The Quest for an Integrated Set of Neural Mechanisms Underlying Object Recognition in Primates
K Kar, JJ DiCarlo - Annual Review of Vision Science, 2024 - annualreviews.org
Inferences made about objects via vision, such as rapid and accurate categorization, are
core to primate cognition despite the algorithmic challenge posed by varying viewpoints and …
core to primate cognition despite the algorithmic challenge posed by varying viewpoints and …
Hydra: A real-time spatial perception system for 3D scene graph construction and optimization
3D scene graphs have recently emerged as a powerful high-level representation of 3D
environments. A 3D scene graph describes the environment as a layered graph where …
environments. A 3D scene graph describes the environment as a layered graph where …
From word models to world models: Translating from natural language to the probabilistic language of thought
How does language inform our downstream thinking? In particular, how do humans make
meaning from language--and how can we leverage a theory of linguistic meaning to build …
meaning from language--and how can we leverage a theory of linguistic meaning to build …
Foundations of spatial perception for robotics: Hierarchical representations and real-time systems
3D spatial perception is the problem of building and maintaining an actionable and
persistent representation of the environment in real-time using sensor data and prior …
persistent representation of the environment in real-time using sensor data and prior …
Visually-prompted language model for fine-grained scene graph generation in an open world
Abstract Scene Graph Generation (SGG) aims to extract< subject, predicate, object>
relationships in images for vision understanding. Although recent works have made steady …
relationships in images for vision understanding. Although recent works have made steady …
Language models, agent models, and world models: The law for machine reasoning and planning
Despite their tremendous success in many applications, large language models often fall
short of consistent reasoning and planning in various (language, embodied, and social) …
short of consistent reasoning and planning in various (language, embodied, and social) …
A State‐of‐the‐Art Computer Vision Adopting Non‐Euclidean Deep‐Learning Models
A distance metric known as non‐Euclidean distance deviates from the laws of Euclidean
geometry, which is the geometry that governs most physical spaces. It is utilized when …
geometry, which is the geometry that governs most physical spaces. It is utilized when …
Lilo: Learning interpretable libraries by compressing and documenting code
While large language models (LLMs) now excel at code generation, a key aspect of software
development is the art of refactoring: consolidating code into libraries of reusable and …
development is the art of refactoring: consolidating code into libraries of reusable and …
Vael: Bridging variational autoencoders and probabilistic logic programming
We present VAEL, a neuro-symbolic generative model integrating variational autoencoders
(VAE) with the reasoning capabilities of probabilistic logic (L) programming. Besides …
(VAE) with the reasoning capabilities of probabilistic logic (L) programming. Besides …
Smcp3: Sequential monte carlo with probabilistic program proposals
This paper introduces SMCP3, a method for automatically implementing custom sequential
Monte Carlo samplers for inference in probabilistic programs. Unlike particle filters and …
Monte Carlo samplers for inference in probabilistic programs. Unlike particle filters and …