Perouz Taslakian

14 papers · 2019–2026 · 9 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+10 more ↓

🗺️ Taxonomy Completionist (34) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird

🤝 Dynamic Duo (10) 🧬 Topic Evolution 👥 Mega-Team · Squad 👑 Triple Crown ⚡ Prolific Year · Productive 🔥 Unstoppable · Bronze 💎 Century Club · Bronze 🚀 Conference Pioneer 🌈 Renaissance Researcher (6) 🗃️ Keyword Collector (71)

Venues

ICLR (4) EMNLP (2) ICML (2) CLeaR (1) CVPR (1) EACL (1) IJCAI (1) JMLR (1) NeurIPS (1)

Top co-authors

David Vázquez (10) Sai Rajeswar (7) Christopher Pal (7) Juan A. Rodriguez (5) Nicolas Chapados (5) Spandana Gella (4) Joao Monteiro (3) Pierre-André Noël (3) Valentina Zantedeschi (3) Amirhossein Abaskohi (3)

Research topics

Artificial Intelligence (9) Core AI (9) Machine Learning (7) Deep Learning (5) Natural Language Processing (4) Core Methods (4) Computer Vision (3) Knowledge & Reasoning (3) Application Areas (3) Applications (3) Analysis (2) Architectures (2) Generation (2) Learning Types (2) Representation (2)

Keywords

multimodal learning (3) large language model (2) knowledge hypergraph (2) vision-language model (2) document understanding (2) code generation (2) knowledge graph completion (2) link prediction (2) metric learning (1) language modeling (1) benchmark evaluation (1) representation learning (1) image captioning (1) question answering (1) sketch recognition (1) visual question answering (1) multi-view learning (1) hypergraph embedding (1) causal discovery (1) language model evaluation (1)

Papers

StarFlow: Generating Structured Workflow Outputs From Sketch Images EACL 2026 BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks ICLR 2025 InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation ICLR 2025 UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction ICML 2025 VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text ICLR 2025 WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation EMNLP 2025 A Sparsity Principle for Partially Observable Causal Representation Learning ICML 2024 Multi-View Causal Representation Learning with Partial Observability ICLR 2024 RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content NeurIPS 2024 XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference EMNLP 2024 Knowledge Hypergraph Embedding Meets Relational Algebra JMLR 2023 Typing assumptions improve identification in causal discovery CLeaR 2022 Knowledge Hypergraphs: Prediction Beyond Binary Relations IJCAI 2020 Context-Aware Visual Compatibility Prediction CVPR 2019