no code implementations • 11 Feb 2025 • Shubham Gupta, Zichao Li, Tianyi Chen, Cem Subakan, Siva Reddy, Perouz Taslakian, Valentina Zantedeschi
In this paper, we propose a tree-based method for organizing and representing reference documents at various granular levels, which offers the flexibility to balance cost and utility, and eases the inspection of the corpus content and retrieval operations.
no code implementations • 5 Dec 2024 • Juan Rodriguez, Xiangru Jian, Siba Smarak Panigrahi, Tianyu Zhang, Aarash Feizi, Abhay Puri, Akshay Kalkunte, François Savard, Ahmed Masry, Shravan Nayak, Rabiul Awal, Mahsa Massoud, Amirhossein Abaskohi, Zichao Li, Suyuchen Wang, Pierre-André Noël, Mats Leon Richter, Saverio Vadacchino, Shubbam Agarwal, Sanket Biswas, Sara Shanian, Ying Zhang, Noah Bolger, Kurt MacDonald, Simon Fauvel, Sathwik Tejaswi, Srinivas Sunkara, Joao Monteiro, Krishnamurthy Dj Dvijotham, Torsten Scholak, Nicolas Chapados, Sepideh Kharagani, Sean Hughes, M. Özsu, Siva Reddy, Marco Pedersoli, Yoshua Bengio, Christopher Pal, Issam Laradji, Spandanna Gella, Perouz Taslakian, David Vazquez, Sai Rajeswar
We use an efficient data curation process to ensure our data is high-quality and license-permissive.
1 code implementation • 8 Jul 2024 • Gaurav Sahu, Abhay Puri, Juan Rodriguez, Amirhossein Abaskohi, Mohammad Chegini, Alexandre Drouin, Perouz Taslakian, Valentina Zantedeschi, Alexandre Lacoste, David Vazquez, Nicolas Chapados, Christopher Pal, Sai Rajeswar Mudumba, Issam Hadj Laradji
We also compare the performance of open- and closed-source LLMs and various evaluation strategies.
1 code implementation • 17 Jun 2024 • Joao Monteiro, Pierre-Andre Noel, Etienne Marcotte, Sai Rajeswar, Valentina Zantedeschi, David Vazquez, Nicolas Chapados, Christopher Pal, Perouz Taslakian
We run a large-scale benchmark comprising several state-of-the-art LLMs to uncover differences in performance across models of various types and sizes in a context-conditional language modeling setting.
1 code implementation • 10 Jun 2024 • Tianyu Zhang, Suyuchen Wang, Lu Li, Ge Zhang, Perouz Taslakian, Sai Rajeswar, Jie Fu, Bang Liu, Yoshua Bengio
This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images.
no code implementations • 23 Apr 2024 • João Monteiro, Étienne Marcotte, Pierre-André Noël, Valentina Zantedeschi, David Vázquez, Nicolas Chapados, Christopher Pal, Perouz Taslakian
Just-in-time processing of a context is inefficient due to the quadratic cost of self-attention operations, and caching is desirable.
1 code implementation • 13 Mar 2024 • Danru Xu, Dingling Yao, Sébastien Lachapelle, Perouz Taslakian, Julius von Kügelgen, Francesco Locatello, Sara Magliacane
Causal representation learning aims at identifying high-level causal variables from perceptual data.
no code implementations • 21 Dec 2023 • Issam Laradji, Perouz Taslakian, Sai Rajeswar, Valentina Zantedeschi, Alexandre Lacoste, Nicolas Chapados, David Vazquez, Christopher Pal, Alexandre Drouin
The extraction of a small number of relevant insights from vast amounts of data is a crucial component of data-driven decision-making.
1 code implementation • 7 Nov 2023 • Dingling Yao, Danru Xu, Sébastien Lachapelle, Sara Magliacane, Perouz Taslakian, Georg Martius, Julius von Kügelgen, Francesco Locatello
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities.
no code implementations • 28 Oct 2023 • Rim Assouel, Pau Rodriguez, Perouz Taslakian, David Vazquez, Yoshua Bengio
A key aspect of human intelligence is the ability to imagine -- composing learned concepts in novel ways -- to make sense of new scenarios.
no code implementations • 14 Oct 2022 • Jonathan Pilault, Michael Galkin, Bahare Fatemi, Perouz Taslakian, David Vasquez, Christopher Pal
While using our new path-finding algorithm as a pretraining signal provides 2-3% MRR improvements, we show that pretraining on all signals together gives the best knowledge graph completion results.
1 code implementation • 22 Jul 2021 • Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste, Sebastien Lachapelle, Alexandre Drouin
Causal discovery from observational data is a challenging task that can only be solved up to a set of equivalent solutions, called an equivalence class.
1 code implementation • 18 Feb 2021 • Bahare Fatemi, Perouz Taslakian, David Vazquez, David Poole
Embedding-based methods for reasoning in knowledge hypergraphs learn a representation for each entity and relation.
1 code implementation • 1 Jun 2019 • Bahare Fatemi, Perouz Taslakian, David Vazquez, David Poole
Knowledge graphs store facts using relations between two entities.
1 code implementation • CVPR 2019 • Guillem Cucurull, Perouz Taslakian, David Vazquez
How do we determine whether two or more clothing items are compatible or visually appealing?
Ranked #1 on
Slot Filling
on Polyvore
no code implementations • 7 Aug 2018 • Nare Karapetyan, Kelly Benson, Chris McKinney, Perouz Taslakian, Ioannis Rekleitis
In this paper we present two approximation heuristics for solving the multi-robot coverage problem.