Hilaf Hasson

activity

20122026

most citedRobust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms

2 citations · 5 across the 16 of their papers we have counts for

collaborators

19 papers

cs.AI2026

ScalableRAG: High-Quality RAG at Zero Ingestion Cost

Hilaf Hasson, Aditya Chakravarty, Jayant Thomas +1

Recent advances in RAG aim to optimize for performance by paying high ingestion costs for knowledge ingestion: building knowledge graphs or extracting SQL tables. In this work we s…

cs.CL2026

Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval

Padmaja Jonnalagedda, Yuguang Yao, Xiang Gao +2

Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inconsistent schemas and formats…

cs.LG2026

Uncertainty-aware Causal Decision Making via Effect Bound Decomposition

Md Musfiqur Rahman, Ziwei Jiang, Hilaf Hasson +1

Causal inference from observational data can provide strong evidence for finding the best action in a decision-making scenario without having to perform expensive randomized trials…

cs.CL2026

RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning

Xiang Gao, Yuguang Yao, Qi Zhang +5

Large language models (LLMs) often struggle to use tools reliably in domain-specific settings, where APIs may be idiosyncratic, under-documented, or tailored to private workflows.…

cs.LG2025

Node-Level Uncertainty Estimation in LLM-Generated SQL

Hilaf Hasson, Ruocheng Guo

We present a practical framework for detecting errors in LLM-generated SQL by estimating uncertainty at the level of individual nodes in the query's abstract syntax tree (AST). Our…

cs.MA2025

OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration

Shijun Li, Hilaf Hasson, Joydeep Ghosh

Agents powered by advanced large language models (LLMs) have demonstrated impressive capabilities across diverse complex applications. Recently, Multi-Agent Systems (MAS), wherein…

cs.LG2024

Goal-Conditioned Supervised Learning for Multi-Objective Recommendation

Shijun Li, Hilaf Hasson, Jing Hu +1

Multi-objective learning endeavors to concurrently optimize multiple objectives using a single model, aiming to achieve high and balanced performance across diverse objectives. How…

cs.IR2024

HyQE: Ranking Contexts with Hypothetical Query Embeddings

Weichao Zhou, Jiaxin Zhang, Hilaf Hasson +2

In retrieval-augmented systems, context ranking techniques are commonly employed to reorder the retrieved contexts based on their relevance to a user query. A standard approach is…

cs.LG2023

Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting

Hilaf Hasson, Danielle C. Maddix, Yuyang Wang +2

Ensembling is among the most popular tools in machine learning (ML) due to its effectiveness in minimizing variance and thus improving generalization. Most ensembling methods for b…

cs.LG2023

Testing Causality for High Dimensional Data

Arun Jambulapati, Hilaf Hasson, Youngsuk Park +1

Determining causal relationship between high dimensional observations are among the most important tasks in scientific discoveries. In this paper, we revisited the \emph{linear tra…

cs.LG2022★ 2 cited

Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms

Linbo Liu, Youngsuk Park, Trong Nghia Hoang +2

This work studies the threats of adversarial attack on multivariate probabilistic forecasting models and viable defense mechanisms. Our studies discover a new attack pattern that n…

cs.LG2021

Dynamic Regret for Strongly Adaptive Methods and Optimality of Online KRR

Dheeraj Baby, Hilaf Hasson, Yuyang Wang

We consider the framework of non-stationary Online Convex Optimization where a learner seeks to control its dynamic regret against an arbitrary sequence of comparators. When the lo…

math.AG2017

Prime-to- $p$ étale fundamental groups of punctured projective lines over strictly Henselian fields

Hilaf Hasson, Jeffrey Yelton

Let $K$ be the fraction field of a strictly Henselian DVR of characteristic $p \geq 0$ with algebraic closure $K ˉ$ , and let $α_{1}, ..., α_{d} \in P_{K}^{1} (K)$ . In t…

math.AG2017

The $ab c$ Conjecture implies the Weak Diversity Conjecture

Hilaf Hasson, Andrew Obus

We show that the abc Conjecture implies the Weak Diversity Conjecture of Bilu and Luca.

math.AG2014

Arithmetic descent of specializations of Galois covers

Ryan Eberhart, Hilaf Hasson

Given a $G$ -Galois branched cover of the projective line over a number field $K$ , we study whether there exists a closed point of $P_{K}^{1}$ with a connected fiber such that…

math.AG2014

Suzuki-invariant codes from the Suzuki curve

Abdulla Eid, Hilaf Hasson, Amy Ksir +1

In this paper we consider the Suzuki curve $y^{q} + y = x^{q_{0}} (x^{q} + x)$ over the field with $q = 2^{2 m + 1}$ elements. The automorphism group of this curve is known to be the Suzuki…

math.AG2013

Minimal fields of definition for Galois action

Hilaf Hasson

Let $K$ be a field, let $G$ be a finite group, and let $X ˉ \to Y ˉ$ be a $G$ -Galois branched cover of varieties over $K^{se p}$ . Given a mere cover model $X\rightarrow…

math.AG2013★ 1 cited

The fields of definition of branched Galois covers of the projective line

Hilaf Hasson

In this paper I explore the structure of the fields of definition of Galois branched covers of the projective line over \bar Q. The first main result states that every mere cover m…

math.AG2012★ 2 cited

The prime-to-p part of étale fundamental groups of curves

Hilaf Hasson

The previous version of this paper relied on a paper by another author whose proof appears to be invalid in a fundamental way. In arXiv:1707.00649 the author, together with Jeff Ye…

ScalableRAG: High-Quality RAG at Zero Ingestion Cost

Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval

Uncertainty-aware Causal Decision Making via Effect Bound Decomposition

RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning

Node-Level Uncertainty Estimation in LLM-Generated SQL

OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration

Goal-Conditioned Supervised Learning for Multi-Objective Recommendation

HyQE: Ranking Contexts with Hypothetical Query Embeddings

Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting

Testing Causality for High Dimensional Data

Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms

Dynamic Regret for Strongly Adaptive Methods and Optimality of Online KRR

Prime-to-p étale fundamental groups of punctured projective lines over strictly Henselian fields

The abc Conjecture implies the Weak Diversity Conjecture

Arithmetic descent of specializations of Galois covers

Suzuki-invariant codes from the Suzuki curve

Minimal fields of definition for Galois action

The fields of definition of branched Galois covers of the projective line

The prime-to-p part of étale fundamental groups of curves

Prime-to- $p$ étale fundamental groups of punctured projective lines over strictly Henselian fields

The $ab c$ Conjecture implies the Weak Diversity Conjecture