101 citations · 136 across the 20 of their papers we have counts for
22 papers
GeoSceneGraph: Geometric Scene Graph Diffusion Model for Text-guided 3D Indoor Scene Synthesis
Antonio Ruiz, Tao Wu, Andrew Melnik +6
Methods that synthesize indoor 3D scenes from text prompts have wide-ranging applications in film production, interior design, video games, virtual reality, and synthetic data gene…
Lane Graph Extraction from Aerial Imagery via Lane Segmentation Refinement with Diffusion Models
Antonio Ruiz, Andrew Melnik, Nicolo Savioli +3
The lane graph is critical for applications such as autonomous driving and lane-level route planning. While previous research has focused on extracting lane-level graphs from aeria…
Benchmarks for Physical Reasoning AI
Andrew Melnik, Robin Schiewer, Moritz Lange +4
Physical reasoning is a crucial aspect in the development of general AI systems, given that human learning starts with interacting with the physical world before progressing to mor…
Behavioral Cloning via Search in Embedded Demonstration Dataset
Federico Malato, Florian Leopold, Ville Hautamaki +1
Behavioural cloning uses a dataset of demonstrations to learn a behavioural policy. To overcome various learning and policy adaptation problems, we propose to use latent space to i…
Contrastive Language, Action, and State Pre-training for Robot Learning
Krishan Rana, Andrew Melnik, Niko Sünderhauf
In this paper, we introduce a method for unifying language, action, and state information in a shared embedding space to facilitate a range of downstream tasks in robot learning. O…
Shape complexity estimation using VAE
Markus Rothgaenger, Andrew Melnik, Helge Ritter
In this paper, we compare methods for estimating the complexity of two-dimensional shapes and introduce a method that exploits reconstruction loss of Variational Autoencoders with…
Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition
Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas +27
To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 20…
Stroke-based Rendering: From Heuristics to Deep Learning
Florian Nolte, Andrew Melnik, Helge Ritter
In the last few years, artistic image-making with deep learning models has gained a considerable amount of traction. A large number of these models operate directly in the pixel sp…
Behavioral Cloning via Search in Video PreTraining Latent Space
Federico Malato, Florian Leopold, Amogh Raut +2
Our aim is to build autonomous agents that can solve tasks in environments like Minecraft. To do so, we used an imitation learning-based approach. We formulate our control problem…
Face Generation and Editing with StyleGAN: A Survey
Andrew Melnik, Maksim Miasayedzenkau, Dzianis Makarovets +6
Our goal with this survey is to provide an overview of the state of the art deep learning methods for face generation and editing using StyleGAN. The survey covers the evolution of…
Planning with RL and episodic-memory behavioral priors
Shivansh Beohar, Andrew Melnik
The practical application of learning agents requires sample efficient and interpretable algorithms. Learning from behavioral priors is a promising way to bootstrap agents with a b…
Solving Learn-to-Race Autonomous Racing Challenge by Planning in Latent Space
Shivansh Beohar, Fabian Heinrich, Rahul Kala +2
Learn-to-Race Autonomous Racing Virtual Challenge hosted on www<dot>aicrowd<dot>com platform consisted of two tracks: Single and Multi Camera. Our UniTeam team was among the final…
Faces: AI Blitz XIII Solutions
Andrew Melnik, Eren Akbulut, Jannik Sheikh +3
AI Blitz XIII Faces challenge hosted on www.aicrowd.com platform consisted of five problems: Sentiment Classification, Age Prediction, Mask Prediction, Face Recognition, and Face D…
Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes
Christian Eichenberger, Moritz Neun, Henry Martin +34
The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks can successfully predict future traffic conditions 1 hour into the future on simply aggrega…
A Graph-based U-Net Model for Predicting Traffic in unseen Cities
Luca Hermes, Barbara Hammer, Andrew Melnik +3
Accurate traffic prediction is a key ingredient to enable traffic management like rerouting cars to reduce road congestion or regulating traffic via dynamic speed limits to maintai…
YOLO -- You only look 10647 times
Christian Limberg, Andrew Melnik, Augustin Harter +1
With this work we are explaining the "You Only Look Once" (YOLO) single-stage object detection approach as a parallel classification of 10647 fixed region proposals. We support thi…
Transfer Learning with Jukebox for Music Source Separation
W. Zai El Amri, O. Tautz, H. Ritter +1
In this work, we demonstrate how a publicly available, pre-trained Jukebox model can be adapted for the problem of audio source separation from a single mixed audio channel. Our ne…
Critic Guided Segmentation of Rewarding Objects in First-Person Views
Andrew Melnik, Augustin Harter, Christian Limberg +3
This work discusses a learning approach to mask rewarding objects in images using sparse reward signals from an imitation learning dataset. For that, we train an Hourglass network…
Towards robust and domain agnostic reinforcement learning competitions
William Hebgen Guss, Stephanie Milani, Nicholay Topin +26
Reinforcement learning competitions have formed the basis for standard research benchmarks, galvanized advances in the state-of-the-art, and shaped the direction of the field. Desp…
Solving Physics Puzzles by Reasoning about Paths
Augustin Harter, Andrew Melnik, Gaurav Kumar +3
We propose a new deep learning model for goal-driven tasks that require intuitive physical reasoning and intervention in the scene to achieve a desired end goal. Its modular struct…
Modularization of End-to-End Learning: Case Study in Arcade Games
Andrew Melnik, Sascha Fleer, Malte Schilling +1
Complex environments and tasks pose a difficult problem for holistic end-to-end learning approaches. Decomposition of an environment into interacting controllable and non-controlla…
Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments
Łukasz Kidziński, Sharada Prasanna Mohanty, Carmichael Ong +26
In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle c…