Author

Abhay Puri

Observed name: Puri, Abhay

Observed institution: ServiceNow (United States)

ORCID: 0009-0003-9370-0814

Observed ORCID: 0009-0003-9370-0814

OpenAlex ID: A5103305840

StarVector: Generating Scalable Vector Graphics Code from Images and Text

2025 · Juan A. Rodriguez, Abhay Puri, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 18

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

2025 · Ahmed Masry, Juan Rodriguez, et al. · neural information processing systems · 5

PDF

LitLLMs, LLMs for Literature Review: Are we there yet?

2024 · Agarwal, Shubham, Sahu, Gaurav, et al. · arXiv (Cornell University) · 5

PDF

StarVector: Generating Scalable Vector Graphics Code from Images and Text

2025 · Juan A. Rodriguez, Abhay Puri, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 3

PDF

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

2025 · Juan Rodriguez, Haotian Zhang, et al. · neural information processing systems · 1

PDF

KV-streams for Efficient Compaction in Agentic Reinforcement Learning

2026 · Penaloza, Emiliano, Malenfant, Dane, et al. · arXiv (Cornell University)

PDF

Backdoor Decontamination Dynamics in LLM Agents

2026 · Huang, Gabriel, Puri, Abhay, et al. · arXiv (Cornell University)

PDF

PrivacyAlign: Contextual Privacy Alignment for LLM Agents

2026 · Tamber, Manveer Singh, Puri, Abhay, et al. · arXiv (Cornell University)

PDF

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

2026 · Léo Boisvert, Abhay Puri, et al. · ACM Conference on AI and Agentic Systems (CAIS)

Scale Dependent Data Duplication

2026 · Kazdan, Joshua, Levi, Noam, et al. · arXiv (Cornell University)

PDF

Quantifying the Effect of Test Set Contamination on Generative Evaluations

2026 · Schaeffer, Rylan, Kazdan, Joshua, et al. · arXiv (Cornell University)

PDF

VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing

2026 · Joan Rodriguez, Haotian Zhang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

PDF

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

2025 · Bhagwatkar, Rishika, Kasa, Kevin, et al. · arXiv (Cornell University)

PDF

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

2025 · Boisvert, Leo, Bansal, Mihir, et al. · arXiv (Cornell University)

PDF

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

2025 · Kazdan, Joshua, Puri, Abhay, et al. · arXiv (Cornell University)

PDF

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

2024 · Sahu, Gaurav, Puri, Abhay, et al. · arXiv (Cornell University)

PDF

Works count: 18

Citation count: 33

H-index: 3

I10-index: 1