The most important AI research papers and pre-prints for Wednesday, September 25, 2024. Today we travel the world for new AI applications and new methods with a specific focus on MultiModal Models (MMMs).

Steward: Natural Language Web Automation
https://arxiv.org/pdf/2409.15441

SEAL: Suite for Evaluating API-use of LLMs
https://arxiv.org/pdf/2409.15523

RAM2C: A Liberal Arts Educational Chatbot based on Retrieval-augmented Multi-role Multi-expert Collaboration
https://arxiv.org/pdf/2409.15461

A Comprehensive Evaluation of Large Language Models on Mental Illnesses
https://arxiv.org/pdf/2409.15687

AsthmaBot: Multi-modal, Multi-Lingual Retrieval Augmented Generation For Asthma Patient Support
https://arxiv.org/pdf/2409.15815

Automated Assessment of Multimodal Answer Sheets in the STEM domain
https://arxiv.org/pdf/2409.15749

MMPT: Multimodal Prompt Tuning for Zero-shot Instruction Learning
https://arxiv.org/pdf/2409.15657

CLSP: High-Fidelity Contrastive Language-State Pre-training for Agent State Representation
https://arxiv.org/pdf/2409.15806
[multimodal data understanding, CLIP 2.0]

Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale
https://arxiv.org/pdf/2409.15637
[Ai machines learn from human manuals]

From Passive Watching to Active Learning: Empowering Proactive Participation in Digital Classrooms with AI Video Assistant
https://arxiv.org/pdf/2409.15843
[humans learn from synthetic videos and Ai tutor]

In-Context Ensemble Improves Video-Language Models for Low-Level Workflow Understanding from Human Demonstrations
https://arxiv.org/pdf/2409.15867
[from ICL to multimodal IC Ensemble Learning]

Planning in the Dark: LLM-Symbolic Planning Pipeline without Experts
https://arxiv.org/pdf/2409.15915

LTNtorch: PyTorch Implementation of Logic Tensor Networks
https://arxiv.org/pdf/2409.16045
[new Neuro-Symbolic framework]

Efficiently Learning Probabilistic Logical Models by Cheaply Ranking Mined Rules
https://arxiv.org/pdf/2409.16238

Thank you to all Ai researcher who publish their result open-source.
All links of today's presented papers are also available in my community tab of this channel.

#news
#ai
#multimodal