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
arXiv:2605.26380v2 Announce Type: replace-cross
Abstract: Frontier multimodal large language models (MLLMs) have been reported to achieve over 90\% accuracy on fine-grained perception benchmarks. How...
By Jingru Chen, Yiming Liu, Mingtao Chen, Sijie Chen, Richeng Xuan, Liang Yang, Zhichao Hu, Fanyang Lu
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.
Audio-visual large language models (AVLLMs) have made remarkable progress in multimodal understanding and reasoning through interactions among visual, auditory, and linguistic information. However, re...
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
The paper introduces a causal and temporal evaluation framework for vision‑language models (VLMs) that tracks how visual input, question text, and generated prefixes influence autoregressive decoding. It defines three step‑indexed causal‑drive metrics—Visual Causal Drive (VCD), Question Causal Drive (QCD), and Prefix Causal Drive (PCD)—using a Structural Causal Model and interventions. Experiments on Qwen3‑VL‑8B‑Instruct and other datasets show a shift from early question and visual guidance to increased reliance on generated prefixes, and demonstrate that QCD and PCD reduce recovery error and improve bias detection.
By Shuyao Xiao, Shengling Wang, Haoyu Niu, Ke Chao, Changwei Xu, Xinran Duan, Chaoyong Jiang
arXiv:2604. 14888v3 Announce Type: replace-cross Abstract: Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear.
By Danae S\'anchez Villegas, Samuel Lewis-Lim, Nikolaos Aletras, Desmond Elliott
arXiv:2609.37568v1 Announce Type: new
Abstract: Audio-visual large language models (AVLLMs) have made remarkable progress in multimodal understanding and reasoning through interactions among visual,...
By Yu Zhang, Pingrui Zhang, Xuefeng Bai, Pengfei Zhang, Yang Xiang, Kehai Chen
arXiv:2608.30712v1 Announce Type: new
Abstract: Large multimodal models follow instructions about what to generate, but not necessarily about what evidence to rely on. Hence, models may continue to d...
By Soyeon Caren Han, Hyunsuk Chung, Jinwoo Kim, Seungyeon Ji, Kyungreem Han
Multimodal LLMs can see a document, but they often can't read it reliably. Small text, tables, visual cues, and topological elements still trip them up under direct visual inference, even when the pag...
arXiv:2609.16795v1 Announce Type: new
Abstract: Multimodal large language models (MLLMs) can answer knowledge-intensive visual questions by combining visual evidence from images with facts retrieved...
By Zhenbin Wang, Lei Zhang, Lituan Wang, Wei Huang, Yan Wang, Zhenwei Zhang
CLIMB is a training‑free inference‑time framework for multimodal retrieval‑augmented generation. It builds a compact complementary evidence pool using an MMR‑style objective that balances relevance and redundancy, then refines answers with a confidence‑controlled critic that scores relevance, specificity, and cross‑modal alignment. The method stops refinement when confidence no longer rises, improving performance on Encyclopedic‑VQA and InfoSeek without altering the retriever or language model.
By Hang Gao, Wujiang Xu, Zhixing Zhang, Kai Mei, Jingyi Yang, Dimitris N. Metaxas