MIT CSAIL

Real-world robot demonstrations can now be collected at 66 demos/hour by optimizing TAMP solution quality for behavior cloning.

The hardest-to-distinguish competitor, not the average, dictates the speed of decentralized adaptive sensing.

It is shown that the workspace token can be used as a drop-in replacement for observations during deployment, enabling policies to solve memory-intensive tasks without the need for VLM reasoning in-the-loop.

Achieving reliable, high-quality motion planning around convex obstacles is now feasible even with poor initial conditions, thanks to a novel biconvex optimization approach.

Ms.Forcing achieves a 39.6% speedup in streaming video generation while significantly enhancing quality by intelligently adapting spatial granularity to noise levels.

DriftWorld achieves 17x faster rollouts than diffusion models, revolutionizing real-time planning for robotic manipulation.

Causal inference in sequential settings reveals how vaccination rates significantly affect COVID-19 death rates, challenging conventional understanding of public health interventions.

A groundbreaking dataset reveals that 3D particle models significantly outperform 2D video models in capturing the complexities of deformable object dynamics.

Historical failure records can be transformed into diverse testing scenarios for autonomous driving, revealing critical system vulnerabilities with minimal effort.

Automating freeway network extraction from OSM can cut analyst effort by two-thirds, making large-scale freeway simulations feasible.

FracEvent achieves superior event timing and downstream performance by accurately modeling pixel dynamics, outperforming traditional simulators.

Memory consistency in video generation models falters significantly when objects disappear, with state-of-the-art models struggling to recover updated states upon reappearance.

Decentralized traffic management for autonomous aircraft can achieve high performance without centralized coordination, adapting seamlessly to complex environments.

Balancing productivity and stability reveals that stronger synchronization can paradoxically increase systemic fragility in multi-agent systems.

Dynestyx transforms the landscape of Bayesian analysis by making advanced state-space modeling techniques accessible to practitioners through a unified interface.

Adaptive opponents can significantly alter the landscape of regret minimization, and our new RP-Regret metric reveals how to achieve better cooperative outcomes in repeated games.

Reachability maps don't have to trade off precision, speed, and flexibility: RichMap achieves all three.

Robots can now "see" hidden objects and understand articulation by learning from human egocentric video, even if they can't physically explore those areas themselves.

Freeing robots from pre-assigned tasks slashes completion times in multi-agent settings, with a new algorithm improving performance on almost 90% of tested scenarios.

Heuristic maritime routes lead to extreme fuel waste in nearly 5% of voyages, but this RL approach cuts that risk by almost 10x.

Forget hand-engineered features: this approach learns symbolic representations for robotic planning directly from pixels using VLMs, enabling impressive zero-shot generalization to new environments and goals.

Forget hand-engineering initial conditions for robust RL: this method *learns* which conditions are feasible while simultaneously training a safe policy.