Search Results for author: Kian Ahrabian

Found 7 papers, 2 papers with code

MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning

1 code implementation21 Apr 2024 Yifan Jiang, Jiarui Zhang, Kexuan Sun, Zhivar Sourati, Kian Ahrabian, Kaixin Ma, Filip Ilievski, Jay Pujara

Further analysis of perception questions reveals that MLLMs struggle to comprehend the visual features (near-random performance) and even count the panels in the puzzle ( <45%), hindering their ability for abstract reasoning.

Visual Reasoning

The Curious Case of Nonverbal Abstract Reasoning with Multi-Modal Large Language Models

no code implementations22 Jan 2024 Kian Ahrabian, Zhivar Sourati, Kexuan Sun, Jiarui Zhang, Yifan Jiang, Fred Morstatter, Jay Pujara

While large language models (LLMs) are still being adopted to new domains and utilized in novel applications, we are experiencing an influx of the new generation of foundation models, namely multi-modal large language models (MLLMs).

Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning

1 code implementation17 May 2023 Dong-Ho Lee, Kian Ahrabian, Woojeong Jin, Fred Morstatter, Jay Pujara

This shows that prior semantic knowledge is unnecessary; instead, LLMs can leverage the existing patterns in the context to achieve such performance.

In-Context Learning

PubGraph: A Large-Scale Scientific Knowledge Graph

no code implementations4 Feb 2023 Kian Ahrabian, Xinwei Du, Richard Delwin Myloth, Arun Baalaaji Sankar Ananthan, Jay Pujara

In this paper, we present PubGraph, a new resource for studying scientific progress that takes the form of a large-scale knowledge graph (KG) with more than 385M entities, 13B main edges, and 1. 5B qualifier edges.

Community Detection Knowledge Graph Completion +2

Structure Aware Negative Sampling in Knowledge Graphs

no code implementations EMNLP 2020 Kian Ahrabian, Aarash Feizi, Yasmin Salehi, William L. Hamilton, Avishek Joey Bose

Learning low-dimensional representations for entities and relations in knowledge graphs using contrastive estimation represents a scalable and effective method for inferring connectivity patterns.

Contrastive Learning Knowledge Graphs

Software Engineering Event Modeling using Relative Time in Temporal Knowledge Graphs

no code implementations2 Jul 2020 Kian Ahrabian, Daniel Tarlow, Hehuimin Cheng, Jin L. C. Guo

We present a multi-relational temporal Knowledge Graph based on the daily interactions between artifacts in GitHub, one of the largest social coding platforms.

Knowledge Graphs Link Prediction +1

On Usage of Autoencoders and Siamese Networks for Online Handwritten Signature Verification

no code implementations7 Dec 2017 Kian Ahrabian, Bagher BabaAli

In this paper, we propose a novel writer-independent global feature extraction framework for the task of automatic signature verification which aims to make robust systems for automatically distinguishing negative and positive samples.

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