Hugging Face Trending Papers June 20, 2026

Zero-Shot Vision-Language Models for Classroom Engagement Recognition: A Benchmark Study of Prompt Sensitivity and Cross-Dataset Generalization

Read the original on Hugging Face Trending Papers →

Automated classroom engagement recognition holds substantial promise for scalable learning analytics, yet the suitability of modern Vision-Language Models (VLMs) for this task under zero-shot conditions remains largely unexplored. We present a systematic benchmark that evaluates five widely-used VLMs: CLIP, BLIP-VQA, GPT-4o, LLaVA-1.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Jul 17

CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models

arXiv:2607. 14125v1 Announce Type: new Abstract: Pre-trained vision-language models (VLMs) enable zero-shot image classification by computing the similarity score between an image and textual descriptions, typically formed by inserting a class label (e.

By Ruijiang Dong, Zesheng Ye, Jianzhong Qi, Lei Feng, Feng Liu, Gang Niu, Masashi Sugiyama

llms computer-vision multimodal benchmarks

arXiv AI

Jul 22

Why Do Vision Language Models Struggle To Recognize Human Emotions?

arXiv:2604. 15280v2 Announce Type: replace-cross Abstract: Understanding emotions is a fundamental ability for intelligent systems to be able to interact with humans.

By Madhav Agarwal, Sotirios A. Tsaftaris, Laura Sevilla-Lara, Steven McDonagh

llms multimodal safety

arXiv AI

Jun 29

Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior

arXiv:2604. 03401v4 Announce Type: replace-cross Abstract: Understanding student engagement usually requires time-consuming manual observation or invasive recording that raises privacy concerns.

By Nolan Platt, Sehrish Nizamani, Alp Tural, Elif Tural, Saad Nizamani, Andrew Katz, Yoonje Lee, Nada Basit

llms multimodal safety

arXiv AI

Jul 31

Facial-Expression-Aware Prompting for Empathetic LLM Tutoring

arXiv:2604. 15336v2 Announce Type: replace-cross Abstract: Large language models (LLMs) enable increasingly capable tutoring-style conversational agents, yet effective tutoring requires sensitivity to learners' affective and cognitive states beyond text alone.

By Shuangquan Feng, Laura Fleig, Ruisen Tu, Philip Chi, Edmund Bu, Melinda Ozel, Junhua Ma, Teng Fei, Virginia R. de Sa

llms agents multimodal

arXiv AI

Jun 24

The Professor: Multi-Teacher Unsupervised Prompt Distillation for Vision-Language Models

arXiv:2606. 23897v1 Announce Type: cross Abstract: Prompt distillation compresses large vision-language models (VLMs) such as CLIP into lightweight student models by matching teacher predictions on unlabeled domain images.

By Ahmad Algadhi, Ahmed Alzuhair, Omar Alkhulaif, Muzammil Behzad

llms efficiency multimodal

arXiv AI

Jul 9

T2T-VICL: Cross-Task Visual In-Context Learning via Implicit Text-Driven VLMs

arXiv:2511. 16107v3 Announce Type: replace-cross Abstract: Visual in-context learning (VICL) solves visual tasks by conditioning on a few input-output demonstrations without any model training.

By Shao-Jun Xia, Huixin Zhang, Zhengzhong Tu

llms multimodal safety

Related stories

CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models

Why Do Vision Language Models Struggle To Recognize Human Emotions?

Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior

Facial-Expression-Aware Prompting for Empathetic LLM Tutoring

The Professor: Multi-Teacher Unsupervised Prompt Distillation for Vision-Language Models

T2T-VICL: Cross-Task Visual In-Context Learning via Implicit Text-Driven VLMs