14 papers
From Citations to Contributions: LLM-Assisted Credit Scoring of Research Articles
Sana Ebrahimi, Suraj Shetiya, Abolfazl Asudeh
Citation-based measures of scientific influence typically treat citations as uniform signals, ignoring the different roles that cited works play in a paper's contribution. We intro…
Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache
Mohsen Dehghankar, Abolfazl Asudeh
Sparse attention improves LLM inference efficiency by selecting a subset of key-value entries, but at the cost of potential accuracy degradation. In particular, omitting critical K…
NeedleDB: A Generative-AI Based System for Accurate and Efficient Image Retrieval using Complex Natural Language Queries
Mahdi Erfanian, Abolfazl Asudeh
We demonstrate NeedleDB, an open-source, deployment-ready database system for answering complex natural language queries over image data. Unlike existing approaches that rely on co…
RSR-core: A High-Performance Engine for Low-Bit Matrix-Vector Multiplication
Mohsen Dehghankar, Abolfazl Asudeh
Matrix-vector multiplication is a fundamental building block in neural networks, vector databases, and large language models, particularly during inference. As a result, efficient…
Dynamic Necklace Splitting
Rishi Advani, Abolfazl Asudeh, Mohsen Dehghankar +1
The necklace splitting problem is a classic problem in fair division with many applications, including data-informed fair hash maps. We extend necklace splitting to a dynamic setti…
Random-Access Ranked Retrieval and Similarity Search
Mohsen Dehghankar, Abolfazl Asudeh, Raghav Mittal +2
We extend Random Access, a fundamental operation that enables efficient search and exploration algorithms, to the modern interactive data systems based on Ranked Retrieval and Simi…
On Fair Epsilon Net and Geometric Hitting Set
Mohsen Dehghankar, Stavros Sintos, Abolfazl Asudeh
Fairness has emerged as a formidable challenge in data-driven decisions. Many of the data problems, such as creating compact data summaries for approximate query processing, can be…
An Adversary-Resistant Multi-Agent LLM System via Credibility Scoring
Sana Ebrahimi, Mohsen Dehghankar, Abolfazl Asudeh
While multi-agent LLM systems show strong capabilities in various domains, they are highly vulnerable to adversarial and low-performing agents. To resolve this issue, in this paper…
HENN: A Hierarchical Epsilon Net Navigation Graph for Approximate Nearest Neighbor Search
Mohsen Dehghankar, Abolfazl Asudeh
Hierarchical graph-based algorithms such as HNSW have achieved state-of-the-art performance for Approximate Nearest Neighbor (ANN) search in practice, yet they often lack theoretic…
Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries
Mahdi Erfanian, Mohsen Dehghankar, Abolfazl Asudeh
Multi-modal datasets, like those involving images, often miss the detailed descriptions that properly capture the rich information encoded in each item. This makes answering comple…
Rank It, Then Ask It: Input Reranking for Maximizing the Performance of LLMs on Symmetric Tasks
Mohsen Dehghankar, Abolfazl Asudeh
Large language models (LLMs) have quickly emerged as practical and versatile tools that provide new solutions for a wide range of domains. In this paper, we consider the applicatio…
An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks
Mohsen Dehghankar, Mahdi Erfanian, Abolfazl Asudeh
Despite their tremendous success and versatility, Deep Neural Networks (DNNs) such as Large Language Models (LLMs) suffer from inference inefficiency and rely on advanced computati…
Mining the Minoria: Unknown, Under-represented, and Under-performing Minority Groups
Mohsen Dehghankar, Abolfazl Asudeh
Due to a variety of reasons, such as privacy, data in the wild often misses the grouping information required for identifying minorities. On the other hand, it is known that machin…
[Experiments & Analysis] Evaluating the Feasibility of Sampling-Based Techniques for Training Multilayer Perceptrons
Sana Ebrahimi, Rishi Advani, Abolfazl Asudeh
The training process of neural networks is known to be time-consuming, and having a deep architecture only aggravates the issue. This process consists mostly of matrix operations,…