Joao Monteiro

Researcher, Apple

Joined

September 2018

Names

Joao Monteiro (Preferred)

Emails

****@gmail.com (Confirmed)

****@autodesk.com (Confirmed)

****@apple.com (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

Researcher

Apple (apple.com)

2025 – Present

Researcher

Autodesk (autodesk.com)

2024 – 2025

Researcher

ServiceNow Research (servicenow.com)

2021 – 2024

PhD student

Institut national de la recherche scientifique (inrs.ca)

2017 – 2021

Advisors, Relations & Conflicts

PhD Advisor

Tiago Falk

2017 – 2021

Expertise

No areas of expertise listed

Publications

LaCy: What Small Language Models Can and Should Learn into Limited Parametric Memory
Szilvia Ujváry, Louis Béthune, Pierre Ablin, Joao Monteiro, marco cuturi, Michael Kirchhof
- ICLR 2026 Workshop MemAgents
- Readers: Everyone
Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing
Anastasiia Filippova, David Grangier, marco cuturi, Joao Monteiro
- TTU at ICLR 2026 (Main)
- Readers: Everyone
Learning Unmasking Policies for Diffusion Language Models
Metod Jazbec, Theo X. Olausson, Louis Béthune, Pierre Ablin, Michael Kirchhof, Joao Monteiro, Victor Guilherme Turrisi da Costa, Jason Ramapuram, marco cuturi
- ICLR 2026 DeLTa Workshop Oral
- Readers: Everyone
PairBench: Are Vision-Language Models Reliable at Comparing What They See?
Aarash Feizi, Sai Rajeswar, Adriana Romero-Soriano, Reihaneh Rabbany, Valentina Zantedeschi, Spandana Gella, Joao Monteiro
- Submitted to ICLR 2026
- Readers: Everyone
GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks
Hao Xu, Xiangru Jian, Xinjian Zhao, Wei Pang, Chao Zhang, Suyuchen Wang, Qixin Zhang, Zhengyuan Dong, Joao Monteiro, Bang Liu, Qiuzhuang Sun, Tianshu Yu
- ICLR 2026 Poster
- Readers: Everyone
BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation
Christos Tsirigotis, Vaibhav Adlakha, Joao Monteiro, Aaron Courville, Perouz Taslakian
- COLM 2025
- Readers: Everyone
One Model to Train Them All: Hierarchical Self-Distillation for Enhanced Early Layer Embeddings
Andrea Gurioli, Federico Pennino, Joao Monteiro, Maurizio Gabbrielli
- DL4C @ ICLR 2025
- Readers: Everyone
Explain-Query-Test: Self-Evaluating LLMs Via Explanation and Comprehension Discrepancy
Saeid Asgari, Joao Monteiro
- SSI-FM Poster
- Readers: Everyone
Training Universal Text Encoders with Pair Relevance Classification Loss
Christos Tsirigotis, Vaibhav Adlakha, Joao Monteiro, Aaron Courville, Perouz Taslakian
- Submitted to ICLR 2025
- Readers: Everyone
Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones
Mehrnaz Mofakhami, Reza Bayat, Ioannis Mitliagkas, Joao Monteiro, Valentina Zantedeschi
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone

View all 43 publications

Co-Authors

View all 151 co-authors