ReVisIT is a train‑free framework that turns retrieved image‑label pairs into units of visual thought, combining structured class definitions, multimodal retrieval, and alternating user/assistant injection before joint decoding. On several benchmarks—including Fast Open MiniImageNet, Bongard‑OpenWorld, and the newly released MAAC‑Bench—ReVisIT achieves performance comparable to or surpassing large, trained models while using far fewer parameters. The approach demonstrates that high‑quality retrieval and a simple turns layer can provide a universal performance boost across diverse multimodal tasks.
arXiv:2607. 05438v1 Announce Type: cross Abstract: Multimodal retrieval-augmented generation (RAG) grounds a generator in evidence drawn from heterogeneous modalities -- text, tables, and images.
ClueTracer is a training‑free, parameter‑free plugin that suppresses hallucinations in multimodal reasoning models by tracing how visual clues propagate from the question through the model’s reasoning pathway. It localizes task‑relevant image patches while ignoring irrelevant regions, thereby addressing the problem of reasoning drift where models over‑focus on question‑irrelevant entities. The method improves performance across various reasoning architectures by an average of 1.21× on reasoning benchmarks.
arXiv:2605.27310v2 Announce Type: replace Abstract: Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they reason in language and discard the fine-grained geometry t...
arXiv:2606. 15134v1 Announce Type: cross Abstract: Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either differed or matched.
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...
WOVEN is a new training source and benchmark for visual transition reasoning, comprising 36,076 examples across 20 scenes, 5 actions, and 8 reasoning types. The study shows that current multimodal large language models (MLLMs) have a systematic deficit in spatial, embodied, physical, and temporal reasoning, and that training on WOVEN improves performance on 22 of 26 external benchmarks by up to 27.3 percentage points. The authors also provide a training recipe that prioritizes reasoning operations and larger visual changes for robust visual world modeling.
The paper investigates how new concepts can be integrated into unified multimodal models (UMMs) by separating generation and understanding objectives through a novel visual entity bound to a single task direction. Experiments show that the effectiveness of cross‑task usability depends on where the concept is injected into the shared computation, with a mid‑stack alignment objective achieving high concept acquisition with minimal loss to overall performance. The study highlights that unified weights alone are insufficient; the two directions must share a semantic format at the entry point for efficient concept integration.
arXiv:2608.30705v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) struggle with fine-grained Visual Search, the task of locating small or rare objects in high-resolution images...
arXiv:2601.19060v2 Announce Type: replace-cross Abstract: Multimodal Retrieval-Augmented Generation (MM-RAG) augments visual question answering (VQA) with external knowledge, but many systems rely on...
arXiv:2608.28696v1 Announce Type: new Abstract: Visual in-context learning (ICL) with multimodal large language models (MLLMs) is effective for fine-grained visual classification, but each retrieved...
The paper introduces Auto-Comp, a fully automated, concept-driven pipeline that generates photorealistic compositional benchmarks for vision‑language models. Auto‑Comp creates paired Minimal and Contextual samples for each concept, enabling isolation of core binding abilities from visio‑linguistic complexity. Evaluations across 25 models reveal consistent failures in attribute and relational binding, with context helping relational tasks but hindering attribute tasks due to visual clutter.
The paper investigates the faithfulness of visual information in multimodal chain-of-thought (MCoT) reasoning by large vision-language models (LVLMs). It shows that visual cues in MCoT are often inaccurate and largely ignored, as predictions change little when visual input is altered but significantly when textual input is changed. To improve visual faithfulness, the authors propose an annotation‑free Sufficient‑Component Cause Model (SCCM) that encourages the generation of minimal yet sufficient visual components, and demonstrate its effectiveness across fine‑grained perception and reasoning benchmarks.