Hugging Face Trending Papers October 1, 2026

MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning

Read the original on Hugging Face Trending Papers →

The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.

arXiv Computer Vision

4d ago

MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning

arXiv:2610.01352v1 Announce Type: new Abstract: Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven da...

By Juekai Lin, Honglin Lin, Yuqian Yuan, Xiaolong Wu, Jie Cao, Liang Liang, Yunqi Cao, Yun Zhu, Wenqiao Zhang, Lijun Wu

reinforcement-learning fine-tuning efficiency multimodal benchmarks data-engineering

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

arXiv AI

Jul 21

Data-Efficient Curation for Multimodal Reasoning under Fixed Training Protocols

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.

By Yosub Shin, Michael Buriek, Boris Sobolev, Pavel Bushuyeu, Vikas Kumar, Haoyang Xu, Samuel Watson, Igor Molybog

fine-tuning multimodal benchmarks safety

arXiv AI

Aug 18

Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning

arXiv:2608. 16316v1 Announce Type: cross Abstract: Large Multimodal Models (LMMs) for video reasoning have long been hindered by the high computational cost of processing vast amounts of visual information.

By Ao Shen, Yongheng Zhang, Yinghui Li, Manning Wang, Di Yin, Xing Sun

efficiency multimodal benchmarks safety

arXiv Machine Learning

Sep 16

Towards Scalable RLVR: Multimodal Instruction Following Data Synthesis and Distillation

arXiv:2609.16059v1 Announce Type: cross Abstract: Multimodal instruction following (MMIF) is crucial for building generalist agents. However, current training paradigms rely heavily on Supervised Fin...

By Yirong Zeng, Zhang Sai, Yuxian Wang, Yutai Hou, Yufei Liu, Xiao Ding, Bibo Cai

agents reinforcement-learning fine-tuning efficiency 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

One email a morning, machine-written

Related stories

MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning

DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning

Data-Efficient Curation for Multimodal Reasoning under Fixed Training Protocols

Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning

Towards Scalable RLVR: Multimodal Instruction Following Data Synthesis and Distillation

DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation