arXiv AI
DISTRACT: Degradation-Indexed Study of Textual Reference Across Competing Targets
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
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 Computer Vision
Oct 12
TextVBench: Evaluating Text Rendering and Preservation in Video Generation
TextVBench is a new benchmark and evaluation framework for assessing how well video generation models render and preserve text. It introduces two tracks—TextVBench‑T2V for prompt‑specified text creation and maintenance, and TextVBench‑Ref2V for preserving text from reference images—using a multi‑target, multi‑instance spatiotemporal correspondence approach. The framework employs target‑conditioned candidate selection, supports multiple OCR regions per target, and separates spatial and temporal fidelity, summarizing results with a length‑weighted harmonic score and detailed diagnostics.
arXiv Machine Learning
Jul 7
Pathways of Visual Information Flow in Vision-Language Models
arXiv:2607. 03358v1 Announce Type: cross Abstract: We study how visual information is routed in vision-language models (VLMs).
arXiv Computation and Language
Oct 15
Vision-Language Models Integrate Conflicting Evidence Like Biased Bayesian Observers
arXiv:2610.19407v1 Announce Type: new Abstract: Vision-language models must reconcile conflicting text and images. Prior work has characterized the resulting behavior in terms of modality biases--e.g...
arXiv Computer Vision
Aug 28
Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information
The paper introduces Visual Retrieval Heads (VRHs), a small fraction of attention heads in vision‑language models that are causally responsible for grounding text descriptions to image regions. By recasting head‑scoring methods and evaluating across eleven VLMs and five benchmarks, the authors show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect. VRHs generalize across various visual reference tasks, preserve output format while corrupting localization, and transfer causally across models sharing an LLM backbone.
Hugging Face Trending Papers
Sep 30
CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models
As vision language models are increasingly deployed in clinical diagnosis, understanding how they internally resolve competing visual and textual signals becomes a safety imperative. Existing mechanis...