◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Milad Nasr

43 papers hereh-index 3315.3k citations85 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author11
  • middle author22
  • last author5

Across the 38 of 43 papers where every author was matched, so the position is known.

fields
  • cs.CR26
  • cs.LG10
  • cs.AI2
  • stat.ML2
  • cs.CL1
  • cs.CY1
same name
  • Milad Nasr — 6 papers

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20172026
most citedScalable Extraction of Training Data from (Production) Language Models

83 citations · 156 across the 25 of their papers we have counts for

collaborators
Showing cs.AIShow all

2 papers · 1 filter

cs.AI2026

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs

Chuan Guo, Juan Felipe Ceron Uribe, Sicheng Zhu +10

Instruction hierarchy (IH) defines how LLMs prioritize system, developer, user, and tool instructions under conflict, providing a concrete, trust-ordered policy for resolving instr…

cs.AI2025

Rebellion: Noise-Robust Reasoning Training for Audio Reasoning Models

Tiansheng Huang, Virat Shejwalkar, Oscar Chang +2

Instilling reasoning capabilities in large models (LMs) using reasoning training (RT) significantly improves LMs' performances. Thus Audio Reasoning Models (ARMs), i.e., audio LMs…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.