Related papers: Reciprocal Space Attention for Learning Long-Range…
Safe and efficient collaboration among multiple robots in unstructured environments is increasingly critical in the era of Industry 4.0. However, achieving robust and autonomous collaboration among humans and other robots requires modern…
Despite great strides in language-guided manipulation, existing work has been constrained to table-top settings. Table-tops allow for perfect and consistent camera angles, properties are that do not hold in mobile manipulation. Task plans…
In the presence of strong electronic spin correlations, the hyperfine interaction imparts long-range coupling between nuclear spins. Efficient protocols for the extraction of such complex information about electron correlations via magnetic…
Lightweight super resolution networks have extremely importance for real-world applications. In recent years several SR deep learning approaches with outstanding achievement have been introduced by sacrificing memory and computational cost.…
Most current machine learning interatomic potentials (MLIPs) rely on short-range approximations, without explicit treatment of long-range electrostatics. To address this, we recently developed the Latent Ewald Summation (LES) method, which…
Machine-learned interatomic potentials (MLIPs) and force fields (i.e. interaction laws for atoms and molecules) are typically trained on limited data-sets that cover only a very small section of the full space of possible input structures.…
Representational Similarity Analysis (RSA) is a popular method for analyzing neuroimaging and behavioral data. Here we evaluate the accuracy and reliability of RSA in the context of model selection, and compare it to that of regression.…
Linear attention has emerged as a promising direction for scaling Vision Transformers beyond the quadratic cost of dense self-attention. A prevalent strategy is to compress spatial tokens into a compact set of intermediate proxies that…
Diffusion models have revolutionized imitation learning, allowing robots to replicate complex behaviours. However, diffusion often relies on cameras and other exteroceptive sensors to observe the environment and lacks long-term memory. In…
Safe exploration is critical for using reinforcement learning (RL) in risk-sensitive environments. Recent work learns risk measures which measure the probability of violating constraints, which can then be used to enable safety. However,…
In this work, we study how multi-head latent attention (MLA), a popular strategy for compressing key/value memory, affects a transformer's internal capacity during pretraining. Using a lightweight suite of Marchenko-Pastur (MP) diagnostics,…
Self-attention has become an important and widely used neural network component that helped to establish new state-of-the-art results for various applications, such as machine translation and automatic speech recognition (ASR). However, the…
The exploration of mutual-benefit cross-domains has shown great potential toward accurate self-supervised depth estimation. In this work, we revisit feature fusion between depth and semantic information and propose an efficient local…
Autonomous manipulation of granular media, such as sand, is crucial for applications in construction, excavation, and additive manufacturing. However, shaping granular materials presents unique challenges due to their high-dimensional…
Mounting a reconfigurable intelligent surface (RIS) on an unmanned aerial vehicle (UAV) holds promise for improving traditional terrestrial network performance. Unlike conventional methods deploying passive RIS on UAVs, this study delves…
The quadratic complexity of attention mechanisms poses a critical bottleneck for large language models processing long contexts. While dynamic sparse attention methods offer input-adaptive efficiency, they face fundamental trade-offs:…
Learning generalizable skills in robotic manipulation has long been challenging due to real-world sized observation and action spaces. One method for addressing this problem is attention focus -- the robot learns where to attend its sensors…
Non-Local Attention (NLA) is a powerful technique for capturing long-range feature correlations in deep single image super-resolution (SR). However, NLA suffers from high computational complexity and memory consumption, as it requires…
Recently, Vision Transformer and its variants have shown great promise on various computer vision tasks. The ability of capturing short- and long-range visual dependencies through self-attention is arguably the main source for the success.…
Skilled robotic manipulation benefits from complex synergies between non-prehensile (e.g. pushing) and prehensile (e.g. grasping) actions: pushing can help rearrange cluttered objects to make space for arms and fingers; likewise, grasping…