arXiv AI July 21, 2026 By Yosub Shin, Michael Buriek, Boris Sobolev, Pavel Bushuyeu, Vikas Kumar, Haoyang Xu, Samuel Watson, Igor Molybog

Data-Efficient Curation for Multimodal Reasoning under Fixed Training Protocols

Read the original on arXiv AI →

arXiv:2601. 10922v2 Announce Type: replace Abstract: We study data curation for multimodal reasoning in a fixed-protocol fine-tuning regime, where the base model, optimizer, training schedule, and evaluation pipeline are held constant and the main degree of freedom is the training data.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 17

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment

arXiv:2607. 14682v1 Announce Type: new Abstract: Efficient multimodal document question answering with explicit visual grounding, locating the precise document region that supports each answer remains an open challenge.

By Harikrishnan P M, Goutham Vignesh, Ganesh Parab, Saisubramaniam Gopalakrishnan, Vishal Vaddina, Varun V, Rohit Agrawal

nlp reinforcement-learning fine-tuning multimodal benchmarks safety

arXiv AI

Jul 21

Constraint-Anchored Reasoning Traces

arXiv:2607. 16727v1 Announce Type: new Abstract: Autoregressive multimodal large language models (MLLMs) suffer from error snowballing: a single incorrect inference early in a chainof-thought (CoT) trace corrupts all downstream reasoning.

By Zehua Cheng, Wei Dai, Jiahao Sun

llms fine-tuning multimodal benchmarks

arXiv AI

Jun 11

Does the Question Really Matter? Training-Free Data Selection for Vision-Language SFT

arXiv:2603. 09715v2 Announce Type: replace Abstract: Visual instruction tuning is crucial for improving vision-language large models (VLLMs).

By Peng Sun, Yi Yang, Huawen Shen, Yi Ban, Tianfan Fu, Yanbo Wang, Yuqiang Li

fine-tuning multimodal

arXiv Machine Learning

Jun 25

SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning

arXiv:2507. 16518v3 Announce Type: replace-cross Abstract: Recent advances in multimodal large language models (MLLMs) have shown impressive reasoning capabilities.

By Xiuwei Chen, Wentao Hu, Hanhui Li, Yongxin Wang Jun Zhou, Zisheng Chen, Meng Cao, Yihan Zeng, Kui Zhang, Yu-Jie Yuan, Jianhua Han, Hang Xu, Xiaodan Liang

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Aug 11

DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation

arXiv:2605. 15532v3 Announce Type: replace-cross Abstract: Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets.

By Jaehun Jung, Hyunwoo Kim, Brandon Cui, Ximing Lu, David Acuna, Prithviraj Ammanabrolu, Yejin Choi

llms fine-tuning efficiency multimodal benchmarks

arXiv Machine Learning

Jun 16

DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning

arXiv:2606. 15160v1 Announce Type: cross Abstract: Reasoning capabilities of multimodal large language models (MLLMs) have improved considerably in recent years.

By David Huang, Lianlei Shan

llms diffusion reinforcement-learning efficiency multimodal benchmarks

Related stories

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment

Constraint-Anchored Reasoning Traces

Does the Question Really Matter? Training-Free Data Selection for Vision-Language SFT

SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning

DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation

DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning