MechReason is a new benchmark for multi-image, multi-hop reasoning in mechanical engineering, featuring 12,000 question-answer pairs with explicit reasoning chains and 21,000 visual items across nine evidence types. It covers eight task types—explanation, prediction, design, and diagnosis—within four reasoning dimensions, and is constructed through a four-stage pipeline that extracts engineering claims, generates verification-masked questions, and validates multimodal quality. Even state‑of‑the‑art models score only 62.89% on this dataset, highlighting its difficulty.
By Tengyue Wang, Kang An, Chenxu Du, Zhongyu Yang, Yuanchi Zhu, Xinqi Yang, Hebao Zhu, Ziliang Wang, FaQiang Qian, Yunli Yang, Qibing Ren
The paper introduces VPRef, the first cross‑domain benchmark for Referring Remote Sensing Image Segmentation, containing 46,972 language‑image‑annotation triplets with a three‑tier linguistic hierarchy. It proposes a parameter‑efficient adaptation method based on the Segment Anything Model and Low‑Rank Adaptation, using pseudo‑label self‑training for visual drift and random multi‑granularity prompt mixing for textual drift. Experiments show the approach improves cross‑domain segmentation while altering only 1.08 % of the base model’s parameters, offering a strong baseline for future research.
By Quanwei Liu, Tao Huang, Jiaqi Yang, Wei Xiang
The paper introduces ReImaGin, a method that uses image generation models as a flexible visual reasoning tool for multimodal large language models. Unlike traditional fixed-function vision tools, ReImaGin accepts natural language commands and can perform open-ended visual operations such as removing occlusions or creating floorplans from multiple views. Experiments on six diverse visual reasoning tasks show that ReImaGin outperforms both text-only reasoning and specialist vision-tool baselines, achieving up to a 25% improvement.
By Nishad Singhi, Hector Garcia Rodriguez, Aditya Arora, Marcus Rohrbach, Anna Rohrbach
SAVOR is a training framework for multimodal large language models that adds token and answer confidence to the output schema, optimises a Group Relative Policy Optimisation objective to penalise calibration error and poor abstention, and uses the learned confidence at inference to revisit visual evidence only when uncertain. Experiments on POPE, HallusionBench, AMBER, and MMHal-Bench with InternVL3-8B and Qwen3-VL-8B backbones show that SAVOR reduces hallucination while maintaining general capability on MME and MMBench, achieving lower Expected Calibration Error than DPO and decoding baselines.
By Zixiu Ding, Zilin Zhao, Yingjie He, Xinlang Kang, Guansu Wang, Wei Zhang
PriorPose introduces a reference-guided correspondence framework for category-level object pose estimation that jointly performs canonicalization and alignment in a shared feature space. By embedding partial observations and a category prior as token sets in a seeded transformer, the network predicts per-point NOCS fields and a canonical deformation, while a deep pose head regresses the similarity transform. A two-part shape consistency objective couples correspondence, deformation, and pose, reducing reliance on memorized canonical orientations and avoiding error cascades, leading to state-of-the-art results on standard and larger-category benchmarks, especially under strict pose thresholds.
By Yihan Chen, Huan Ren, Wenfei Yang, Hang Du, Tianzhu Zhang, Feng Wu
The paper introduces the Multi-modal Knowledge Preserving Adapter (MKP-Adapter), an adapter-only approach that enables backward compatible training for multi-modal large language models without updating the backbone. It employs a multi-level preservation loss to maintain embedding geometry and a focal re-weighting strategy to focus on difficult samples. Experiments show strong backward compatibility across image, text, visual document, and video retrieval tasks with minimal latency overhead.
By Jaeseok Byun, Gukyeong Kwon, Han-Kai Hsu, Meher Gitika Karumuri, Zhikang Zhang, Hao Yang, Davide Modolo
Video-HolmesV2 is a new benchmark that tests multimodal large language models on their ability to reason with spatio‑temporal audio‑visual evidence in long videos. It requires models to justify answers with precise evidence, uses a multi‑model cross‑verification pipeline and a spatio‑temporal evidence‑aware metric, and introduces an audio‑text guided token compression framework to reduce long‑context noise. In evaluations, even strong proprietary models score below 60% while the proposed approach outperforms comparable open‑source omni‑models.
By Zhaoyang Wei, Zipeng Wang, Yushe Cao, Chenhui Qiang, Shuaibing Cheng, Xuesong Yang, Sen Nie, Bowen Jiang, Wenchao Ding, Yanchao Hao, Zheng Wei, Xuehui Yu, Zhenjun Han
Probe‑VAD introduces an ordinal binary‑probing framework that leverages frozen vision‑language models for training‑free video anomaly detection. By querying ten ordered severity thresholds and extracting YES/NO continuation likelihoods, it builds a cumulative severity profile that is converted into a continuous anomaly score with isotonic projection for ordinal consistency. Experiments on public benchmarks show that this simple interface yields superior performance at low computational cost, avoiding the limitations of caption‑based compression or restricted numerical scoring.
By Jiawei Gu, Qilin Zhao, Tengkuo Guo, Zhiming Zhong, Shuangqing Zhang, Fan Lyu, Fang Zhao, Guo-Sen Xie, Caifeng Shan
arXiv:2609.16033v1 Announce Type: cross
Abstract: Cervical vertebral maturation (CVM) assessment plays a pivotal role in orthodontic diagnosis and determining the optimal timing of treatment, especia...
By Peng Wang, Wanzhen Song, Anli Wang, Xueshuo Xie, Xiaohang Guan, Tao Li
arXiv:2601.18493v2 Announce Type: replace
Abstract: Vision--language models (VLMs) show promise for disaster-response remote sensing, but existing benchmarks mainly emphasize scene-level or damage-ce...
By Sara Tehrani, Yonghao Xu, Leif Haglund, Amanda Berg, Gulnaz Zhambulova, Michael Felsberg
arXiv:2604.11082v2 Announce Type: replace
Abstract: Visual glitches in video games degrade player experience and perceived quality, yet manual quality assurance cannot keep pace with the growing test...
By Yakun Yu, Ashley Wiens, Adri\'an Barahona-R\'ios, Benedict Wilkins, Saman Zadtootaghaj, Nabajeet Barman, Cor-Paul Bezemer
arXiv:2604.15678v2 Announce Type: replace
Abstract: Pretrained Vision-Language Models (VLMs) like CLIP show promise in continual learning, but existing Few-Shot Class-Incremental Learning (FSCIL) met...
By Eunju Lee, MiHyeon Kim, JuneHyoung Kwon, Yoonji Lee, JiHyun Kim, Soojin Jang, YoungBin Kim
arXiv:2605.16581v2 Announce Type: replace
Abstract: Masked language modeling (MLM) is the standard objective for training protein language models, typically implemented by randomly masking individual...
By Thomas Walton, Ayan Goel, Amirali Aghazadeh
arXiv:2605.27293v2 Announce Type: replace
Abstract: Reinforcement learning with verifiable rewards has become a standard recipe for improving the reasoning abilities of large language models. Existin...
By Shijin Gong, Erhan Xu, Kai Ye, Giulia Livieri, Francesco Quinzan, Chengchun Shi
arXiv:2601.11716v2 Announce Type: replace-cross
Abstract: Accurate and efficient detector simulation is essential for modern collider experiments. To reduce the high computational cost, various fast...
By Thorsten Buss, Henry Day-Hall, Frank Gaede, Gregor Kasieczka, Katja Kr\"uger
arXiv:2609.16372v1 Announce Type: new
Abstract: Masked diffusion language models (dLLMs) generate text by iteratively denoising masked tokens with bidirectional attention. Extending reasoning across...
By Albert Ge, Chandan Singh, Yufan Zhuang, Xiaodong Liu, Jianfeng Gao, Frederic Sala
arXiv:2609.16627v1 Announce Type: new
Abstract: Quantifying organizational environmental action from publicly available web content remains a challenging environmental data science problem because re...
By Quinn Reynolds, Daniel Shore, Vianey Leos Barajas, Tanhum Yoreh, Meredith Franklin
arXiv:2609.16854v1 Announce Type: new
Abstract: Probability is fundamental to theories of language comprehension, production, acquisition, and evolution, as well as to large language models. Existing...
By Ferm\'{\i}n Moscoso del Prado Mart\'{\i}n
arXiv:2609.16646v1 Announce Type: new
Abstract: When strong multimodal models are widely available, progress requires new scientific methodologies beyond benchmark scores---using models as instrument...
By Zhipeng Zhao, Wenxu Wang, Peishun Liu, Ruichun Tang
arXiv:2609.16773v1 Announce Type: new
Abstract: Image segmentation remains challenging due to occlusions, poor lighting, and irregular structures. Although transformer-based methods achieve high accu...
By Ruibo Wang, Ziyi Shen, Huaming Wu, Dong Liang, Kun Shang