arXiv Machine Learning August 21, 2026 By Haoqiang Kang, Yinpeng Chen, Luyang Liu, Jesper Sparre Andersen, Abhijit Ogale, Baochen Sun, Lichan Hong, Ed H. Chi

Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning

Read the original on arXiv Machine Learning →

arXiv:2608. 19669v1 Announce Type: cross Abstract: Latent reasoning has advanced multimodal reasoning through a two-stage training paradigm: (1) a helper image is encoded into latent tokens to teach visual chain-of-thought during a supervised fine-tuning (SFT) stage, and (2) these latent tokens are further refined with reward feedback during a reinforcement learning (RL) stage.

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.

Hugging Face Trending Papers

Aug 20

Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning

Latent reasoning has advanced multimodal reasoning through a two-stage training paradigm: (1) a helper image is encoded into latent tokens to teach visual chain-of-thought during a supervised fine-tuning (SFT) stage, and (2) these latent tokens are further refined with reward feedback during a reinforcement learning (RL) stage. In this paper, we identify two key limitations of this framework, one in each stage.

diffusion reinforcement-learning fine-tuning multimodal benchmarks

arXiv Machine Learning

Jul 28

LanteRn: Latent Visual Structured Reasoning

arXiv:2603. 25629v2 Announce Type: replace-cross Abstract: While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs).

By Andr\'e G. Viveiros, Nuno Gon\c{c}alves, Matthias Lindemann, Andr\'e Martins

llms rag diffusion reinforcement-learning fine-tuning 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

arXiv Machine Learning

Jun 16

Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models

arXiv:2606. 15099v1 Announce Type: cross Abstract: Existing Vision-Language-Action (VLA) models predominantly rely on explicit Chain-of-Thought (CoT) reasoning to bridge perception and action.

By Dianqiao Lei, Lianlei Shan

reinforcement-learning robotics multimodal benchmarks safety

arXiv Machine Learning

Jun 2

DeepLatent: Think with Images via Parallel Latent Visual Reasoning

arXiv:2606. 00562v1 Announce Type: cross Abstract: The emerging paradigm of "thinking with images" embeds visual states into intermediate reasoning steps, defining a new frontier for Vision-Language Models.

By Dongchen Lu, Zhimo Li, Mao Shu, Huo Cao

llms rag reinforcement-learning robotics efficiency multimodal benchmarks

arXiv AI

Aug 18

Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning

arXiv:2608. 15869v1 Announce Type: cross Abstract: Multimodal large language models increasingly use visual chain-of-thought (Visual CoT) to reason about spatial, temporal, and embodied environments.

By Xiaoyu Zhu, Xinke Deng, Suresh Taddewadikar, Arnab Kumar Mondal, Zhongyu Jiang, Ian Fasel, Joerg Liebelt

llms rag robotics fine-tuning multimodal

One email a morning, machine-written

Related stories

Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning

LanteRn: Latent Visual Structured Reasoning

DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning

Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models

DeepLatent: Think with Images via Parallel Latent Visual Reasoning

Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning