iOS World Agents – Embodied AI Evaluation Framework
Embodied evaluation framework for LLM-driven agents executing real iOS actions in simulator environments.
Embodied evaluation framework for LLM-driven agents executing real iOS actions in simulator environments.
Serverless multi-agent cybersecurity system for real-time threat detection and compliance enforcement.
On-Site Manufacturing Co-Pilot — A local-first AI agent system deployed inside factories to help operators, supervisors, and managers make decisions in real time..
RAG-based AI assistant for semantic search and knowledge retrieval in Confluence.
Dynamic Depth Allocation via Second-Order Residual Dynamics.
Training Transformer Embeddings for Semantic Search.
Teaching Large Reasoning Models when to think — and when not to
Published in Journal 1, 2010
This paper is about the number 2. The number 3 is left for future work.
Recommended citation: Your Name, You. (2010). "Paper Title Number 2." Journal 1. 1(2).
Download Paper | Download Slides
Published in IEEE INDICON 2022 (19th India Council International Conference), 2022
🟢 Accepted @ IEEE INDICON 2022. Keywords: Medical Image Segmentation, U-Net, Cardiac Imaging, Deep Learning.
Published in NLDB 2025 (Natural Language Processing and Information Systems), 2025
🟢 Presented at NLDB 2025. Keywords: Multimodal Learning, Vision–Language Models, Disaster Detection. We present a systematic study of multimodal disaster event detection on social media, comparing supervised fusion models with LLM-based approaches; while LLMs are robust to noisy language, supervised multimodal systems remain more reliable for structured event classification.
Published in NeurIPS 2026 (Planned Submission), 2025
🔵 Research in Progress. Upcoming NeurIPS submission on Latent-to-Parameter Transfer (LPT), a hypernetwork-based framework that conditions on teacher latent states to generate adaptive LoRA parameters for efficient reasoning transfer.
Published in ACL 2026 (Association for Computational Linguistics), 2026
🟡 Under Review at ACL 2026. Training-free universal UI grounding using experience-based similarity and elastic visual memory.
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.