The paper presents BoxTwin, an interactive digital twin framework that learns the full dynamics of elastoplastic articulated objects from videos and accurately tracks joint trajectories and reproduces…

Crazyflow is a novel, highly accelerated, and differentiable drone simulator that provides a unified platform for generating large-scale synthetic data for aerial robotics, enabling advanced training…

The paper proposes an attention-enhanced deep learning framework using EfficientNet and CBAM to achieve high accuracy (93.3%) in classifying peach leaf damage, demonstrating improved robustness under…

The paper presents AutoDex, a system that automatically collects real-world data for robust dexterous grasping, achieving a 4.8x throughput improvement over teleoperation and higher success rate than…

This paper presents LightFARM, a predictive lighting control framework for energy-efficient indoor farming that combines finite-horizon predictive control with compact models of photosynthesis, therma…

This paper presents Mana, a sim-to-real framework for dexterous articulated tool manipulation.

This paper presents ABot-C0, a motion-control system for quadruped robots, which includes a scalable multi-source motion-data pipeline, robust policy learning, and a unified deployment stack for real-…

This paper presents GRAIL, a digital generation pipeline that synthesizes human-object interactions for humanoid robots.

The paper introduces NewtPhys, a novel 4D dataset of real-world scenes with dense physical annotations, to systematically evaluate and reveal the limitations of foundation models in low-level Newtonia…

The paper introduces RoboWits, a new bi-manual robotic benchmark designed to test a robot's cognitive reasoning and adaptability to unexpected challenges, revealing that current Vision-Language-Action…

This paper proposes CertifiedCacheMPC, a caching system for Model Predictive Control in hierarchical quadruped controllers, ensuring primal feasibility and cost suboptimality.

This paper introduces X4Val, a framework for variance-reduced real-world metric estimation using non-paired, multi-domain data.

The paper introduces DexVerse, a large-scale and modular benchmark for dexterous manipulation with 100 tasks, 3 robot arms, 6 hands, and configurable visual variations.

The paper advocates for the establishment of Model Science, a systematic discipline that moves beyond simple benchmarking to deeply analyze AI models' internal workings and failure modes.

This paper presents CARLA-GS, a modular corner-case synthesis pipeline for autonomous driving that decouples visual representation, semantic reasoning, and physics-based execution while maintaining ti…