ResearchTrend Connect | LLMAG VLM FedML

Join us for a ResearchTrend Connect session focused on Large-Language Model Agents + Vision-Language Models + Federated Machine Learning (LLMAG VLM FedML). This is an opportunity to connect with fellow researchers, share insights, and discuss the latest developments. The session will be hosted online via Zoom.

Why join us

• Engage directly with authors of cutting-edge papers in Large-Language Model Agents + Vision-Language Models + Federated Machine Learning.
• Participate in free (bi-)weekly online sessions featuring current research without registration fees or travel expenses.
• Connect with peers through our interactive format.
• Watch recordings of past sessions on our YouTube channel.

Agenda

16:00 - 16:05 (UTC) LLMAG	Introduction
16:05 - 16:15 (UTC) LLMAG	Tianci Xue (The Ohio State University) - An Illusion of Progress? Assessing the Current State of Web Agents
16:20 - 16:30 (UTC) LLMAG	Sherzod Hakimov (University of Potsdam) - Plant in Cupboard, Orange on Rably, Inat Aphone. Benchmarking Incremental Learning of Situation and Language Model using a Text-Simulated Situated Environment
16:35 - 17:00 (UTC) LLMAG	Interactive discussion
17:00 - 17:05 (UTC) VLM	Introduction
17:05 - 17:15 (UTC) VLM	Davide Talon (Fondazione Bruno Kessler) - Seeing the Abstract: Translating the Abstract Language for Vision Language Models
17:20 - 17:30 (UTC) VLM	Mir Rayat Imtiaz Hossain (University of British Columbia ) - The Power of One: A Single Example is All it Takes for Segmentation in VLMs
17:35 - 18:00 (UTC) VLM	Interactive discussion
18:00 - 18:05 (UTC) FedML	Introduction
18:05 - 19:00 (UTC) FedML	Interactive discussion

Visit our event page at: https://researchtrend.ai/social-events/researchtrend-connect-llmag-vlm-fedml

We look forward to seeing you there!