Publications

Efficient Graphics Representation with Differentiable Indirection
Sayantan Datta
Carl Marshall
Zhao Dong
Zhengqin Li
Derek Nowrouzezahrai
We introduce differentiable indirection – a novel learned primitive that employs differentiable multi-scale lookup tables as an effective … (see more)substitute for traditional compute and data operations across the graphics pipeline. We demonstrate its flexibility on a number of graphics tasks, i.e., geometric and image representation, texture mapping, shading, and radiance field representation. In all cases, differentiable indirection seamlessly integrates into existing architectures, trains rapidly, and yields both versatile and efficient results.
2023-12-11
SIGGRAPH Asia 2023 Conference Papers (published)
doi.org
arxiv.org
Explorable Mesh Deformation Subspaces from Unstructured 3D Generative Models
Arman Maesumi
Paul Guerrero
Noam Aigerman
Vladimir Kim
Matthew Fisher
Siddhartha Chaudhuri
Daniel Ritchie
2023-12-11
SIGGRAPH Asia 2023 Conference Papers (published)
doi.org
arxiv.org
Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks
MohammadReza Davari
Eugene Belilovsky
2023-12-11
ArXiv (preprint)
doi.org
arxiv.org
Lagrangian Properties and Control of Soft Robots Modeled with Discrete Cosserat Rods
Lekan Molu
Shaoru Chen
Audrey Sedal
The characteristic ``in-plane"bending associated with soft robots' deformation make them preferred over rigid robots in sophisticated manipu… (see more)lation and movement tasks. Executing such motion strategies to precision in soft deformable robots and structures is however fraught with modeling and control challenges given their infinite degrees-of-freedom. Imposing \textit{piecewise constant strains} (PCS) across (discretized) Cosserat microsolids on the continuum material however, their dynamics become amenable to tractable mathematical analysis. While this PCS model handles the characteristic difficult-to-model ``in-plane"bending well, its Lagrangian properties are not exploited for control in literature neither is there a rigorous study on the dynamic performance of multisection deformable materials for ``in-plane"bending that guarantees steady-state convergence. In this sentiment, we first establish the PCS model's structural Lagrangian properties. Second, we exploit these for control on various strain goal states. Third, we benchmark our hypotheses against an Octopus-inspired robot arm under different constant tip loads. These induce non-constant ``in-plane"deformation and we regulate strain states throughout the continuum in these configurations. Our numerical results establish convergence to desired equilibrium throughout the continuum in all of our tests. Within the bounds here set, we conjecture that our methods can find wide adoption in the control of cable- and fluid-driven multisection soft robotic arms; and may be extensible to the (learning-based) control of deformable agents employed in simulated, mixed, or augmented reality.
2023-12-10
ArXiv (preprint)
doi.org
arxiv.org
Maximum flow-based formulation for the optimal location of electric vehicle charging stations
Pierre-Luc Parent
Margarida Carvalho
Miguel F. Anjos
Ribal Atallah
With the increasing effects of climate change, the urgency to step away from fossil fuels is greater than ever before. Electric vehicles (EV… (see more)s) are one way to diminish these effects, but their widespread adoption is often limited by the insufficient availability of charging stations. In this work, our goal is to expand the infrastructure of EV charging stations, in order to provide a better quality of service in terms of user satisfaction (and availability of charging stations). Specifically, our focus is directed towards urban areas. We first propose a model for the assignment of EV charging demand to stations, framing it as a maximum flow problem. This model is the basis for the evaluation of user satisfaction with a given charging infrastructure. Secondly, we incorporate the maximum flow model into a mixed‐integer linear program, where decisions on the opening of new stations and on the expansion of their capacity through additional outlets is accounted for. We showcase our methodology for the city of Montreal, demonstrating the scalability of our approach to handle real‐world scenarios. We conclude that considering both spacial and temporal variations in charging demand is meaningful when solving realistic instances.
2023-12-10
ArXiv (preprint)
doi.org
arxiv.org
A Distributed ADMM-based Deep Learning Approach for Thermal Control in Multi-Zone Buildings
Vincent Taboga
Hanane Dagdougui
The surge in electricity use, coupled with the dependency on intermittent renewable energy sources, poses significant hurdles to effectively… (see more) managing power grids, particularly during times of peak demand. Demand Response programs and energy conservation measures are essential to operate energy grids while ensuring a responsible use of our resources This research combines distributed optimization using ADMM with Deep Learning models to plan indoor temperature setpoints effectively. A two-layer hierarchical structure is used, with a central building coordinator at the upper layer and local controllers at the thermal zone layer. The coordinator must limit the building's maximum power by translating the building's total power to local power targets for each zone. Local controllers can modify the temperature setpoints to meet the local power targets. The resulting control algorithm, called Distributed Planning Networks, is designed to be both adaptable and scalable to many types of buildings, tackling two of the main challenges in the development of such systems. The proposed approach is tested on an 18-zone building modeled in EnergyPlus. The algorithm successfully manages Demand Response peak events.
2023-12-08
ArXiv (preprint)
doi.org
arxiv.org
Filtering Pixel Latent Variables for Unmixing Noisy and Undersampled Volumetric Images
Catherine Bouchard
Andréanne Deschênes
Vincent Boulanger
Jean-Michel Bellavance
Flavie Lavoie-Cardinal
Christian Gagné
2023-12-08
ArXiv (preprint)
arxiv.org
arxiv.org
Harnessing Predictive Modeling and Software Analytics in the Age of LLM-Powered Software Development (Invited Talk)
Foutse Khomh
2023-12-08
International Conference on Predictive Models in Software Engineering (published)
doi.org
Pretrainable Geometric Graph Neural Network for Antibody Affinity Maturation
Huiyu Cai
Zuobai Zhang
Mingkai Wang
Bozitao Zhong
Yanling Wu
Tianlei Ying
Jian Tang
2023-12-07
bioRxiv (preprint)
doi.org
Pretrainable Geometric Graph Neural Network for Antibody Affinity Maturation
Huiyu Cai
Zuobai Zhang
Mingkai Wang
Bozitao Zhong
Yanling Wu
Tianlei Ying
Jian Tang
In the realm of antibody therapeutics development, increasing the binding affinity of an antibody to its target antigen is a crucial task. T… (see more)his paper presents GearBind, a pretrainable deep neural network designed to be effective for in silico affinity maturation. Leveraging multi-level geometric message passing alongside contrastive pretraining on protein structural data, GearBind capably models the complex interplay of atom-level interactions within protein complexes, surpassing previous state-of-the-art approaches on SKEMPI v2 in terms of Pearson correlation, mean absolute error (MAE) and root mean square error (RMSE). In silico experiments elucidate that pretraining helps GearBind become sensitive to mutation-induced binding affinity changes and reflective of amino acid substitution tendency. Using an ensemble model based on pretrained GearBind, we successfully optimize the affinity of CR3022 to the spike (S) protein of the SARS-CoV-2 Omicron strain. Our strategy yields a high success rate with up to 17-fold affinity increase. GearBind proves to be an effective tool in narrowing the search space for in vitro antibody affinity maturation, underscoring the utility of geometric deep learning and adept pre-training in macromolecule interaction modeling.
2023-12-07
bioRxiv (preprint)
doi.org
Anomaly Detection for Scalable Task Grouping in Reinforcement Learning-based RAN Optimization
Jimmy Li
Igor Kozlov
Di Wu
Xue (Steve) Liu
Gregory Dudek
The use of learning-based methods for optimizing cellular radio access networks (RAN) has received increasing attention in recent years. Thi… (see more)s coincides with a rapid increase in the number of cell sites worldwide, driven largely by dramatic growth in cellular network traffic. Training and maintaining learned models that work well across a large number of cell sites has thus become a pertinent problem. This paper proposes a scalable framework for constructing a reinforcement learning policy bank that can perform RAN optimization across a large number of cell sites with varying traffic patterns. Central to our framework is a novel application of anomaly detection techniques to assess the compatibility between sites (tasks) and the policy bank. This allows our framework to intelligently identify when a policy can be reused for a task, and when a new policy needs to be trained and added to the policy bank. Our results show that our approach to compatibility assessment leads to an efficient use of computational resources, by allowing us to construct a performant policy bank without exhaustively training on all tasks, which makes it applicable under real-world constraints.
2023-12-06
ArXiv (preprint)
doi.org
arxiv.org
Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers
Umberto Cappellazzo
Daniele Falavigna
Alessio Brutti
Mirco Ravanelli
The common modus operandi of fine-tuning large pre-trained Transformer models entails the adaptation of all their parameters (i.e., full fin… (see more)e-tuning). While achieving striking results on multiple tasks, this approach becomes unfeasible as the model size and the number of downstream tasks increase. In natural language processing and computer vision, parameter-efficient approaches like prompt-tuning and adapters have emerged as solid alternatives by fine-tuning only a small number of extra parameters, without sacrificing performance accuracy. For audio classification tasks, the Audio Spectrogram Transformer model shows impressive results. However, surprisingly, how to efficiently adapt it to several downstream tasks has not been tackled before. In this paper, we bridge this gap and present a detailed investigation of common parameter-efficient methods, revealing that adapters and LoRA consistently outperform the other methods across four benchmarks. Whereas adapters prove to be more efficient in few-shot learning settings, LoRA turns out to scale better as we increase the number of learnable parameters. We finally carry out ablation studies to find the best configuration for adapters and LoRA.
2023-12-06
ArXiv (preprint)
arxiv.org
arxiv.org