Uncovering Grounding IDs: How External Cues Shape Multi-Modal Binding

• URL: http://arxiv.org/abs/2509.24072v2
• Date: Fri, 03 Oct 2025 22:57:00 GMT
• Title: Uncovering Grounding IDs: How External Cues Shape Multi-Modal Binding
• Abstract summary: We propose the concept of Grounding IDs, latent identifiers induced by external cues that bind objects to their designated partitions across modalities.<n>We show that Grounding IDs strengthen attention between related components, which in turn improves cross-modal grounding and reduces hallucinations.
• Score: 8.918147502104603
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large vision-language models (LVLMs) show strong performance across multimodal benchmarks but remain limited in structured reasoning and precise grounding. Recent work has demonstrated that adding simple visual structures, such as partitions and annotations, improves accuracy, yet the internal mechanisms underlying these gains remain unclear. We investigate this phenomenon and propose the concept of Grounding IDs, latent identifiers induced by external cues that bind objects to their designated partitions across modalities. Through representation analysis, we find that these identifiers emerge as robust within-partition alignment in embedding space and reduce the modality gap between image and text. Causal interventions further confirm that these identifiers mediate binding between objects and symbolic cues. We show that Grounding IDs strengthen attention between related components, which in turn improves cross-modal grounding and reduces hallucinations. Taken together, our results identify Grounding IDs as a key symbolic mechanism explaining how external cues enhance multimodal binding, offering both interpretability and practical improvements in robustness.

Related papers

• Zero-Shot Semantic Re-Identification for Autonomous Driving: A VLM Baseline Study [0.5599792629509229]
  Re-Identification in autonomous driving is typically formulated as a visual matching problem, where observations of vehicles, pedestrians, and cyclists are associated across time, frames, or camera views.<n>We propose a baseline study of a zero-shot pipeline using Vision-Language Models (VLMs) to generate textual descriptions of detected traffic participants.<n>We show that zero-shot semantic descriptions can support effective object re-identification, achieving retrieval performance comparable to a supervised CNN baseline.
  arXiv  Detail & Related papers  (2026-06-08T11:35:34Z)
• MIRAGE: A Micro-Interaction Relational Architecture for Grounded Exploration in Multi-Figure Artworks [9.397297838455238]
  We present MIRAGE, an evidence-centric framework designed to scaffold the exploration of "micro-interactions" in multi-figure artworks.<n>Results show that MIRAGE significantly improves identity consistency, reduces relational hallucinations, and increases the coverage of subtle interactions.
  arXiv  Detail & Related papers  (2026-04-26T16:25:30Z)
• Identity Clue Refinement and Enhancement for Visible-Infrared Person Re-Identification [20.544872117860915]
  Visible-Infrared Person Re-Identification (VI-ReID) is a challenging cross-modal matching task due to significant modality discrepancies.<n>We propose a novel Identity Clue Refinement and Enhancement (ICRE) network to mine and utilize the implicit discriminative knowledge inherent in modality-specific attributes.
  arXiv  Detail & Related papers  (2025-12-04T07:13:38Z)
• VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning [69.64660280965971]
  VideoAnchor is a plug-and-play module that leverages subspace affinities to reinforce visual cues across frames without retraining.<n>We show consistent performance gains on benchmarks with InternVL2-8B and Q2.5VL-72B.<n>Our codes will be made public at https://github.com/feufhd/VideoAnchor.
  arXiv  Detail & Related papers  (2025-09-29T17:54:04Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception [71.26728044621458]
  DeCLIP is a novel framework that enhances CLIP by decoupling the self-attention module to obtain content'' and context'' features respectively.<n>It consistently achieves state-of-the-art performance across a broad spectrum of tasks, including 2D detection and segmentation, 3D instance segmentation, video instance segmentation, and 6D object pose estimation.
  arXiv  Detail & Related papers  (2025-08-15T06:43:51Z)
• LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance [54.683384204063934]
  Large multi-modal models (LMMs) struggle with inaccurate segmentation and hallucinated comprehension.<n>We propose LIRA, a framework that capitalizes on the complementary relationship between visual comprehension and segmentation.<n>LIRA achieves state-of-the-art performance in both segmentation and comprehension tasks.
  arXiv  Detail & Related papers  (2025-07-08T07:46:26Z)
• HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping [29.678756772610797]
  Unsupervised object discovery and localization aims to detect or segment objects in an image without any supervision. Recent efforts have demonstrated a notable potential to identify salient foreground objects by utilizing self-supervised transformer features. To address these problems, we introduce Hierarchical mErging framework via contrAstive grouPing (HEAP)
  arXiv  Detail & Related papers  (2023-12-29T06:46:37Z)
• VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement [39.154059294954614]
  Online Video Instance (VIS) methods have shown remarkable advancement with their powerful query-based detectors. However, our observations demonstrate that these methods heavily rely on location information, which often causes incorrect associations between objects. This paper presents that a key axis of object matching in trackers is appearance information, which becomes greatly instructive under conditions where positional cues are insufficient for distinguishing their identities.
  arXiv  Detail & Related papers  (2023-12-08T07:48:03Z)
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition [57.08108545219043]
  Recognizing novel sub-categories with scarce samples is an essential and challenging research topic in computer vision. Existing literature addresses this challenge by employing local-based representation approaches. This article proposes a novel model, Robust Saliency-aware Distillation (RSaD), for few-shot fine-grained visual recognition.
  arXiv  Detail & Related papers  (2023-05-12T00:13:17Z)
• Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification [88.79480792084995]
  We propose a joint learning framework that disentangles id-related/unrelated features and enforces adaptation to work on the id-related feature space exclusively. Our model involves a disentangling module that encodes cross-domain images into a shared appearance space and two separate structure spaces, and an adaptation module that performs adversarial alignment and self-training on the shared appearance space.
  arXiv  Detail & Related papers  (2020-07-20T17:57:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.