arXiv Machine Learning June 4, 2026 By Niloufar Alipour Talemi, Hossein Kashiani, Fatemeh Afghah

Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning

Read the original on arXiv Machine Learning →

arXiv:2606. 04434v1 Announce Type: cross Abstract: Multimodal In-Context Learning (ICL) has emerged as a practical inference paradigm for Multimodal Large Language Models, where a small set of interleaved image-text In-Context Demonstrations (ICDs) conditions the model to solve new tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Sep 11

Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning

The paper introduces a multimodal in‑context learning framework that uses contrastive demonstration modeling to align large language models’ responses with the required reasoning paths. By contrasting suboptimal and better responses and incorporating a response‑conditioned retrieval mechanism, the method explicitly guides models beyond surface imitation. Experiments on various multimodal tasks, especially visual question answering, show consistent performance gains.

By Mingbo Yang, Wenqiang Wang, Zhaolu Kang, Peng Chen, Yannan Chen, Sunshang Wang, Yan Xiao

llms nlp multimodal safety

arXiv Machine Learning

Sep 15

TwinICL: Diagnosing Multimodal In-Context Learning through Paired Counterfactuals

TwinICL is a procedurally generated benchmark that pairs matched text and image versions of tasks to enable controlled comparison of in‑context learning (ICL) across modalities. Experiments on six open‑weight models and 38 tasks show that multimodal ICL consistently underperforms text‑only ICL, with varying gaps by task family. Interventions targeting visual access, task framing, and reasoning can recover strong multimodal performance on a diagnostic subset, yet a modality gap remains even when explicit task instructions are provided, highlighting the dual role of demonstrations as context and evidence.

By Zihan Xue, Po-Yi Lu, Serhii Honcharenko, Zih-Ching Chen, Hsuan-Tien Lin, Nanyun Peng, I-Hung Hsu, Kuan-Hao Huang

llms multimodal benchmarks

arXiv AI

2d ago

Capturing In-Context Learning Dynamics with Task Operators

arXiv:2610.01054v1 Announce Type: cross Abstract: In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requi...

By Guangzhi Xiong, Zhenghao He, Bohan Liu, Sanchit Sinha, Wenqian Ye, Aidong Zhang

llms

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

arXiv AI

2d ago

Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes

arXiv:2610.02117v1 Announce Type: cross Abstract: On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a froze...

By Sophia Sirko-Galouchenko, Monika Wysoczanska, Andrei Bursuc, Nicolas Thome, Spyros Gidaris

llms efficiency multimodal benchmarks

arXiv Computation and Language

3d ago

MCD: Causal Distillation of Multimodal In-Context Learning in Large Vision-Language Models

arXiv:2609.39920v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) exhibit strong multimodal in-context learning (ICL) capabilities, yet this ability degrades substantially as mod...

By Yanshu Li, Jiaqian Li, Canran Xiao, Xi Xiao, Tianyang Wang, Yongtai Liu

llms efficiency multimodal benchmarks safety

One email a morning, machine-written

Related stories

Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning

TwinICL: Diagnosing Multimodal In-Context Learning through Paired Counterfactuals

Capturing In-Context Learning Dynamics with Task Operators

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

Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes

MCD: Causal Distillation of Multimodal In-Context Learning in Large Vision-Language Models