 offers a massive, diverse, and reproducible benchmark for household mobile manipulation.
By pausing to "think" with latent diffusion, STAR-LDM achieves superior language understanding, narrative coherence, and controllable generation compared to standard autoregressive models of similar size.
Forget painstakingly engineering robot behaviors: DreamZero learns directly from video of other robots or even humans, adapting to new tasks and bodies with just minutes of data.
Key contribution not extracted.
Training a robot foundation model on 30,000 hours of heterogeneous embodied data lets it outperform prior methods by up to 48% on complex manipulation tasks and even benefit from low-quality data.
Forget synthetic data that looks like it came from a PS2 game: NVIDIA's new Cosmos-Predict2.5 generates high-fidelity videos for training embodied AI, opening the door to more realistic and reliable simulations.
Ditch slow iterative refinement: conditional flow-matching models can directly learn meaningful proposal distributions from noisy sampling-based MPC data, slashing planning time.
Imagine training robots to manipulate objects in the real world, but entirely within a high-fidelity, diffusion-based dream.
