Search Results for author: Perouz Taslakian

Found 16 papers, 9 papers with code

ReTreever: Tree-based Coarse-to-Fine Representations for Retrieval

no code implementations11 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.

Answer Generation Question Answering +1

RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content

1 code implementation17 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.

Benchmarking General Knowledge +3

VCR: Visual Caption Restoration

1 code implementation10 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.

Language Modeling Language Modelling +4

Multi-View Causal Representation Learning with Partial Observability

1 code implementation7 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.

Contrastive Learning Disentanglement

Using Graph Algorithms to Pretrain Graph Completion Transformers

no code implementations14 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.

Knowledge Graph Completion Knowledge Graph Embedding +1

Typing assumptions improve identification in causal discovery

1 code implementation22 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.

Causal Discovery

Knowledge Hypergraph Embedding Meets Relational Algebra

1 code implementation18 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.

hypergraph embedding Knowledge Graphs +1

Efficient Multi-Robot Coverage of a Known Environment

no code implementations7 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.