The heavy computational burden of Large Vision-Language Models (LVLMs) stems primarily from the lengthy visual token sequences generated by their vision encoders. To mitigate this, recent work has shifted towards pruning tokens within the vision encoder. However, we observe that these methods predominantly rely on a suboptimal decoupled heuristic method. This strategy is conceptually flawed: it is prone to sampling collapse, fails to fundamentally eliminate token redundancy, and tends to systematically discard secondary yet important semantic clusters. Addressing this limitation, this paper proposes to formalize visual token pruning as a unified Representativeness Optimization Problem. We introduce SCoRe (Salience-Coverage Reduction), a unified optimization method theoretically grounded in the Weighted k-Center Problem. SCoRe constructs the final token set greedily: at each iteration, it selects the token that maximizes the unified representativeness score, thereby optimizing global representativeness. Extensive experiments demonstrate that SCoRe achieves State-of-the-Art (SOTA) performance across multiple benchmarks. Notably, with negligible computational overhead, our method reduces tokens by 94.4% while retaining 95% of the full performance.
论文检索
输入标题、作者或关键词，从 9,654 篇学术成果中精准定位
Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be maliciously activated at test time. Existing defenses typically rely on retraining backdoored parameters (e.g., adapters or LoRA modules) with clean data, which is computationally expensive and often degrades model performance. In this work, we provide a new mechanistic understanding of backdoor behaviors in LVLMs: the trigger does not influence prediction through low-level visual patterns, but through abnormal cross-modal attention redistribution, where trigger-bearing visual tokens steal attention away from the textual context -- a phenomenon we term attention stealing. Motivated by this, we propose CleanSight, a training-free, plug-and-play defense that operates purely at test time. CleanSight (i) detects poisoned inputs based on the relative visual-text attention ratio in selected cross-modal fusion layers, and (ii) purifies the input by selectively pruning the suspicious high-attention visual tokens to neutralize the backdoor activation. Extensive experiments show that CleanSight significantly outperforms existing pixel-based purification defenses across diverse datasets and backdoor attack types, while preserving the model's utility on both clean and poisoned samples.
Unsupervised domain adaptation (UDA) for semantic segmentation seeks to transfer models from a labeled source domain to an unlabeled target domain. While auxiliary self-supervised tasks such as contrastive learning have enhanced feature discriminability, masked modeling remains underexplored due to architectural constraints and misaligned objectives. We propose Masked Representation Modeling (MRM), an auxiliary task that performs representation masking and reconstruction directly in the latent space. Unlike prior masked modeling methods that reconstruct low-level signals (e.g., pixels or visual tokens), MRM targets high-level semantic features, aligning its objective with segmentation and integrating seamlessly into standard architectures like DeepLab and DAFormer. To support efficient reconstruction, we design a lightweight auxiliary module, Rebuilder, which is jointly trained with the segmentation network but removed during inference, introducing zero test-time overhead. Extensive experiments demonstrate that MRM consistently improves segmentation performance across diverse architectures and UDA benchmarks. When integrated with four representative baselines, MRM achieves an average gain of +2.3 mIoU on GTA -> Cityscapes and +2.8 mIoU on Cityscapes -> Synthia, establishing it as a simple, effective, and generalizable strategy for unsupervised domain-adaptive semantic segmentation.
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in visual reasoning across diverse tasks. These tasks place different demands on visual representations: some prioritize high-level global context, while others emphasize fine-grained local details. However, most existing methods operate on visual representations primarily in the spatial domain, lacking an explicit mechanism for distinguishing between high-frequency local details and low-frequency global context. This limitation hinders fine-grained control of visual representations and complicates their hierarchical alignment with language. To address this issue, we introduce Language-guided Frequency Modulation (LFM), a plug-and-play approach that adaptively refines visual signals in the frequency domain under linguistic guidance. By selectively enhancing critical regions and details, LFM enables more structured and precise visual processing. Crucially, it adds no extra training parameters, relying solely on a lightweight learnable projector to refine visual tokens before integration into the LLM, thereby ensuring minimal computational overhead. Extensive experiments across diverse vision-language benchmarks highlight LFM's scalability, effectiveness, and broad applicability to LVLMs.
STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrieval
PDF ↗Training-free zero-shot composed image retrieval models are recently gaining increasing research interest due to their generalizability and flexibility in unseen multimodal retrieval. Recent LLM-based advances focus on generating the expected target caption by exploring the compositional ability behind the LLMs. Although efficient, we find that 1) the generated captions tend to introduce unexpected features from the reference image due to the semantic gap between the input image and text modification, where the image contains much more details than the text; 2) the point-to-point alignment during the retrieval stage fails to capture diverse compositions.To address these challenges, we introduce a novel Semantic Transition and Transportation in Collaboration framework for training-free zero-shot CIR tasks. Specifically, given the composed caption inferred by an LLM, we aim to refine it through a transition vector in the embedding space and make it closer to the target image. Combining LLMs with user instruction, the refined caption concentrates more on the core modification intent and thus filters out unnecessary noise. Moreover, to explore diverse alignment during the retrieval stage, we model the caption and image as discrete distributions and reformulate the retrieval task as a set-to-set alignment task. Finally, a bidirectional transportation distance is developed to consider fine-grained alignments across modalities and calculate the retrieval score.Extensive experimentsdemonstrate that our method can be general, effective, and beneficial for many CIR tasks.The code is attached in the supplementary material.
Multimodal Large Language Models (MLLMs) have recently achieved remarkable progress in vision-language understanding. Yet, human perception is inherently multisensory, integrating sight, sound, and motion to reason about the world. Among these modalities, sound provides indispensable cues about spatial layout, off-screen events, and causal interactions, particularly in egocentric settings where auditory and visual signals are tightly coupled. To this end, we introduce EgoSound, the first benchmark designed to systematically evaluate egocentric sound understanding in MLLMs. EgoSound unifies data from Ego4D and EgoBlind, encompassing both sighted and sound-dependent experiences. It defines a seven-task taxonomy spanning intrinsic sound perception, spatial localization, causal inference, and cross-modal reasoning. Constructed through a multi-stage auto-generative pipeline, EgoSound contains 7315 validated QA pairs across 900 videos. Comprehensive experiments on nine state-of-the-art MLLMs reveal that current models exhibit emerging auditory reasoning abilities but remain limited in fine-grained spatial and causal understanding. EgoSound establishes a challenging foundation for advancing multisensory egocentric intelligence, bridging the gap between seeing and truly hearing the world. Project page: https://groolegend.github.io/EgoSound/.
Recent multimodal reasoning models, inspired by DeepSeek-R1, have significantly advanced vision-language systems. However, in remote sensing (RS) tasks, we observe widespread pseudo reasoning: models narrate the process of reasoning rather than genuinely reason toward the correct answer based on visual evidence. We attribute this to the Glance Effect, where a single, coarse perception of large-scale RS imagery results in incomplete understanding and reasoning based on linguistic self-consistency instead of visual evidence. To address this, we propose RS-EoT (Remote Sensing Evidence-of-Thought), a language-driven, iterative visual evidence-seeking paradigm. To instill this paradigm, we propose SocraticAgent, a self-play multi-agent system that synthesizes reasoning traces via alternating cycles of reasoning and visual inspection. To enhance and generalize these patterns, we propose a two-stage progressive RL strategy: first, RL on fine-grained Grounding tasks to enhance RS-EoT capabilities, followed by RL on RS VQA to generalize to broader understanding scenarios. Experiments show RS-EoT achieves state-of-the-art performance on multiple RS VQA and grounding benchmarks. Analyses reveal clear iterative cycles of reasoning and evidence seeking, confirming RS-EoT mitigates the Glance Effect and enables genuine evidence-grounded reasoning. Our code, data, and models are available at https://geox-lab.github.io/Asking_like_Socrates/.
GP-4DGS: Probabilistic 4D Gaussian Splatting from Monocular Video via Variational Gaussian Processes
PDF ↗We present GP-4DGS, a novel framework that integrates Gaussian Processes (GPs) into 4D Gaussian Splatting (4DGS) for principled probabilistic modeling of dynamic scenes. While existing 4DGS methods focus on deterministic reconstruction, they are inherently limited in capturing motion ambiguity and lack mechanisms to assess prediction reliability. By leveraging the kernel-based probabilistic nature of GPs, our approach introduces three key capabilities: (i) uncertainty quantification for motion predictions, (ii) motion estimation for unobserved or sparsely sampled regions, and (iii) temporal extrapolation beyond observed training frames. To scale GPs to the large number of Gaussian primitives in 4DGS, we design spatio-temporal kernels that capture the correlation structure of deformation fields and adopt variational Gaussian Processes with inducing points for tractable inference. Our experiments show that GP-4DGS enhances reconstruction quality while providing reliable uncertainty estimates that effectively identify regions of high motion ambiguity. By addressing these challenges, our work takes a meaningful step toward bridging probabilistic modeling and neural graphics.
All-in-One Image Restoration (AIO-IR) aims to develop a unified model that can handle multiple degradations under complex conditions. However, existing methods often rely on task-specific designs or latent routing strategies, making it hard to adapt to real-world scenarios with various degradations. We propose FAPE-IR, a Frequency-Aware Planning and Execution framework for image restoration. It uses a frozen Multimodal Large Language Model (MLLM) as a planner to analyze degraded images and generate concise, frequency-aware restoration plans. These plans guide a LoRA-based Mixture-of-Experts (LoRA-MoE) module within a diffusion-based executor, which dynamically selects high- or low-frequency experts, complemented by frequency features of the input image. To further improve restoration quality and reduce artifacts, we introduce adversarial training and a frequency regularization loss. By coupling semantic planning with frequency-based restoration, FAPE-IR offers a unified and interpretable solution for all-in-one image restoration. Extensive experiments show that FAPE-IR achieves state-of-the-art performance across seven restoration tasks and exhibits strong zero-shot generalization under mixed degradations. Code is available at https://github.com/Programmergg/FAPE-IR.
In recent years, while Scene Graph Generation has advanced significantly, mainstream methods remain constrained by predefined object and relationship categories, limiting generalization to open real-world scenarios. Inspired by open vocabulary object detection, recent efforts have expanded SGG to the open vocabulary domain. However, these models often rely on off-the-shelf VLMs, lacking discriminative attribute extraction and suffering from limited object-relationship semantic interaction, which leads to misclassification of novel categories. To address these issues, we propose the MoE Feature Decoupling (MoE-FD) framework for Open Vocabulary Scene Graph Generation. MoE-FD adaptively learns feature decoupling for objects and relationships via multiple experts, prioritizing critical features through gating network weights. Moreover, it models semantic interactions between objects and relationships using iterative cross-attention, enhancing relationship triple associations and visual-semantic alignment. The main contributions of MoE-FD are threefold: (1) A MoE-based feature decoupling framework that adaptively enhances discriminative feature representation for objects and relations. (2) Semantic interaction modeling between objects and relations to strengthen relationship triple associations and image-text alignment accuracy. (3) Extensive experiments demonstrate the effectiveness of MoE-FD on the Visual Genome dataset.
Long-horizon robotic manipulation is increasingly important for real-world deployment, requiring spatial disambiguation in complex layouts and temporal resilience under dynamic interaction. However, existing end-to-end and hierarchical Vision-Language-Action (VLA) policies often rely on text-only cues while keeping plan intent latent, which undermines referential grounding in cluttered or underspecified scenes, impedes effective task decomposition of long-horizon goals with close-loop interaction, and limits causal explanation by obscuring the rationale behind action choices. To address these issues, we first introduce Visual Sketch, an implausible visual intermediate that renders points, boxes, arrows, and typed relations in the robot's current views to externalize spatial intent, connect language to scene geometry, and provide a human-verifiable bridge between high-level reasoning and low-level control. Building on Visual Sketch, we present Action-Sketcher, a VLA framework that operates in a cyclic See -> Think -> Sketch -> Act workflow coordinated by adaptive token-gated strategy for reasoning triggers, sketch revision, and action issuance, thereby supporting reactive corrections and human interaction while preserving real-time action prediction. To enable scalable training and evaluation, we curate diverse corpus with interleaved images, text, Visual Sketch supervision, and action sequences, and train Action-Sketcher with a multi-stage curriculum recipe that combines interleaved sequence alignment for modality unification, language-to-sketch consistency for precise linguistic grounding, and imitation learning augmented with sketch-to-action reinforcement for robustness. Extensive experiments on cluttered scenes and multi-object tasks, in simulation and on real-world tasks, show improved long-horizon success, stronger robustness to dynamic scene changes, and enhanced interpretability via editable sketches and step-wise plans.
Rapidly-exploring random trees (RRTs) have been widely adopted for robot motion planning due to their robustness and theoretical guarantees. However, existing RRT-based planners require explicit goal configurations specified as numerical joint angles, while many practical applications provide goal specifications through visual observations such as images or demonstration videos where precise goal configurations are unavailable. In this paper, we propose visual-RRT (vRRT), a motion planner that enables visual-goal planning by unifying gradient-based exploitation from differentiable robot rendering with sampling-based exploration from RRTs. We further introduce (1) a frontier-based exploration-exploitation strategy that adaptively prioritizes visually promising search regions, and (2) inertial gradient tree expansion that inherits optimization states across tree branches for momentum-consistent gradient exploitation. Extensive experiments across various robot manipulators including Franka, UR5e, and Fetch demonstrate that vRRT achieves effective visual-goal planning in both simulated and real-world settings, bridging the gap between sampling-based planning and vision-centric robot applications. Our code is available at https://sgvr.kaist.ac.kr/Visual-RRT.
Hallucination has been a significant impediment to the development and application of current Large Vision-Language Models (LVLMs). To mitigate hallucinations, one intuitive and effective way is to directly increase attention weights to image tokens during inference. Although this effectively reduces the hallucination rate, it often induces repetitive descriptions. To address this, we first conduct an analysis of attention patterns and reveal that real object tokens tend to assign higher attention to the generated text than hallucinated ones. This inspires us to leverage the generated text, which contains instruction-related visual information and contextual knowledge, to alleviate hallucinations while maintaining linguistic coherence. We therefore propose Increase Attention to Generated Text (IAT) and demonstrate that it significantly reduces the hallucination rate while avoiding repetitive descriptions. To prevent naive amplification from impairing the inherent prediction capabilities of LVLMs, we further explore Adaptive IAT (AdaIAT) that employs a layer-wise threshold to control intervention time and fine-grained amplification magnitude tailored to the characteristics of each attention head.Both analysis and experiments demonstrate the effectiveness of AdaIAT. Results of several LVLMs show that AdaIAT effectively alleviates hallucination (reducing hallucination rates C_S and C_I on LLaVA-1.5 by 35.8% and 37.1%, respectively) while preserving linguistic performance and prediction capability, achieving an attractive trade-off.
Spatial transcriptomics provides both spatial coordinates and gene expression profiles, enabling the study of tissue organization and cellular heterogeneity. Despite recent progress, current spatial clustering methods still face two major limitations. First, representations learned from spatial and expression views often differ due to view-specific noise and incomplete structural information. Without enforcing sample-level cross-view consistency, embeddings from the two views may not correspond to the same biological identity, reducing discriminative capability. Second, existing approaches lack effective semantic-level supervision. Although node embeddings capture local neighborhood patterns, they do not explicitly reflect high-level semantic structures. Prototype-based modeling can provide such semantic abstraction, yet current methods seldom align prototypes with node representations, leading to weak semantic consistency. To overcome these issues, we propose a Multi-View Hierarchical Alignment Learning for Spatial Transcriptomics (MHAL). At the sample level, MHAL introduce positive sample alignment to enforce consistency between spatial and expression embeddings. At the semantic level, MHAL design prototype level contrastive learning, where prototypes act as semantic anchors and guide the formation of coherent cluster structures. Together, these two alignment mechanisms progressively ensure both local consistency and global semantic discrimination. Extensive experimental results demonstrate that the proposed hierarchical contrastive multi-view clustering method achieves competitive performance in spatial domain identification compared to other state-of-the-art methods.
Anomaly segmentation seeks to detect and localize unknown or out-of-distribution (OoD) objects that fall outside predefined semantic classes--a capability essential for safe autonomous driving. However, the scarcity and limited diversity of anomaly data severely constrain model generalization in open-world environments. Existing approaches mitigate this issue through synthetic data generation, either by copy-pasting external objects into driving scenes or by leveraging text-to-image diffusion models to inpaint anomalous regions. While these methods improve anomaly diversity, they often lack contextual coherence and physical realism, resulting in domain gaps between synthetic and real data. In this paper, we present ClimaDrive, a semantics-guided image-to-image framework for synthesizing semantically coherent, weather-diverse, and physically plausible OoD driving data. ClimaDrive unifies structure-guided multi-weather generation with prompt-driven anomaly inpainting, enabling the creation of visually realistic training data. Based on this framework, we construct ClimaOoD, a large-scale benchmark spanning six representative driving scenarios under both clear and adverse weather conditions.Extensive experiments on four state-of-the-art methods show that training with ClimaOoD leads to robust improvements in anomaly segmentation. Across all methods, AUROC, AP, and FPR95 show notable gains, with FPR95 dropping from 3.97 to 3.52 for RbA on Fishyscapes LAF. These results demonstrate that ClimaOoD enhances model robustness, offering valuable training data for better generalization in open-world anomaly detection.
Rearranging disarrayed objects to their intended goal states requires the agent to comprehend the changes that have occurred in the scene and to reason about the process of these changes. To address this, we propose a novel perspective on the visual rearrangement task, drawing inspiration from the diffusion processes in molecular thermodynamics. We model the room shuffle and unshuffle stages as the forward and reverse processes of diffusion. In contrast to conventional methods that rely on scene modeling and differential comparisons, our approach provides insight into the intrinsic evolution process between the goal and initial states of the scene, which allows for a more reasonable rearrangement of objects through fine-grained and progressive denoising steps with high confidence. By analyzing the task objectives, we represent the scene via spatial distributions of objects and model the visual rearrangement process using a diffusion bridge model. Building upon this, we introduce the Diffusion Rearrangement model, which takes point cloud data as input, fits it into Gaussian mixture distributions to represent the states of objects, and predicts the rearrangement target through an iterative denoising transformer. Experimental results on the RoomR dataset demonstrate the effectiveness of our approach.
Text-to-Image (T2I) diffusion/flow models have recently achieved remarkable progress in visual fidelity and text alignment. However, they remain limited when users need to precisely control image layouts, something that natural language alone cannot reliably express. Controllable generation methods augment the initial T2I model with additional conditions that more easily describe the scene. Prior works straightforwardly train the augmented network with the same loss as the initial network. Although natural at first glance, this can lead to very long training times in some cases before convergence. In this work, we revisit the training objective of controllable diffusion models through a detailed analysis of their denoising dynamics. We show that direct supervision on the clean target image, dubbed x_0-supervision, or an equivalent re-weighting of the diffusion loss, yields faster convergence. Experiments on multiple control settings demonstrate that our formulation accelerates convergence by up to 2xaccording to our novel metric (mean Area Under the Convergence Curve - mAUCC), while also improving both visual quality and conditioning accuracy. Our code is available at https://github.com/CEA-LIST/x0-supervision.
Federated Learning (FL) enables collaborative model training while preserving data privacy, but its practical deployment is hampered by system and statistical heterogeneity. While federated network pruning offers a path to mitigate these issues, existing methods face a critical dilemma: server-side pruning lacks personalization, whereas client-side pruning is computationally prohibitive for resource-constrained devices. Furthermore, the pruning process itself induces significant parametric divergence among heterogeneous submodels, destabilizing training and hindering global convergence. To address these challenges, we propose SubFLOT, a novel framework for server-side personalized federated pruning. SubFLOT introduces an Optimal Transport-enhanced Pruning (OTP) module that treats historical client models as proxies for local data distributions, formulating the pruning task as a Wasserstein distance minimization problem to generate customized submodels without accessing raw data. Concurrently, to counteract parametric divergence, our Scaling-based Adaptive Regularization (SAR) module adaptively penalizes a submodel's deviation from the global model, with the penalty's strength scaled by the client's pruning rate. Comprehensive experiments demonstrate that SubFLOT consistently and substantially outperforms state-of-the-art methods, underscoring its potential for deploying efficient and personalized models on resource-constrained edge devices.
We introduce a parameter-efficient adaptation method for panel-aware in-context image generation with pre-trained diffusion transformers. The key idea is to compose learnable, panel-specific orthogonal operators onto the backbone's frozen positional encodings. This design provides two desirable properties: (1) isometry, which preserves the geometry of internal features, and (2) same-panel invariance, which maintains the model's pre-trained intra-panel synthesis behavior. Through controlled experiments, we demonstrate that the effectiveness of our adaptation method is not tied to a specific positional encoding design but generalizes across diverse positional encoding regimes. By enabling effective panel-relative conditioning, the proposed method consistently improves in-context image-based instructional editing pipelines, including state-of-the-art approaches.
Chest X-ray radiography (CXR) is an essential medical imaging technique for disease diagnosis. However, as 2D projectional images, CXRs are limited by structural superposition and hence fail to capture 3D anatomies. This limitation makes representation learning and disease diagnosis challenging. To address this challenge, we propose a novel CXR world model named X-WIN, which distills volumetric knowledge from chest computed tomography (CT) by learning to predict its 2D projections in latent space. The core idea is that a world model with internalized knowledge of 3D anatomical structure can predict CXRs under various transformations in 3D space. During projection prediction, we introduce an affinity-guided contrastive alignment loss that leverages mutual similarities to capture rich, correlated information across projections from the same volume. To improve model adaptability, we incorporate real CXRs into training through masked image modeling and employ a domain classifier to encourage statistically similar representations for real and simulated CXRs. Comprehensive experiments show that X-WIN outperforms existing foundation models on diverse downstream tasks using linear probing and few-shot fine-tuning. X-WIN also demonstrates the ability to render 2D projections for reconstructing a 3D CT volume.