Search papers, labs, and topics across Lattice.
Faithful reasoning in VLA models can boost policy responsiveness to rare scenarios by 1.6x compared to state-of-the-art approaches, revealing a critical gap in current alignment strategies.
Freeform Preference Learning allows robots to be trained on nuanced human preferences, leading to a dramatic 38% improvement in manipulation tasks.
Robots can now learn new tasks on-the-fly from just one demonstration, revolutionizing how we teach machines to manipulate their environments.
Adapting pretrained policies with just a modest multisensory dataset can enhance robot manipulation performance across diverse tasks without sacrificing prior knowledge.
Synthesizing 48,000 interaction trajectories without human input enables a humanoid robot to learn complex loco-manipulation tasks effectively.
Touch is not just an add-on; it fundamentally enhances object representation, leading to dramatic improvements in physical property estimation and manipulation tasks.
Policies trained in SimFoundry's automated environments achieve up to 40% higher success rates in real-world tasks by leveraging affordance-preserving scene variations.
Pretraining through play can revolutionize how robots learn dexterous assembly, achieving 60% success in tight insertions with minimal contact clearance.
Complex manipulation capabilities can be achieved by dynamically composing simple behaviors, leading to unprecedented precision and adaptability in real-world tasks.
Primitive steerability in VLAs allows for autonomous skill acquisition, enabling robots to learn new tasks without human demonstrations.
Cloak enables VLA models to seamlessly adapt to new robotic embodiments without any additional training data, revolutionizing the way we think about robotic adaptability.
This vine robot can autonomously navigate and manipulate in complex environments, overcoming traditional control limitations with a robust vision-based approach.
Advanced Vision-Language-Action models can be dramatically compressed by up to 50% without losing performance, reshaping our approach to robotic manipulation.
DREAM-Chunk transforms action chunking by leveraging latent world models to enhance robustness against stochastic dynamics without the need for policy retraining.
SC3-Eval achieves a remarkable 0.929 Pearson correlation in evaluating robot policies, revealing critical insights into their real-world performance.
Action-view augmentation can transform how robots adapt to unforeseen obstacles, boosting manipulation success rates significantly.
Flow Reversal Steering transforms vague human commands into precise robotic actions, achieving up to 95% higher success rates in real-world tasks with minimal training.
Zero-shot sim-to-real transfer for articulated tool manipulation is now achievable with just a few clicks, revolutionizing how robots interact with complex objects.
Action-conditioned predictions from a compact latent model reveal that diffusion methods can dramatically outperform traditional regression in scene forecasting for autonomous vehicles.
Naively scaling test-time compute is wasteful; strategically allocating it with DIRECT can enhance embodied agent performance while slashing latency by up to 65%.
A single VLA model enables decentralized multi-robot collaboration, achieving a 64% performance boost without the need for individual policies or communication.
High-quality dense rewards can elevate robotic manipulation success rates from 50% to near perfection, transforming how robots learn from their environments.
LadderMan enables humanoid robots to climb ladders and manipulate objects with unprecedented robustness and adaptability in real-world scenarios.
A triangular roller tip mount significantly reduces friction and improves the performance of growing vine robots, enabling reliable sensor integration for complex tasks.
Training VLA policies without human demos is now feasible, with LEGS achieving better performance than traditional methods at a fraction of the cost.
Forget hand-crafted physics models – NeuROK learns to generate realistic object deformations directly from data, opening the door to more general and scalable 4D simulations.
Humanoid states, not low-level actions, are the key to unlocking text-driven control, enabling a diffusion model to generate more natural and semantically aligned behaviors.
Achieve near-perfect robotic manipulation with just 20 minutes of robot experience by smartly finetuning vision-language-action models with reinforcement learning.
Get the performance boost of expensive sampling-based RL policies for a fraction of the compute by learning to prune action candidates early in the diffusion denoising process.
Generate navigable, 3D-consistent simulations of real-world locations with arbitrary weather and dynamic object configurations using only geo-registered video data.
Runners stick to their pace 60% better and enjoy the workout more when coached by a robot dog than when using an Apple Watch.
Scaling robot learning with human data isn't a simple "more is better" equation; alignment with robot learning objectives is key.
Unlock interactive digital twins from messy, real-world videos: FunRec automatically turns egocentric RGB-D recordings into simulation-ready 3D scenes.
Stochastic resetting—randomly teleporting RL agents back to the start—surprisingly speeds up learning, even when it wouldn't help a non-learning agent.
Forget slow, model-dependent curation: FAKTUAL offers a fast, model-free way to boost robot imitation learning by directly maximizing the entropy of demonstration datasets.
Ditch the anchors and NMS: AutoReg3D reimagines 3D object detection as a sequence generation problem, opening the door for language-model techniques in 3D perception.
Turns out, the best memory design for robotic manipulation depends heavily on the task, with no single architecture dominating across the board.
Unlock compliant robot control without force sensors or complex learning, using only motor signals already available in most modern robots.
By unifying hand motion estimation and generation into a single diffusion framework, UniHand handles heterogeneous inputs and challenging conditions like occlusions better than task-specific models.
Robots can now navigate complex outdoor environments and find objects using natural language queries, even without prior maps or precise depth sensing.
A single RL policy trained on procedurally generated tools in simulation can achieve zero-shot dexterous manipulation of diverse real-world tools, rivaling task-specific policies.
Verification at test time can be a surprisingly effective alternative to scaling policy learning for vision-language-action alignment, yielding substantial gains in both simulated and real-world robotic tasks.
A deployable robotic arm achieves sub-15mm accuracy at 1.8m reach, opening the door to autonomous lunar construction.
Q-functions and implicit policy extraction are game-changers for batch online RL in robotics, unlocking significant performance gains over imitation-based approaches.
