Connect Session: Advances in Vision-Language Models (VLM)

🔗 Connect Session: Advances in Vision-Language Models (VLM)

📅 Date: 2nd July 2025
🕔 Time: 17:00–18:00 (UTC)
📍 Hosted by: ResearchTrend.AI
🎟️ Register now: https://lnkd.in/e8DW4vkw

We’re excited to invite you to an upcoming Connect Session highlighting cutting-edge research in Vision-Language Models, featuring innovative work from researchers at UNC Chapel Hill and UIUC.

🚀 Agenda:
🔹 17:00 – 17:05 | Welcome & Introduction

🔹 17:05 – 17:15 | David Wan (UNC Chapel Hill)
📄 CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval

🔹 17:20 – 17:30 | Yao Xiao (University of Illinois at Urbana-Champaign)
📄 TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models

💬 17:35 – 18:00 | Interactive Discussion

Join the discussion on retrieval, alignment, and representation in state-of-the-art VLMs with two outstanding researchers in the field.

This session is ideal for those working in multimodal AI, information retrieval, and vision-language understanding.

👉 Register here: https://lnkd.in/e8DW4vkw

Follow ResearchTrend.AI to stay connected with leading minds in AI.