1765 papers
This category explores the vast and evolving landscape of research falling between the letters C and R, capturing a diverse array of scientific inquiries from chemistry to robotics. These studies often bridge the gap between theoretical models and real-world applications, offering fresh perspectives on everything from material science to complex biological systems. As these fields advance rapidly, staying updated with the latest findings can be challenging without a clear guide.
At Gist.Science, we ensure you never miss a breakthrough by processing every new preprint in this section directly from arXiv. Our team transforms complex academic manuscripts into accessible content, providing both plain-language overviews for general readers and detailed technical summaries for experts. This dual approach ensures that whether you are a student, researcher, or curious observer, you can grasp the core significance of each study without getting lost in dense jargon.
Below are the latest papers in this dynamic collection, sorted by their recent release dates to keep you at the forefront of discovery.
This paper introduces WarmPrior, a temporally grounded prior derived from recent action history that replaces the standard Gaussian source in flow-matching policies to produce straighter probability paths, thereby consistently improving success rates, sample efficiency, and exploration in robotic manipulation tasks.
This paper proposes an adaptive ergodic imitation framework that constructs a target distribution from retrieved demonstrations to generate trajectories capable of dynamically interpolating between tracking and exploration, thereby enabling robots to recover from training-deployment mismatches and complete tasks despite environmental changes or observation errors.
This paper demonstrates that behavior cloning using low-resolution egocentric vision and relative joint delta prediction is sufficient for a robot arm to successfully perform active perception by repositioning itself to center a partially visible object before grasping.
This paper presents a novel mathematical model and a gain-scheduled linear-quadratic regulator (LQR) for the SeaVis remotely operated towed vehicle, demonstrating through high-fidelity simulation that the proposed controller outperforms conventional PID approaches in robustness, efficiency, and actuation reduction for high-resolution seabed mapping.
This paper proposes a behavioral data-driven framework based on Willems' fundamental lemma to generate optimal, open-loop slewing trajectories for rotary cranes that effectively suppress load sway and reduce operation time and energy consumption without requiring explicit system modeling or extensive datasets.
This paper proposes a multi-modal world model that integrates tactile and visual information to significantly improve the accuracy and robustness of robotic action predictions in physically ambiguous environments, supported by two novel datasets collected using magnetic-based tactile sensors.
This paper introduces RSR-RSMARL, a robust and safe multi-agent reinforcement learning framework that integrates communication, robust policy training for zero-shot sim-to-real transfer, and Control Barrier Function-based safety shields, successfully demonstrating enhanced coordination and safety on hardware autonomous vehicles.
UniJEPA is a unified robot policy framework that leverages large-scale pretraining on instructional videos to learn combined continuous and discrete representations, enabling superior performance in both simulation and real-world out-of-distribution tasks compared to existing vision-language and generative approaches.
QuickLAP is a Bayesian framework that leverages Large Language Models to fuse ambiguous physical corrections with high-level language feedback, enabling semi-autonomous systems to rapidly and robustly infer user reward functions in real time.
This paper introduces a unified KL-regularized framework for optimal control that generalizes classical and risk-sensitive objectives through soft-policy surrogates, which can be iterated to recover original goals and, in a synchronized case, yield linear Bellman operators and path-integral solutions.