When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding

Large Multimodal Models (LMMs) have achieved impressive progress in visual perception and reasoning. However, when confronted with visually ambiguous or non-semantic scene text, they often struggle to accurately spot and understand the content, frequently generating semantically plausible yet visually incorrect answers, which we refer to as semantic hallucination. In this work, we investigate the underlying causes of semantic hallucination and identify a key finding: Transformer layers in LLM with stronger attention focus on scene text regions are less prone to producing semantic hallucinations. Thus, we propose a training-free semantic hallucination mitigation framework comprising two key components: (1) ZoomText, a coarse-to-fine strategy that identifies potential text regions without external detectors; and (2) Grounded Layer Correction, which adaptively leverages the internal representations from layers less prone to hallucination to guide decoding, correcting hallucinated outputs for non-semantic samples while preserving the semantics of meaningful ones. To enable rigorous evaluation, we introduce TextHalu-Bench, a benchmark of over 1,730 samples spanning both semantic and non-semantic cases, with manually curated question-answer pairs designed to probe model hallucinations. Extensive experiments demonstrate that our method not only effectively mitigates semantic hallucination but also achieves strong performance on public benchmarks for scene text spotting and understanding.

VidText: Towards Comprehensive Evaluation for Video Text Understanding

Visual texts embedded in videos carry rich semantic information, which is crucial for both holistic video understanding and fine-grained reasoning about local human actions. However, existing video understanding benchmarks largely overlook textual information, while OCR-specific benchmarks are constrained to static images, limiting their ability to capture the interaction between text and dynamic visual contexts. To address this gap, we propose VidText, a new benchmark designed for comprehensive and in-depth evaluation of video text understanding. VidText offers the following key features: 1) It covers a wide range of real-world scenarios and supports multilingual content, encompassing diverse settings where video text naturally appears. 2) It introduces a hierarchical evaluation framework with video-level, clip-level, and instance-level tasks, enabling assessment of both global summarization and local retrieval capabilities. 3) The benchmark also introduces a set of paired perception reasoning tasks, ranging from visual text perception to cross-modal reasoning between textual and visual information. Extensive experiments on 18 state-of-the-art Large Multimodal Models (LMMs) reveal that current models struggle across most tasks, with significant room for improvement. Further analysis highlights the impact of both model-intrinsic factors, such as input resolution and OCR capability, and external factors, including the use of auxiliary information and Chain-of-Thought reasoning strategies. We hope VidText will fill the current gap in video understanding benchmarks and serve as a foundation for future research on multimodal reasoning with video text in dynamic environments.

Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals

While virtual try-on (VTON) systems aim to render a garment onto a target person image, this paper tackles the novel task of virtual try-off (VTOFF), which addresses the inverse problem: generating standardized product images of garments from real-world photos of clothed individuals. Unlike VTON, which must resolve diverse pose and style variations, VTOFF benefits from a consistent and well-defined output format -- typically a flat, lay-down-style representation of the garment -- making it a promising tool for data generation and dataset enhancement. However, existing VTOFF approaches face two major limitations: (i) difficulty in disentangling garment features from occlusions and complex poses, often leading to visual artifacts, and (ii) restricted applicability to single-category garments (e.g., upper-body clothes only), limiting generalization. To address these challenges, we present Text-Enhanced MUlti-category Virtual Try-Off (TEMU-VTOFF), a novel architecture featuring a dual DiT-based backbone with a modified multimodal attention mechanism for robust garment feature extraction. Our architecture is designed to receive garment information from multiple modalities like images, text, and masks to work in a multi-category setting. Finally, we propose an additional alignment module to further refine the generated visual details. Experiments on VITON-HD and Dress Code datasets show that TEMU-VTOFF sets a new state-of-the-art on the VTOFF task, significantly improving both visual quality and fidelity to the target garments.

What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models

Instruction-based image editing models offer increased personalization opportunities in generative tasks. However, properly evaluating their results is challenging, and most of the existing metrics lag in terms of alignment with human judgment and explainability. To tackle these issues, we introduce DICE (DIfference Coherence Estimator), a model designed to detect localized differences between the original and the edited image and to assess their relevance to the given modification request. DICE consists of two key components: a difference detector and a coherence estimator, both built on an autoregressive Multimodal Large Language Model (MLLM) and trained using a strategy that leverages self-supervision, distillation from inpainting networks, and full supervision. Through extensive experiments, we evaluate each stage of our pipeline, comparing different MLLMs within the proposed framework. We demonstrate that DICE effectively identifies coherent edits, effectively evaluating images generated by different editing models with a strong correlation with human judgment. We publicly release our source code, models, and data.

Self-Supervised and Generalizable Tokenization for CLIP-Based 3D Understanding

Vision-language models like CLIP can offer a promising foundation for 3D scene understanding when extended with 3D tokenizers. However, standard approaches, such as k-nearest neighbor or radius-based tokenization, struggle with cross-domain generalization due to sensitivity to dataset-specific spatial scales. We present a universal 3D tokenizer designed for scale-invariant representation learning with a frozen CLIP backbone. We show that combining superpoint-based grouping with coordinate scale normalization consistently outperforms conventional methods through extensive experimental analysis. Specifically, we introduce S4Token, a tokenization pipeline that produces semantically-informed tokens regardless of scene scale. Our tokenizer is trained without annotations using masked point modeling and clustering-based objectives, along with cross-modal distillation to align 3D tokens with 2D multi-view image features. For dense prediction tasks, we propose a superpoint-level feature propagation module to recover point-level detail from sparse tokens.

Manifold-aware Representation Learning for Degradation-agnostic Image Restoration

Image Restoration (IR) aims to recover high quality images from degraded inputs affected by various corruptions such as noise, blur, haze, rain, and low light conditions. Despite recent advances, most existing approaches treat IR as a direct mapping problem, relying on shared representations across degradation types without modeling their structural diversity. In this work, we present MIRAGE, a unified and lightweight framework for all in one IR that explicitly decomposes the input feature space into three semantically aligned parallel branches, each processed by a specialized module attention for global context, convolution for local textures, and MLP for channel-wise statistics. This modular decomposition significantly improves generalization and efficiency across diverse degradations. Furthermore, we introduce a cross layer contrastive learning scheme that aligns shallow and latent features to enhance the discriminability of shared representations. To better capture the underlying geometry of feature representations, we perform contrastive learning in a Symmetric Positive Definite (SPD) manifold space rather than the conventional Euclidean space. Extensive experiments show that MIRAGE not only achieves new state of the art performance across a variety of degradation types but also offers a scalable solution for challenging all-in-one IR scenarios. Our code and models will be publicly available at https://amazingren.github.io/MIRAGE/.

MLLMs are Deeply Affected by Modality Bias

Recent advances in Multimodal Large Language Models (MLLMs) have shown promising results in integrating diverse modalities such as texts and images. MLLMs are heavily influenced by modality bias, often relying on language while under-utilizing other modalities like visual inputs. This position paper argues that MLLMs are deeply affected by modality bias. Firstly, we diagnose the current state of modality bias, highlighting its manifestations across various tasks. Secondly, we propose a systematic research road-map related to modality bias in MLLMs. Thirdly, we identify key factors of modality bias in MLLMs and offer actionable suggestions for future research to mitigate it. To substantiate these findings, we conduct experiments that demonstrate the influence of each factor: 1. Data Characteristics: Language data is compact and abstract, while visual data is redundant and complex, creating an inherent imbalance in learning dynamics. 2. Imbalanced Backbone Capabilities: The dominance of pretrained language models in MLLMs leads to overreliance on language and neglect of visual information. 3. Training Objectives: Current objectives often fail to promote balanced cross-modal alignment, resulting in shortcut learning biased toward language. These findings highlight the need for balanced training strategies and model architectures to better integrate multiple modalities in MLLMs. We call for interdisciplinary efforts to tackle these challenges and drive innovation in MLLM research. Our work provides a fresh perspective on modality bias in MLLMs and offers insights for developing more robust and generalizable multimodal systems-advancing progress toward Artificial General Intelligence.

FreeInsert: Disentangled Text-Guided Object Insertion in 3D Gaussian Scene without Spatial Priors

Text-driven object insertion in 3D scenes is an emerging task that enables intuitive scene editing through natural language. However, existing 2D editing-based methods often rely on spatial priors such as 2D masks or 3D bounding boxes, and they struggle to ensure consistency of the inserted object. These limitations hinder flexibility and scalability in real-world applications. In this paper, we propose FreeInsert, a novel framework that leverages foundation models including MLLMs, LGMs, and diffusion models to disentangle object generation from spatial placement. This enables unsupervised and flexible object insertion in 3D scenes without spatial priors. FreeInsert starts with an MLLM-based parser that extracts structured semantics, including object types, spatial relationships, and attachment regions, from user instructions. These semantics guide both the reconstruction of the inserted object for 3D consistency and the learning of its degrees of freedom. We leverage the spatial reasoning capabilities of MLLMs to initialize object pose and scale. A hierarchical, spatially aware refinement stage further integrates spatial semantics and MLLM-inferred priors to enhance placement. Finally, the appearance of the object is improved using the inserted-object image to enhance visual fidelity. Experimental results demonstrate that FreeInsert achieves semantically coherent, spatially precise, and visually realistic 3D insertions without relying on spatial priors, offering a user-friendly and flexible editing experience.

Cues3D: Unleashing the Power of Sole NeRF for Consistent and Unique Instances in Open-Vocabulary 3D Panoptic Segmentation

Open-vocabulary 3D panoptic segmentation has recently emerged as a significant trend. Top-performing methods currently integrate 2D segmentation with geometry-aware 3D primitives. However, the advantage would be lost without high-fidelity 3D point clouds, such as methods based on Neural Radiance Field (NeRF). These methods are limited by the insufficient capacity to maintain consistency across partial observations. To address this, recent works have utilized contrastive loss or cross-view association pre-processing for view consensus. In contrast to them, we present Cues3D, a compact approach that relies solely on NeRF instead of pre-associations. The core idea is that NeRF's implicit 3D field inherently establishes a globally consistent geometry, enabling effective object distinction without explicit cross-view supervision. We propose a three-phase training framework for NeRF, initialization-disambiguation-refinement, whereby the instance IDs are corrected using the initially-learned knowledge. Additionally, an instance disambiguation method is proposed to match NeRF-rendered 3D masks and ensure globally unique 3D instance identities. With the aid of Cues3D, we obtain highly consistent and unique 3D instance ID for each object across views with a balanced version of NeRF. Our experiments are conducted on ScanNet v2, ScanNet200, ScanNet++, and Replica datasets for 3D instance, panoptic, and semantic segmentation tasks. Cues3D outperforms other 2D image-based methods and competes with the latest 2D-3D merging based methods, while even surpassing them when using additional 3D point clouds. The code link could be found in the appendix and will be released on \href{https://github.com/mRobotit/Cues3D}{github}

Visual Text Processing: A Comprehensive Review and Unified Evaluation

Visual text is a crucial component in both document and scene images, conveying rich semantic information and attracting significant attention in the computer vision community. Beyond traditional tasks such as text detection and recognition, visual text processing has witnessed rapid advancements driven by the emergence of foundation models, including text image reconstruction and text image manipulation. Despite significant progress, challenges remain due to the unique properties that differentiate text from general objects. Effectively capturing and leveraging these distinct textual characteristics is essential for developing robust visual text processing models. In this survey, we present a comprehensive, multi-perspective analysis of recent advancements in visual text processing, focusing on two key questions: (1) What textual features are most suitable for different visual text processing tasks? (2) How can these distinctive text features be effectively incorporated into processing frameworks? Furthermore, we introduce VTPBench, a new benchmark that encompasses a broad range of visual text processing datasets. Leveraging the advanced visual quality assessment capabilities of multimodal large language models (MLLMs), we propose VTPScore, a novel evaluation metric designed to ensure fair and reliable evaluation. Our empirical study with more than 20 specific models reveals substantial room for improvement in the current techniques. Our aim is to establish this work as a fundamental resource that fosters future exploration and innovation in the dynamic field of visual text processing. The relevant repository is available at https://github.com/shuyansy/Visual-Text-Processing-survey.