activity
20242026
most citedGeneral Geospatial Inference with a Population Dynamics Foundation Model

3 citations · 4 across the 3 of their papers we have counts for

collaborators
Showing 2024Show all

5 papers · 1 filter

cs.LG2024

Best of Both Worlds: Advantages of Hybrid Graph Sequence Models

Ali Behrouz, Ali Parviz, Mahdi Karami +3

Modern sequence models (e.g., Transformers, linear RNNs, etc.) emerged as dominant backbones of recent deep learning frameworks, mainly due to their efficiency, representational po…

cs.LG2024

Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights

Zhikai Chen, Haitao Mao, Jingzhe Liu +8

Given the ubiquity of graph data and its applications in diverse domains, building a Graph Foundation Model (GFM) that can work well across different graphs and tasks with a unifie…

cs.CL2024

Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning

Bahare Fatemi, Mehran Kazemi, Anton Tsitsulin +6

Large language models (LLMs) have showcased remarkable reasoning capabilities, yet they remain susceptible to errors, particularly in temporal reasoning tasks involving complex tem…

cs.LG2024

Understanding Transformer Reasoning Capabilities via Graph Algorithms

Clayton Sanford, Bahare Fatemi, Ethan Hall +5

Which transformer scaling regimes are able to perfectly solve different classes of algorithmic problems? While tremendous empirical advances have been attained by transformer-based…

cs.CL2024

Don't Forget to Connect! Improving RAG with Graph-based Reranking

Jialin Dong, Bahare Fatemi, Bryan Perozzi +2

Retrieval Augmented Generation (RAG) has greatly improved the performance of Large Language Model (LLM) responses by grounding generation with context from existing documents. Thes…