Publications - Majid Daliri

Research in action

TurboQuant Vector quantization Latent reasoning Exploration for RL Math olympiads Data & evaluation Graph search Nearest neighbors Data sketching Coordinated sampling KDEformer Efficient attention

You can also find my articles on my Google Scholar profile.

Preprints

Preprint 2026

Singular Value Perturbation: Unlocking RL Performance via Diverse Latent Reasoning

Jihwan Shin, Majid Daliri, Vahab Mirrokni, Amir Zandieh, Insu Han

Paper link not yet available.

Project

2026

On Worst-Case Guarantees for Graph-Based Nearest-Neighbor Search

Majid Daliri, Mohammadreza Daneshvaramoli, Purna Dutta, Edo Liberty, Cameron N. Musco, Christopher Musco, Torsten Suel

Paper link not yet available.

VecDB Workshop @ VLDB 2026

Quantizing Sampling-Based Inner Product Sketches

Gabriel M. Silva, Aécio Santos, Majid Daliri, Juliana Freire, Christopher Musco

Workshop paper

MosaicJoin: Compact Semantic Sketches for Value-Level Join Discovery

Grace Fan, Eden Wu, Majid Daliri, Juliana Freire

ATLAS: Learning to Optimally Memorize the Context at Test Time

Ali Behrouz, Zeman Li, Praneeth Kacham, Majid Daliri, Yuan Deng, Peilin Zhong, Meisam Razaviyayn, Vahab Mirrokni

TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate

Amir Zandieh, Majid Daliri, Majid Hadian, Vahab Mirrokni

2025

MATH-AI Workshop @ NeurIPS 2025

RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows

Hamed Mahdavi, Pouria Mahdavinia, Samira Malek, Pegah Mohammadipour, Alireza Hashemi, Majid Daliri, Alireza Farhadi, Amir Khasahmadi, Niloofar Mireshghallah, Vasant Honavar

MATH-AI Workshop @ NeurIPS 2025

CombiGraph-Vis: A Curated Multimodal Olympiad Benchmark for Discrete Mathematical Reasoning

Hamed Mahdavi, Pouria Mahdavinia, Alireza Farhadi, Pegah Mohammadipour, Samira Malek, Majid Daliri, Pedram Mohammadipour, Alireza Hashemi, Amir Khasahmadi, Vasant Honavar

Brains vs. Bytes: Evaluating LLM Proficiency in Olympiad Mathematics

Hamed Mahdavi, Alireza Hashemi, Majid Daliri, Pegah Mohammadipour, Alireza Farhadi, Samira Malek, Yekta Yazdanifard, Amir Khasahmadi, Vasant Honavar

Coupling without Communication and Drafter-Invariant Speculative Decoding

Majid Daliri, Christopher Musco, Ananda Theertha Suresh

Unlock the Theory behind Scaling 1-bit Neural Networks

Majid Daliri, Zhao Song, Chiwun Yang

QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead

Amir Zandieh, Majid Daliri, Insu Han

Matrix Product Sketching via Coordinated Sampling

Majid Daliri, Juliana Freire, Danrong Li, Christopher Musco

2024

Sampling Methods for Inner Product Sketching

Majid Daliri, Juliana Freire, Christopher Musco, Aécio Santos, Haoxiang Zhang

Simple Analysis of Priority Sampling

Majid Daliri, Juliana Freire, Christopher Musco, Aécio Santos, Haoxiang Zhang

2023

KDEformer: Accelerating Transformers via Kernel Density Estimation

Amir Zandieh, Insu Han*, Majid Daliri*, Amin Karbasi

* Equal contribution

Weighted Minwise Hashing Beats Linear Sketching for Inner Product Estimation

Aline Bessa, Majid Daliri, Juliana Freire, Cameron Musco, Christopher Musco, Aécio Santos, Haoxiang Zhang

2022

Efficient Approximations for Cache-conscious Data Placement

Ali Ahmadi, Majid Daliri, Amir Kafshdar Goharshady, Andreas Pavlogiannis

A 10-Approximation of the π/2-MST

Ahmad Biniaz, Majid Daliri, AmirHossein Moradpour

Proceedings