arXiv AI August 10, 2026 By Chen Ling, Hanqian Li, Dongnan Liu, Keyu Qian, Jungang Li, Xinglong liu, Shiyi Wang, Xin Dong, Pengcheng Zhu, Wei Zhou, Linjian Mo, Nai Ding

Debias in Text, Believe Your Eyes: Text-Anchored Cross-Modal Transfer for Visual Counter-Commonsense Reasoning

Read the original on arXiv AI →

arXiv:2608. 06938v1 Announce Type: cross Abstract: The visual reasoning ability of multimodal large language models (MLLMs) is crucial for downstream applications, particularly counter-commonsense reasoning, which requires models to reason beyond common assumptions.

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 AI.

arXiv AI

Jun 26

ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP

arXiv:2606. 26794v1 Announce Type: cross Abstract: CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text alignment.

By Sicheng Zhang, Muzammal Naseer, Binzhu Xie, Naufal Suryanto, Shi Qiu, Jamal Bentahar, Naveed Akhtar, Mubarak Shah

llms multimodal benchmarks safety

arXiv AI

Aug 25

Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents

arXiv:2608.22963v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed as multi-step agents, where explicit reasoning supports task decomposition and tool...

By Yuchen Huang, Sijia Li, Jun Zhang, Yi R. Fung

llms agents fine-tuning efficiency multimodal benchmarks

Hugging Face Trending Papers

Aug 24

Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents

Multimodal Large Language Models (MLLMs) are increasingly deployed as multi-step agents, where explicit reasoning supports task decomposition and tool coordination but also accumulates self-generated...

llms agents fine-tuning efficiency multimodal benchmarks

arXiv AI

Aug 25

SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering

arXiv:2608.21796v1 Announce Type: cross Abstract: Knowledge-based Visual Question Answering (KB-VQA) aims to answer queries that necessitate reasoning over external knowledge sources beyond the visua...

By Long Shu, Shuochen Liu, Wei Chen, Junda Lin, Zhi Zheng, Huijun Hou, Tong Xu

llms nlp reinforcement-learning multimodal benchmarks safety

arXiv Computer Vision

3d ago

Tracing the Evidence: Faithful Token Attribution Through Vision-Language Reasoning

arXiv:2609.37656v1 Announce Type: new Abstract: Large vision-language models (LVLMs) exhibit strong reasoning capabilities, yet the visual and textual evidence supporting the generated responses rema...

By Bowen Yuan, Danny Wang, Ruihong Qiu, Zijian Wang, Zi Huang

llms multimodal benchmarks

arXiv AI

Jun 17

See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL

arXiv:2606. 17678v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) integrate strong text reasoning with visual inputs, yet their responses can be inconsistent with the underlying images, indicating ineffective utilization of visual evidence during inference.

By Yilian Liu, Sicong Leng, Guoshun Nan, Junyi Zhu, Jiayu Huang, Minghao Sun, Xuancheng Zhu, Yisong Chen, Zexian Wei, Xiaofeng Tao

llms reinforcement-learning fine-tuning multimodal benchmarks safety

One email a morning, machine-written

Related stories

ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP

Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents

Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents

SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering

Tracing the Evidence: Faithful Token Attribution Through Vision-Language Reasoning

See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL