arXiv:2608. 19739v1 Announce Type: cross Abstract: Multimodal LLMs can see a document, but they often can't read it reliably.
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.
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:2607. 15565v1 Announce Type: cross Abstract: Where should the question go in a vision-language model (VLM) prompt: before the image or after it?
The paper investigates how visual interventions—training‑free edits applied to multimodal large language models—affect hallucinations and prediction quality. By applying a visual‑residual edit across successive decoder layers and matching its RMS strength, the authors identify an Evidence Anchoring Boundary (EAB) where the intervention’s influence drops sharply; effects before the EAB are 13.78–26.10× larger than after it. They further compare counterfactual subtraction across different question types and introduce calibrated selective routing, which only alters predictions when calibration supports an intervention, improving attribute accuracy by 1.56–1.81 percentage points while avoiding the harms of universal subtraction.
The paper introduces <flowreader>, a method that casts evidence selection for long multimodal documents as a minimum‑cost flow problem over a multimodal content graph. It uses spectral decomposition to identify latent query‑relevant aspects and allocates a fixed evidence budget proportionally to their spectral energy, ensuring aspect coverage without a language‑model planning call. On the VisDoMBench benchmark with Qwen3‑VL‑32B, <flowreader> achieves the highest macro accuracy (68.9%) and outperforms prior systems by 2.7 points, while using fewer content nodes and reader tokens.
arXiv:2606. 16494v1 Announce Type: cross Abstract: Knowledge-based visual question answering (KB-VQA) lets vision-language systems answer questions that exceed their parametric knowledge by conditioning a reader on passages retrieved from a Wikipedia-scale knowledge base.
arXiv:2610.32664v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) read images through visual tokens, and under the small per-image budgets that efficient deployment requires, t...