ResearchTrend Connect | VLM LLMAG AIFin

Join us for a ResearchTrend Connect session focused on Vision-Language Models + Large-Language Model Agents + AI in Finance (VLM LLMAG AIFin). 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 Vision-Language Models + Large-Language Model Agents + AI in Finance.
• 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) VLM	Introduction
16:05 - 16:15 (UTC) VLM	Matteo Merler (Fondazione Bruno Kessler) - ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models
16:20 - 16:30 (UTC) VLM	Zhaowei Wang (HKUST) - MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly
16:35 - 17:00 (UTC) VLM	Interactive discussion
17:00 - 17:05 (UTC) LLMAG	Introduction
17:05 - 17:15 (UTC) LLMAG	Li Zhang (University of Pittsburgh) - Mitigating Manipulation and Enhancing Persuasion: A Reflective Multi-Agent Approach for Legal Argument Generation
17:20 - 17:30 (UTC) LLMAG	Aditya Bharat Soni (Language Technologies Institute, School of Computer Science, Carnegie Mellon University) - Coding Agents with Multimodal Browsing are Generalist Problem Solvers
17:35 - 18:00 (UTC) LLMAG	Interactive discussion
18:00 - 18:05 (UTC) AIFin	Introduction
18:05 - 18:15 (UTC) AIFin	Junzhe Jiang (None) - FinMaster: A Holistic Benchmark for Mastering Full-Pipeline Financial Workflows with LLMs
18:20 - 19:00 (UTC) AIFin	Interactive discussion

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

We look forward to seeing you there!