The paper introduces TTIQ, a test‑time reinforcement learning framework that improves vision‑language model (VLM) adaptation by explicitly measuring image‑question dependence. By teacher‑forcing responses on the original and ablated image‑question pairs, TTIQ derives token‑level likelihood changes to estimate how much each input contributes, then uses these signals to construct a reward that favors jointly grounded, confident responses. Experiments on eight VQA datasets and various VLM sizes show that TTIQ consistently outperforms prior consensus‑based methods and generalizes across model families and unseen datasets.
By Xinrui He, Ting-Wei Li, Junting Wang, Mengting Ai, Xinyu He, Hanghang Tong, Jingrui He
arXiv:2609.36893v1 Announce Type: new
Abstract: Detailed image captioning requires accurate and comprehensive descriptions of fine-grained visual content, yet caption quality spans factual accuracy,...
By Zhenwen Ji, Lei Jin, Shanyong Wang, Jiaming Lu, Chengqiang Lu, Yi Wu, Yao Hu, Lizhen Cui, Yanyu Xu
arXiv:2606. 02578v1 Announce Type: cross Abstract: Recent multimodal large language models have demonstrated strong reasoning ability, yet their reliability as automated evaluators remains limited by a critical weakness: when visual evidence conflicts with textual cues, MLLM judges tend to reward plausible narratives over perceptually correct answers.
By Seojeong Park, Jiho Choi, Junyong Kang, Seonho Lee, Jaeyo Shin, Hyunjung Shim
The paper introduces a test‑time reinforcement learning framework for anomalous video understanding, addressing challenges such as unreliable pseudo‑labels, inadequate reward design, and collapsed group‑relative advantages. It proposes dual‑query consistency filtering, an entropy‑aware consensus reward, and a virtual negative anchor mechanism to improve sample reliability, reward quality, and policy‑gradient signals. Experiments on VAU‑Bench demonstrate significant performance gains, especially on the ECVA subset where accuracy rises from 75.81% to 90.00%.
By Huining Li, Yuxiang Duan, Jiyang Tan, Qian Li, MingCai Chen, Jian Zhang, Xingdong Sheng, Yuntao Du
Generalized CycleGRPO is a unified reinforcement learning framework that jointly trains region understanding and localization across spatial, temporal, and spatio‑temporal domains. It uses a multimodal large language model to generate candidate descriptions for a given region, then localizes each description to reconstruct the original region, providing verifiable rewards for both captioning and localization. The approach extends beyond image masks and boxes to video intervals and timestamped spatial evidence, and introduces the DOVE benchmark to evaluate temporal distinctiveness, achieving significant performance gains on several grounding and temporal tasks.
By Xin Zhang, Haochen Wang, Beibei Lin, Zhaoxiang Zhang, Robby T. Tan, Jason Li, Dacheng Tao
arXiv:2606. 04434v1 Announce Type: cross Abstract: Multimodal In-Context Learning (ICL) has emerged as a practical inference paradigm for Multimodal Large Language Models, where a small set of interleaved image-text In-Context Demonstrations (ICDs) conditions the model to solve new tasks.
By Niloufar Alipour Talemi, Hossein Kashiani, Fatemeh Afghah
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
arXiv:2511. 16107v3 Announce Type: replace-cross Abstract: Visual in-context learning (VICL) solves visual tasks by conditioning on a few input-output demonstrations without any model training.
By Shao-Jun Xia, Huixin Zhang, Zhengzhong Tu
The paper introduces AVA, a training‑free framework that improves interleaved multimodal in‑context learning for frozen large vision‑language models. AVA decomposes the interleaved context into per‑sample threads, selects influential demonstrations while removing redundancy, and calibrates consistency using a weak sibling model’s confidence. Across five vision‑language benchmarks, AVA raises performance by up to 2.4 points, narrows the visual performance gap on ScienceQA‑IMG, and remains robust even with 30% noisy demonstrations, all while keeping the LVLM frozen and adding only modest latency.
By Yigit Yilmaz, Elena Petrova, Mehmet Kaya, Lucia Rossi, Amir Rahman
arXiv:2608. 04509v1 Announce Type: new Abstract: Vision-language systems combine images with retrieved text, but these sources can disagree or jointly fail to support an answer.
By De Jiang, Zhengyang Zhang, Kehong Yuan, Shaohua Ma
arXiv:2607. 28986v1 Announce Type: cross Abstract: Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and frozen pretrained image-text scorers.
By Duy Tran Thanh, Thien-Phuc Doan, Long Nguyen-Vu, Ngo Tan Vu Khanh
Multimodal large language models (MLLMs) have made strong progress on visual question answering and image captioning, yet they still produce fluent claims about objects, attributes, or relations that...