arXiv AI
Cross-Modal Latent Influence: Patch-Level Training Sample Attribution for Vision-Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 30
Tracing the Evidence: Faithful Token Attribution Through Vision-Language Reasoning
arXiv:2609.37656v1 Announce Type: new Abstract: Large vision-language models (LVLMs) exhibit strong reasoning capabilities, yet the visual and textual evidence supporting the generated responses rema...
arXiv AI
Sep 16
Layers, Sinks, and Scaling: Adaptive Evidence Selection for Multimodal Large Language Models
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...
arXiv AI
Jul 15
Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models
arXiv:2509. 22415v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved strong vision-language performance, yet their token-level visual evidence remains difficult to inspect.
arXiv Machine Learning
Jun 30
Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders
arXiv:2606. 29888v1 Announce Type: new Abstract: Vision-language models map images and text into a joint embedding space.
arXiv AI
Jun 2
Multimodal Function Vectors for Visual Relations
arXiv:2510. 02528v2 Announce Type: replace Abstract: Large Multimodal Models (LMMs) demonstrate impressive in-context learning abilities from few multimodal demonstrations, yet the internal mechanisms supporting such task learning remain opaque.
arXiv AI
Sep 2
Visual Attention Faithfulness in Vision-Language Models is Heterogeneous
The study investigates whether attention weights in Vision‑Language Models (VLMs) accurately reflect model reasoning for visual inputs. Using causal perturbation analysis, it identifies three distinct processing modes—Faithful‑Sufficient, Faithful‑Distributed, and Non‑Focal—indicating heterogeneous visual attention faithfulness. The research also shows that human‑annotated ground‑truth regions align with model attention in only about 60% of cases, highlighting a systematic divergence between model visual reliance and human intuition across VQA, document, and chart tasks.