1 citations · 1 across the 14 of their papers we have counts for
17 papers
Structure-Adaptive Tree Field Integrators
Millend Roy, Soham Samal, Ivan Zelich +1
We present a new class of near-linear algorithms for efficiently integrating general tensor fields defined on trees with distance dependent kernels, the Structure-Adaptive Tree Fie…
Unlocking Geodesic Gromov-Wasserstein Distances for 3D Modeling
Krzysztof Marcin Choromanski, Derek Long, Ananya Parashar +1
\textit{Gromov-Wasserstein Distances} (GWDs) provide quantitative ways of comparing probabilistic distributions defined on different metric spaces by applying techniques from the o…
ClockRoPE: Random Fourier Rotations for Temporal Routine Modeling
Yiwen Chen, Joshua Ainslie, Krzysztof Choromanski +4
Rotary Position Embedding (RoPE) has been widely adopted in transformer-based large language models. However, its log-linear frequency schedule, originally designed to produce long…
Near-Linear Time Generalized Sinkhorn Algorithms for Bounded Genus Graphs
Krzysztof Choromanski, Derek Long, Ananya Parashar +1
We present GenusSink, a new class of approximate generalized Sinkhorn algorithms with shortest-path-distance costs for bounded genus (e.g. planar) graphs, providing near-linear tim…
RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings
Byeongchan Kim, Arijit Sehanobish, Avinava Dubey +2
We present a new class of efficient attention mechanisms applying universal 3D Relative Positional Encoding (RPE) methods given by arbitrary integrable modulation functions . Th…
TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment
Bingyi Cao, Koert Chen, Kevis-Kokitsi Maninis +16
Recent progress in vision-language pretraining has enabled significant improvements to many downstream computer vision applications, such as classification, retrieval, segmentation…
SLAY: Geometry-Aware Spherical Linearized Attention with Yat-Kernel
Jose Miguel Luna, Taha Bouhsine, Krzysztof Choromanski
We propose a new class of linear-time attention mechanisms based on a relaxed and computationally efficient formulation of the recently introduced E-Product, often referred to as t…
Manifold Random Features
Ananya Parashar, Derek Long, Dwaipayan Saha +1
We present a new paradigm for creating random features to approximate bi-variate functions (in particular, kernels) defined on general manifolds. This new mechanism of Manifold Ran…
CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining
I-Chun Arthur Liu, Krzysztof Choromanski, Sandy Huang +1
Leveraging pre-trained 2D image representations in behavior cloning policies has achieved great success and has become a standard approach for robotic manipulation. However, such r…
Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer
Gemini Robotics Team, Abbas Abdolmaleki, Saminda Abeyruwan +169
General-purpose robots need a deep understanding of the physical world, advanced reasoning, and general and dexterous control. This report introduces the latest generation of the G…
Computationally-efficient Graph Modeling with Refined Graph Random Features
Krzysztof Choromanski, Avinava Dubey, Arijit Sehanobish +1
We propose refined GRFs (GRFs++), a new class of Graph Random Features (GRFs) for efficient and accurate computations involving kernels defined on the nodes of a graph. GRFs++ reso…
Graph Random Features for Scalable Gaussian Processes
Matthew Zhang, Jihao Andreas Lin, Krzysztof Choromanski +3
We study the application of graph random features (GRFs) - a recently introduced stochastic estimator of graph node kernels - to scalable Gaussian processes on discrete input space…
Rotary Position Encodings for Graphs
Isaac Reid, Arijit Sehanobish, Cederik Höfs +7
We study the extent to which rotary position encodings (RoPE), a recent transformer position encoding algorithm broadly adopted in large language models (LLMs) and vision transform…
Linear Transformer Topological Masking with Graph Random Features
Isaac Reid, Kumar Avinava Dubey, Deepali Jain +12
When training transformers on graph-structured data, incorporating information about the underlying topology is crucial for good performance. Topological masking, a type of relativ…
Variance-Reducing Couplings for Random Features
Isaac Reid, Stratis Markou, Krzysztof Choromanski +2
Random features (RFs) are a popular technique to scale up kernel methods in machine learning, replacing exact kernel evaluations with stochastic Monte Carlo estimates. They underpi…
General Graph Random Features
Isaac Reid, Krzysztof Choromanski, Eli Berger +1
We propose a novel random walk-based algorithm for unbiased estimation of arbitrary functions of a weighted adjacency matrix, coined universal graph random features (u-GRFs). This…
Repelling Random Walks
Isaac Reid, Eli Berger, Krzysztof Choromanski +1
We present a novel quasi-Monte Carlo mechanism to improve graph-based sampling, coined repelling random walks. By inducing correlations between the trajectories of an interacting e…