Harsh Agrawal

18 papers · 2016–2025 · 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 ↓

+7 more ↓

🗺️ Taxonomy Completionist (32) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird

🤝 Dynamic Duo (11) 🧭 Keyword Pioneer 🌈 Renaissance Researcher (5) 🔥 Unstoppable · Bronze ❓ The Questioner 💎 Century Club · Bronze 🗃️ Keyword Collector (69)

Venues

ICCV (5) CVPR (2) ECCV (2) EMNLP (2) ICLR (2) NeurIPS (2) AAAI (1) ACL (1) UAI (1)

Top co-authors

Dhruv Batra (11) Devi Parikh (5) Andrew Szot (4) Bogdan Mazoure (3) Peter Anderson (3) Yash Kant (3) Alexander Toshev (3) Yinfei Yang (2) Abhinav Moudgil (2) Zhe Gan (2)

Research topics

Artificial Intelligence (11) Core AI (9) Computer Vision (5) Deep Learning (5) Machine Learning (4) Learning Types (3) Models (3) Natural Language Processing (2) Robotics (2) Analysis (2) Application Areas (2) Capabilities (2) Generation (2) Learning Paradigms (2) Reinforcement Learning (1)

Keywords

multimodal large language model (3) object detection (3) embodied ai (3) vision-language navigation (2) data augmentation (2) multimodal learning (2) reinforcement learning (2) dialogue generation (1) knowledge distillation (1) image generation (1) visual question answering (1) visual grounding (1) few-shot learning (1) scene understanding (1) depth estimation (1) image captioning (1) policy learning (1) visual navigation (1) transfer learning (1) zero-shot learning (1)

Papers

Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms ICLR 2025 From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons CVPR 2025 UINavBench: A Framework for Comprehensive Evaluation of Interactive Digital Agents ICCV 2025 Grounding Multimodal Large Language Models in Actions NeurIPS 2024 Large Language Models as Generalizable Policies for Embodied Tasks ICLR 2024 Multimodal Persona Based Generation of Comic Dialogs ACL 2023 Simple and Effective Synthesis of Indoor 3D Scenes AAAI 2023 Housekeep: Tidying Virtual Households Using Commonsense Reasoning ECCV 2022 Contrast and Classify: Training Robust VQA Models ICCV 2021 Known unknowns: Learning novel concepts using reasoning-by-elimination UAI 2021 SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation NeurIPS 2021 The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation ICCV 2021 Spatially Aware Multimodal Transformers for TextVQA ECCV 2020 nocaps: novel object captioning at scale ICCV 2019 Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning ICCV 2019 Human Attention in Visual Question Answering: Do Humans and Deep Networks look at the same regions? EMNLP 2016 Object-Proposal Evaluation Protocol is 'Gameable' CVPR 2016 Sort Story: Sorting Jumbled Images and Captions into Stories EMNLP 2016