Deep learning-enabled medical computer vision

A Esteva, K Chou, S Yeung, N Naik, A Madani… - NPJ digital …, 2021 - nature.com
A decade of unprecedented progress in artificial intelligence (AI) has demonstrated the
potential for many fields—including medicine—to benefit from the insights that AI techniques …

Coderl: Mastering code generation through pretrained models and deep reinforcement learning

H Le, Y Wang, AD Gotmare… - Advances in Neural …, 2022 - proceedings.neurips.cc
Program synthesis or code generation aims to generate a program that satisfies a problem
specification. Recent approaches using large-scale pretrained language models (LMs) have …

Scene representation networks: Continuous 3d-structure-aware neural scene representations

V Sitzmann, M Zollhöfer… - Advances in Neural …, 2019 - proceedings.neurips.cc
Unsupervised learning with generative models has the potential of discovering rich
representations of 3D scenes. While geometric deep learning has explored 3D-structure …

Shapeassembly: Learning to generate programs for 3d shape structure synthesis

RK Jones, T Barton, X Xu, K Wang, E Jiang… - ACM Transactions on …, 2020 - dl.acm.org
Manually authoring 3D shapes is difficult and time consuming; generative models of 3D
shapes offer compelling alternatives. Procedural representations are one such possibility …

Learning to synthesize programs as interpretable and generalizable policies

D Trivedi, J Zhang, SH Sun… - Advances in neural …, 2021 - proceedings.neurips.cc
Recently, deep reinforcement learning (DRL) methods have achieved impressive
performance on tasks in a variety of domains. However, neural network policies produced …

Learning to infer and execute 3d shape programs

Y Tian, A Luo, X Sun, K Ellis, WT Freeman… - arxiv preprint arxiv …, 2019 - arxiv.org
Human perception of 3D shapes goes beyond reconstructing them as a set of points or a
composition of geometric primitives: we also effortlessly understand higher-level shape …

Learning unsupervised hierarchical part decomposition of 3d objects from a single rgb image

D Paschalidou, LV Gool… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Humans perceive the 3D world as a set of distinct objects that are characterized by various
low-level (geometry, reflectance) and high-level (connectivity, adjacency, symmetry) …

Outline, then details: Syntactically guided coarse-to-fine code generation

W Zheng, SP Sharan, AK Jaiswal… - International …, 2023 - proceedings.mlr.press
For a complicated algorithm, its implementation by a human programmer usually starts with
outlining a rough control flow followed by iterative enrichments, eventually yielding carefully …

Symbol-LLM: leverage language models for symbolic system in visual human activity reasoning

X Wu, YL Li, J Sun, C Lu - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Human reasoning can be understood as a cooperation between the intuitive, associative"
System-1''and the deliberative, logical" System-2''. For existing System-1-like methods in …

Proto: Program-guided transformer for program-guided tasks

Z Zhao, K Samel, B Chen - Advances in neural …, 2021 - proceedings.neurips.cc
Programs, consisting of semantic and structural information, play an important role in the
communication between humans and agents. Towards learning general program executors …