Publications

No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms

Joshua Kazdan, Abhay Puri, Lisa Yu, Rylan Schaeffer, Chris Cundy, Sanmi Koyejo, Krishnamurthy (Dj) Dvijotham

VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing

Juan A. Rodriguez, Haotian Zhang, Abhay Puri, Tianyu Zhang, Rishav Pramanik, et al.

Scale Dependent Data Duplication

Joshua Kazdan, Noam Levi, Rylan Schaeffer, Jessica Chudnovsky, Abhay Puri, Bo He, et al.

Quantifying the Effect of Test Set Contamination on Generative Evaluations

Rylan Schaeffer, Joshua Kazdan, Baber Abbasi, Ken Ziyu Liu, Brando Miranda, Ahmed Ahmed, Abhay Puri, et al.

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

Juan A. Rodriguez*, Haotian Zhang*, Abhay Puri, Aarash Feizi, Rishav Pramanik, Pascal Wichmann, Arnab Mondal, Mohammad Reza Samsami, Rabiul Awal, Perouz Taslakian, Spandana Gella, Sai Rajeswar Mudumba, David Vazquez, Christopher Pal, Marco Pedersoli

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

Ahmed Masry, Juan A. Rodriguez, Tianyu Zhang, Suyuchen Wang, Chao Wang, Aarash Feizi, Akshay Kalkunte, Abhay Puri, Xiangru Jian, Pierre-André Noël, Sathwik Madhusudhan, Marco Pedersoli, Bang Liu, Nicolas Chapados, Yoshua Bengio, Enamul Hoque Prince, Christopher Pal, Issam H. Laradji, David Vazquez, Perouz Taslakian, Spandana Gella, Sai Rajeswar Mudumba

DoomArena: A Framework for Testing AI Agents Against Evolving Security Threats

Abhay Puri*, Léo Boisvert*, Mihir Bansal*, Chandra Kiran Reddy Evuru*, Gabriel Huang*, Avinandan Bose*, Maryam Fazel, Quentin Cappart, Jason Stanley, Alexandre Lacoste, Alexandre Drouin, Krishnamurthy (Dj) Dvijotham

BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning

Ahmed Masry, Abhay Puri, Masoud Hashemi, Juan A. Rodriguez, Megh Thakkar, Khyati Mahajan, Vikas Yadav, Sathwik Tejaswi Madhusudhan, Alexandre Piche, Dzmitry Bahdanau, Christopher Pal, David Vazquez, Enamul Hoque Prince, Perouz Taslakian, Sai Rajeswar Mudumba, Spandana Gella

StarVector: Generating Scalable Vector Graphics Code from Images and Text

Juan A. Rodriguez, Abhay Puri, Shubham Agarwal, Issam H. Laradji, Pau Rodriguez, Sai Rajeswar Mudumba, David Vazquez, Christopher Pal, Marco Pedersoli

LitLLMs, LLMs for Literature Review: Are We There Yet?

Abhay Puri*, Shubham Agarwal*, Gaurav Sahu*, Issam H. Laradji, Krishnamurthy (Dj) Dvijotham, Jason Stanley, Laurent Charlin, Christopher Pal

BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks

Abhay Puri*, Juan A. Rodriguez*, Xiangru Jian*, Siba Smarak Panigrahi*, Tianyu Zhang*, Aarash Feizi*, et al.

InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation

Gaurav Sahu, Abhay Puri, Juan A. Rodriguez, Amirhossein Abaskohi, Mohammad (Aaron) Chegini, Alexandre Drouin, Perouz Taslakian, Valentina Zantedeschi, Alexandre Lacoste, David Vazquez, Nicolas Chapados, Christopher Pal, Sai Rajeswar Mudumba, Issam H. Laradji

Shifting AI Security to the Left: Design-Time Defenses to Mitigate the Risks of Prompt Injections

Abhay Puri, Kevin Kasa, Kiarash Mohammadi, Georges Belanger Albarran, Mihir Bansal, Yanick Chénard, Marc-Etienne Brunet, Jason Stanley

Attack What Matters: Integrating Expert Insight and Automation in Threat-Model-Aligned Red Teaming

Kiarash Mohammadi, Abhay Puri, Georges Belanger Albarran, Mihir Bansal, Navdeep Gill, Yanick Chénard, Segan Subramanian, Marc-Etienne Brunet, Jason Stanley

Silent Sabotage: Injecting Backdoors into AI Agents Through Fine-Tuning

Abhay Puri*, Léo Boisvert*, Chandra Kiran Reddy Evuru*, Joshua Kazdan, Avinandan Bose, Quentin Cappart, Maryam Fazel, Sai Rajeswar Mudumba, Jason Stanley, Nicolas Chapados, Alexandre Drouin, Krishnamurthy (Dj) Dvijotham

Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?

Rishika Bhagwatkar*, Kevin Kasa*, Abhay Puri, Gabriel Huang, Irina Rish, Graham W. Taylor, et al.

Evaluating and Improving LitLLMs with Deep Research

Gaurav Sahu, Shubham Agarwal, Abhay Puri, Issam H. Laradji, Krishnamurthy (Dj) Dvijotham, Jason Stanley, Laurent Charlin, et al.

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain

Abhay Puri*, Léo Boisvert*, Chandra Kiran Reddy Evuru, Nicolas Chapados, Quentin Cappart, Alexandre Lacoste, et al.

LitLLM: A Toolkit for Scientific Literature Review

Abhay Puri*, Shubham Agarwal*, Gaurav Sahu*, Issam H. Laradji, Krishnamurthy (Dj) Dvijotham, Jason Stanley, Laurent Charlin, Christopher Pal

StarVector: Generating Scalable Vector Graphics Code from Images and Text

Juan A. Rodriguez, Abhay Puri, Shubham Agarwal, Issam H. Laradji, Pau Rodriguez, Sai Rajeswar Mudumba, David Vazquez, Christopher Pal, Marco Pedersoli