Hugging Face Trending Papers August 10, 2026

Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots

Read the original on Hugging Face Trending Papers →

Self-improvement for multimodal large language models (MLLMs) is typically driven by reward-based methods that provide only coarse scalar feedback. Distillation offers a richer alternative through dense token-level supervision, but in the visual domain it usually depends on privileged context constructed using external annotations and tools, or stronger models.

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 Hugging Face Trending Papers.

arXiv AI

Jun 3

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation

arXiv:2605. 18740v4 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image.

By Qianhao Yuan, Jie Lou, Xing Yu, Hongyu Lin, Le Sun, Xianpei Han, Yaojie Lu

llms agents efficiency multimodal benchmarks

arXiv AI

1d 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 Machine Learning

Jul 28

Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation

arXiv:2607. 23125v1 Announce Type: new Abstract: Post-training enables vision-language models (VLMs) to understand human instructions and perform various downstream tasks.

By Shuai Wang, Daoan Zhang, Zhe Tang, Hao Cheng, Jiaheng Wei

llms reinforcement-learning efficiency multimodal benchmarks

arXiv AI

2d ago

Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation

arXiv:2609.39168v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet existing...

By Zhihan Zhang, Lizi Liao

llms reinforcement-learning multimodal benchmarks

arXiv Computer Vision

Sep 22

Look Where It Counts: A Free, Label-Free Visual Evidence Signal for Fine-Grained Vision-Language Reasoning

The paper introduces a free, label‑free visual evidence signal that improves fine‑grained vision‑language reasoning. By selecting image crops that maximize the model’s answer distribution peak, the method locates answer‑bearing regions without training or annotations, boosting accuracy from 70 % to 85 %. The evidence gap also complements model confidence, enabling better correctness prediction and error flagging.

By Santi Ram Tiwari, Nihal Naik, Devbrat Pandey, Nishant Sinha

llms fine-tuning efficiency multimodal

arXiv AI

Aug 6

OPD-V: Visual On-Policy Self-Distillation with Modality Balance

arXiv:2608. 05131v1 Announce Type: cross Abstract: On-Policy Self-Distillation (OPSD) has become a standard post-training approach for improving visual reasoning in multimodal large language models (MLLMs).

By Aniri, Jinhe Bi, Peng Liao, Zengjie Jin, Volker Tresp, Fei Shen, Yunpu Ma, Tat-Seng Chua

llms efficiency multimodal benchmarks

One email a morning, machine-written

Related stories

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation

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

Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation

Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation

Look Where It Counts: A Free, Label-Free Visual Evidence Signal for Fine-Grained Vision-Language Reasoning

OPD-V: Visual On-Policy Self-Distillation with Modality Balance