The rapid advancement of diffusion-based image generation models has raised serious concerns regarding potential copyright and privacy infringements involving human-created data. Membership inference attacks (MIAs) have emerged as a promising tool for identifying unauthorized data usage during model training. Existing methods typically assess the ability of model to denoise perturbed suspect images as an indicator of membership status. However, the discriminative power of such features is highly dependent on the degree of model memorization and deteriorates significantly when applied to less exposed data (e.g., pre-training data). Although several methods attempt to enhance detection by leveraging internal model features, these features are generally inaccessible in mainstream closed-source image generation platforms, limiting their practicality. In this paper, we demonstrate that analyzing how a black-box diffusion model denoises a target image and corresponding perturbed textual instructions can reveal more distinctive membership cues. Based on this insight, we propose a black-box membership inference attack framework (named SD-MIA) that leverages a cross-modal data perturbation mechanism to detect pre-training data in diffusion models. We conduct extensive experiments on both a public benchmark dataset and a newly constructed dataset, each comprising pre-training membership and non-membership samples with identical distributions. Experimental results demonstrate that SD-MIA achieves superior performance compared to existing baselines, including those with the unfair advantage of accessing internal model features.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
Recently, Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach to incentivizing reasoning capability in Large Multimodal Models (LMMs), while the underlying mechanisms behind this post-training paradigm are poorly understood. We begin by exploring how input activations are affected by RLVR through the perspective of logit lens. Our systematic investigations across multiple post-trained LMMs suggest that RLVR shifts low-entropy activations unexpectedly, while high-entropy ones are less affected. We further demonstrate that such phenomena are associated with LMM reasoning by controlled experiments, suggesting a potentially beneficial role of modulating low-entropy activations. To this end, we propose Activation Replay, a novel simple yet effective training-free approach that boosts multimodal reasoning of post-trained LMMs without requiring expensive policy optimization. Our design involves manipulation of visual tokens at test time, replaying low-entropy activations from the input context of base LMMs to regulating the RLVR counterparts. Activation Replay triggers better reasoning across diverse scenarios, including mathematics, o3-like visual agents, and video reasoning. We further show that Activation Replay boosts Pass@K and mitigates narrower reasoning coverage of RLVR. Our design is compared against alternative choices, such as replaying high-entropy activations instead of low-entropy ones, or direct cross-model intervention instead of manipulating input tokens, demonstrating the superiority of our implementation. Codes will be made publicly available.
We present Streamo, a real-time streaming video LLM that serves as a general-purpose interactive assistant. Unlike existing online video models that focus narrowly on question answering or captioning, Streamo performs a broad spectrum of streaming video tasks, including real-time narration, action understanding, event captioning, temporal event grounding, and time-sensitive question answering. To develop such versatility, we construct Streamo-Instruct-465K, a large-scale instruction-following dataset tailored for streaming video understanding. The dataset covers diverse temporal contexts and multi-task supervision, enabling unified training across heterogeneous streaming tasks. After training end-to-end on the instruction-following dataset through a streamlined pipeline, Streamo exhibits strong temporal reasoning, responsive interaction, and broad generalization across a variety of streaming benchmarks. Extensive experiments show that Streamo bridges the gap between offline video perception models and real-time multimodal assistants, making a step toward unified, intelligent video understanding in continuous video streams.
Generating long videos using pre-trained video diffusion models, which are typically trained on short clips, presents a significant challenge. Directly applying these models for long-video inference often leads to a notable degradation in visual quality. This paper identifies that this issue primarily stems from two out-of-distribution (O.O.D) problems: frame-level relative position O.O.D and contextlength O.O.D. To address these challenges, we propose FreeLOC, a novel training-free, layer-adaptive framework that introduces two core techniques: Video-based Relative Position Re-encoding (VRPR) for frame-level relative position O.O.D, a multi-granularity strategy that hierarchically re-encodes temporal relative positions to align with the model's pre-trained distribution, and Tiered Sparse Attention (TSA) for context-length O.O.D, which preserves both local detail and long-range dependencies by structuring attention density across different temporal scales. Crucially, we introduce a layer-adaptive probing mechanism that identifies the sensitivity of each transformer layer to these O.O.D issues, allowing for the selective and efficient application of our methods. Extensive experiments demonstrate that our approach significantly outperforms existing training-free methods, achieving state-of-the-art results in both temporal consistency and visual quality. Code is available at https://github.com/Westlake-AGI-Lab/FreeLOC.
Humans have remarkable selective sensitivity to identities--they easily distinguish between highly-similar identities, even across significantly different contexts such as diverse viewpoints or lighting. Vision models have struggled to match this capability, and progress towards identity-focused tasks such as personalized image generation is slowed by a lack of identity-focused evaluation metrics. To help facilitate progress, we propose ID-Sim, a feed-forward metric designed to faithfully reflect human selective sensitivity. To build ID-Sim, we curate a high-quality training set of images spanning diverse real-world domains, augmented with generative synthetic data that provides controlled, fine-grained identity and contextual variations. We evaluate our metric on a new unified evaluation benchmark for assessing consistency with human annotations across identity-focused recognition, retrieval, and generative tasks.
MMDIR: Multimodal Instruction-Driven Framework for Mixed-Degradation Document Image Restoration
PDF ↗Restoring degraded document image is essential for both improving visual quality and optimizing performance in downstream document analysis tasks. Although existing methods have demonstrated substantial improvements in restoration outcomes, they primarily address single-type degradation scenarios. Current approaches typically necessitate training multiple specialized models for specific degradation types or rely on explicit prior knowledge of degradation patterns to guide the training process. To overcome these limitations, we propose MMDIR, a multimodal instruction-driven framework designed for document image restoration under mixed and uncertain degradation conditions. By leveraging semantically structured instructions, MMDIR dynamically identifies present degradation types (blur, shadow, text watermark, and seal), while enhancing degradation-aware representation learning. Furthermore, we introduce a novel benchmark named MixedDoc comprising complex mixed degradations, where each image contains randomized combinations of the aforementioned types. This benchmark addresses a critical gap in existing datasets, which lack realistic multi-degradation samples and often overlook common obstructions such as seals and text watermarks. The effectiveness of our approach is thoroughly validated across both released public benchmarks and our newly proposed dataset. The dataset is available at https://github.com/xiaomore/MMDIR.
Stereo video inpainting, which aims to fill the occluded regions of warped videos with visually coherent content while maintaining temporal consistency, remains a challenging open problem. The regions to be filled are scattered along object boundaries and occupy only a small fraction of each frame, leading to two key challenges. First, existing approaches perform poorly on such tasks due to the scarcity of high-quality stereo inpainting datasets, which limits their ability to learn effective inpainting priors. Second, these methods apply equal processing to all regions of the frame, even though most pixels require no modification, resulting in substantial redundant computation. To address these issues, we introduce three interconnected components. We first propose Gradient-Aware Parallax Warping (GAPW), which leverages backward warping and the gradient of the coordinate mapping function to obtain continuous edges and smooth occlusion regions. Then, a Parallax-Based Dual Projection (PBDP) strategy is introduced, which incorporates GAPW to produce geometrically consistent stereo inpainting pairs and accurate occlusion masks without requiring stereo videos. Finally, we present Sparsity-Aware Stereo Inpainting (SASI), which reduces over 70% of redundant tokens, achieving a 10.7xspeedup during diffusion inference and delivering results comparable to its full-computation counterpart, enabling real-time processing of HD (768x1280) videos at 25\,FPS on a single A100 GPU.
Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency
PDF ↗Efficient adaptation between Egocentric (Ego) and Exocentric (Exo) views is crucial for applications such as human-robot cooperation. However, the success of most existing Ego-Exo adaptation methods relies heavily on target-view data for training, thereby increasing computational and data collection costs. In this paper, we make the first exploration of a Test-time Ego-Exo Adaptation for Action Anticipation (TE^ 2 A^ 3 ) task, which aims to adjust the source-view-trained model online during test time to anticipate target-view actions. It is challenging for existing Test-Time Adaptation (TTA) methods to address this task due to the multi-action candidates and significant temporal-spatial inter-view gap. Hence, we propose a novel Dual-Clue enhanced Prototype Growing Network (DCPGN), which accumulates multi-label knowledge and integrates cross-modality clues for effective test-time Ego-Exo adaptation and action anticipation. Specifically, we propose a Multi-Label Prototype Growing Module (ML-PGM) to balance multiple positive classes via multi-label assignment and confidence-based reweighting for class-wise memory banks, which are updated by an entropy priority queue strategy. Then, the Dual-Clue Consistency Module (DCCM) introduces a lightweight narrator to generate textual clues indicating action progressions, which complement the visual clues containing various objects. Moreover, we constrain the inferred textual and visual logits to construct dual-clue consistency for temporally and spatially bridging Ego and Exo views. Extensive experiments on the newly proposed EgoMe-anti and the existing EgoExoLearn benchmarks show the effectiveness of our method, which outperforms related state-of-the-art methods by a large margin. Code is available at \href https://github.com/ZhaofengSHI/DCPGN https://github.com/ZhaofengSHI/DCPGN .
Counting is one of the fundamental abilities of large language models (LLMs) and large vision-language models (LVLMs). This paper examines how these foundation models represent and compute numerical information in counting tasks. We use controlled experiments with repeated textual and visual items and analyze counting in LLMs and LVLMs through a set of behavioral, observational, and causal mediation analyses. To this end, we design a specialized tool, CountScope, for the mechanistic interpretability of numerical content. Results show that individual tokens or visual features encode latent positional count information that can be extracted and transferred across contexts. Layerwise analyses reveal a progressive emergence of numerical representations, with lower layers encoding small counts and higher layers representing larger ones. We identify an internal counter mechanism that updates with each item, stored mainly in the final token or region. In LVLMs, numerical information also appears in visual embeddings, shifting between background and foreground regions depending on spatial composition. We further reveal that models rely on structural cues such as separators in text, which act as shortcuts for tracking item counts and strongly influence the accuracy of numerical predictions. Overall, counting emerges as a structured, layerwise process in LLMs and follows the same general pattern in LVLMs, shaped by the properties of the vision encoder.
Radiance field methods (e.g. 3D Gaussian Splatting) have emerged as a powerful paradigm for novel view synthesis, yet their appearance modeling often relies on Spherical Harmonics (SH), which impose fundamental limitations. SH struggle with high-frequency signals, exhibit Gibbs ringing artifacts, and fail to capture specular reflections---a key component of realistic rendering. Although alternatives like spherical Gaussians offer improvements, they add significant optimization complexity. We propose Spherical Voronoi (SV) as a unified framework for appearance representation in 3D Gaussian Splatting. SV partitions the directional domain into learnable regions with smooth boundaries, providing an intuitive and stable parameterization for view-dependent effects. For diffuse appearance, SV achieves competitive results while keeping optimization simpler than existing alternatives. For reflections---where SH fail---we leverage SV as learnable reflection probes, taking reflected directions as input following principles from classical graphics. This formulation attains state-of-the-art results on synthetic and real-world datasets, demonstrating that SV offers a principled, efficient, and general solution for appearance modeling in explicit 3D representations.
D$^2$-FOSA: Dual-Diffusion Guided EEG-to-Image Reconstruction with Frequency-Oriented Semantic Alignment
PDF ↗Reconstructing visual semantics from Electroencephalography (EEG) signals enables a deeper understanding of human visual cognition and supports next-generation brain-computer interface (BCI) applications.Despite notable advances in recent years, most existing EEG encoders still struggle to capture the frequency-specific neural dynamics that reflect perceptual and cognitive rhythms. Moreover, the cross-modal alignment between EEG and visual content remains insufficiently tackled, leading to limited semantic consistency and visual fidelity. To address these issues, we propose D^2-FOSA, a unified dual-diffusion guided framework with frequency-oriented semantic alignment, which strengthens the frequency-aware EEG representation for more semantically aligned image reconstruction.Specifically, we design a Frequency-Spatio-Temporal Dynamics Encoder (FSTDE) based on the Frequency-Oriented Mamba (FOMamba) to explicitly model oscillatory patterns and long-range dependencies in EEG signals. The extracted features are then pulled into the CLIP-aligned visual semantic space via contrastive learning.Meanwhile, a Dual Diffusion Latent Generator (DDLG) with bidirectional EEG-image conditioning is designed to enforce cross-modal alignment and promote cycle-consistent generation.Extensive experiments on four challenging datasets demonstrate that our proposed D^2-FOSA significantly outperforms existing methods in both retrieval and reconstruction tasks. Particularly, our D^2-FOSA surpasses the contemporary MB2C method by over 17 FID in the reconstruction task on THINGS-EEG, indicating a substantial improvement in perceptual fidelity. The source code is in the supplementary material.
Large vision-language models (LVLMs) have demonstrated remarkable capabilities by integrating pre-trained vision encoders with large language models (LLMs). Similar to single-modal LLMs, chain-of-thought (CoT) prompting has been adapted for LVLMs to enhance multi-modal reasoning by generating intermediate rationales based on visual and textual inputs. While CoT is assumed to improve grounding and accuracy in LVLMs, our experiments reveal a key challenge: existing LVLMs often ignore the contents of generated rationales in CoT reasoning. To address this, we re-formulate multi-modal CoT reasoning as a KL-constrained reward maximization focused on rationale-conditional log-likelihood. As the optimal solution, we propose rationale-enhanced decoding (RED), a novel plug-and-play inference-time decoding strategy. RED harmonizes visual and rationale information by multiplying distinct image-conditional and rationale-conditional next token distributions. Extensive experiments show that RED consistently and significantly improves reasoning over standard CoT and other decoding methods across multiple benchmarks and LVLMs. Our work offers a practical and effective approach to improve both the faithfulness and accuracy of CoT reasoning in LVLMs, paving the way for more reliable rationale-grounded multi-modal systems.
Data-driven approaches have revolutionized 3D vision, enabling transformers to effectively reconstruct and generate static 3D objects. However, generating simulative 4D dynamics---realistic temporal deformations of static objects under various physical conditions---remains challenging and often ad hoc despite being critical for building comprehensive 3D world models. Most existing methods assume a predefined physical model and use system identification to estimate parameters, restricting these methods to specific categories and small-scale datasets. We propose that these restrictions can be overcome by learning a data-driven kinematic state parameterization for object-centric physical systems. Specifically, we learn both a latent space of all possible states of the object and a decoder that maps any sampled latent to a plausibly deformed shape of the object. We refer to this parameterization as Neural Object Kinematics (NeuROK), and learn a transformer-based encoder-decoder model on a curated large-scale 4D dataset. This formulation and the learned model significantly simplify the generation of simulative dynamics since we only need to consider the dynamics within a low-dimensional latent space from the Lagrangian mechanics' perspective in classical physics. We demonstrate the effectiveness and generality of this framework across diverse dynamic object types, showing clear advantages over prior works.
Consistency Beyond Contrast: Enhancing Open-Vocabulary Object Detection Robustness via Contextual Consistency Learning
PDF ↗Recent advances in open-vocabulary object detection focus primarily on two aspects: scaling up datasets and leveraging contrastive learning to align language and vision modalities. However, these approaches often neglect internal consistency within a single modality, particularly when background or environmental changes occur. This lack of consistency leads to a performance drop because the model struggles to detect the same object in different scenes, which reveals a robustness gap. To address this issue, we introduce Contextual Consistency Learning (CCL), a novel framework that integrates two key strategies: Contextual Bootstrapped Data Generation (CBDG) and Contextual Consistency Loss (CCLoss). CBDG functions as a data generation mechanism, producing images that contain the same objects across diverse backgrounds. This is essential because existing datasets alone do not support our CCL framework. The CCLoss further enforces the invariance of object features despite environmental changes, thereby improving the model's robustness in different scenes. These strategies collectively form a unified framework for ensuring contextual consistency within the same modality. Our method achieves state-of-the-art performance, surpassing previous approaches by +16.3 AP on OmniLabel and +14.9 AP on D^3. These results demonstrate the importance of enforcing intra-modal consistency, significantly enhancing model generalization in diverse environments. Our code is publicly available at: https://github.com/bozhao-li/CCL
EE-RL: Vision Language Guided Reinforcement Learning with Explorer and Expert model for End-to-End Autonomous Driving
PDF ↗End-to-end driving frameworks, which directly map raw sensor data to vehicle control commands, have shown remarkable potential. However, their performance often deteriorates in sparse-critical scenarios, where rare but safety-sensitive events occur. To address this problem, we propose Explorer-Expert Reinforcement Learning (EE-RL), a novel end-to-end framework that integrates an RL-based explorer, a fine-tuned vision-language model (VLM)-based expert, and a dual replay buffer. EE-RL adopts a collaborative learning strategy in which an explorer and two experts jointly generate experiences from regular driving scenarios to guide policy learning. As training progresses, one of the VLMs focuses on reasoning about sparse-critical scenarios, thereby enhancing learning efficiency and policy optimization in both scenarios. Additionally, the StateHash algorithm is designed to separately measure RGB image similarity and vehicle kinematic similarity, thereby skipping unnecessary VLM reasoning and enabling denser, more effective expert experience generation. Experiments on the CARLA Leaderboard demonstrate that EE-RL significantly outperforms state-of-the-art (SOTA) baselines, achieving +19.82% and +20.98% improvements in driving and infraction scores on Town03, respectively. The EE-RL further achieves 0% accident probability for red-light running and an average driving score of 80.09 in Town05-06, demonstrating robustness, generalizability, and the capability to handle sparse-critical scenarios.
The Aerial Object Goal Navigation, a challenging frontier in Embodied AI, requires an Unmanned Aerial Vehicle (UAV) agent to autonomously explore, reason, and identify a specific target using only visual perception and language description. However, existing methods struggle with the memorization of complex spatial representations in aerial environments, reliable and interpretable action decision-making, and inefficient exploration and information gathering. To address these challenges, we introduce **APEX** (Aerial Parallel Explorer), a novel hierarchical agent designed for efficient exploration and target acquisition in complex aerial settings. APEX is built upon a modular, three-part architecture: 1) Dynamic Spatio-Semantic Mapping Memory, which leverages the zero-shot capability of a Vision-Language Model (VLM) to dynamically construct high-resolution 3D Attraction, Exploration, and Obstacle maps, serving as an interpretable memory mechanism. 2) Action Decision Module, trained with reinforcement learning, which translates this rich spatial understanding into a fine-grained and robust control policy. 3) Target Grounding Module, which employs an open-vocabulary detector to achieve definitive and generalizable target identification. All these components are integrated into a hierarchical, asynchronous, and parallel framework, effectively bypassing the VLM's inference latency and boosting the agent's proactivity in exploration. Extensive experiments show that APEX outperforms the previous state of the art by +4.2% SR and +2.8% SPL on challenging UAV-ON benchmarks, demonstrating its superior efficiency and the effectiveness of its hierarchical asynchronous design.
DeepScan: A Training-Free Framework for Visually Grounded Reasoning in Large Vision-Language Models
PDF ↗Humans can robustly localize visual evidence and provide grounded answers even in noisy environments by identifying critical cues and then relating them to the full context in a bottom-up manner. Inspired by this, we propose DeepScan, a training-free framework that combines Hierarchical Scanning, Refocusing, and Evidence-Enhanced Reasoning for visually grounded reasoning in Large Vision-Language Models (LVLMs). Unlike existing methods that pursue one-shot localization of complete evidence, Hierarchical Scanning performs local cue exploration and multi-scale evidence extraction to recover evidence in a bottom-up manner, effectively mitigating the impacts of distractive context. Refocusing then optimizes the localized evidence view through collaboration of LVLMs and visual experts. Finally, Evidence-Enhanced Reasoning aggregates multi-granular views via a hybrid evidence memory and yields accurate and interpretable answers. Experimental results demonstrate that DeepScan significantly boosts LVLMs in diverse visual tasks, especially in fine-grained visual understanding. It achieves 90.6% overall accuracy on V* when integrated with Qwen2.5-VL-7B. Moreover, DeepScan provides consistent improvements for LVLMs across various architectures and model scales without additional adaptation cost. The code will be open-source soon.
Reinforcement learning (RL) provides a principled framework for improving vision-language models (VLMs) on complex reasoning tasks. However, existing RL approaches often depend on human-annotated labels or task-specific heuristics to define verifiable rewards--both costly and limited in scalability. We introduce VisPlay, a self-evolving RL framework that enables VLMs to autonomously improve their reasoning capabilities from massive unlabeled image data. Starting from a single base VLM, VisPlay assigns the model into two interacting roles: an Image-Conditioned Questioner that formulates challenging yet answerable visual questions, and a Multimodal Reasoner that generates silver responses. These roles are jointly trained using Group Relative Policy Optimization (GRPO), which uses diversity and difficulty rewards to balance the difficulty of generated questions with the quality of silver answers. VisPlay scales efficiently across two model families. Trained on Qwen2.5-VL and MiMo-VL, VisPlay achieves consistent improvements in visual reasoning, compositional generalization, and hallucination reduction across eight benchmarks including MM-Vet and MMMU, and establishes a scalable path toward self-evolving multimodal intelligence.
Finetuning Large Vision-Language Models with reinforcement learning has emerged as a promising approach to enhance their capability in object-level grounding. However, existing methods, mainly based on GRPO, assign rewards at the response level. Such sparse reward leads to minimal learning signals when all candidate responses are failed in challenging scenarios.In this work, we propose a group-revision optimisation paradigm that enhances learning on hard cases. It begins with a sampled initial response and generates a set of revised candidates to explore improved grounding outcomes. Inspired by reward shaping, we introduce a consolidation process that quantifies each candidate's improvement over the initial attempt and converts it into informative shaping signals.These signals are used to both refine the reward and modulate the advantage, amplifying the influence of high-quality revisions.Our method achieves consistent gains across referring and reasoning segmentation, REC, and counting benchmarks compared with prior GRPO-based models. Code is available at https://github.com/yyliu01/GroupRevision.
DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Models
PDF ↗Multimodal Large Language Models have achieved impressive performance on a variety of vision-language tasks, yet their fine-grained visual perception and precise spatial reasoning remain limited. In this work, we introduce DiG (Differential Grounding), a novel proxy task framework where MLLMs learn fine-grained perception by identifying and localizing all differences between similar image pairs without prior knowledge of their number. To support scalable training, we develop an automated 3D rendering-based data generation pipeline that produces high-quality paired images with fully controllable discrepancies. To address the sparsity of difference signals, we further employ curriculum learning that progressively increases complexity from single to multiple differences, enabling stable optimization. Extensive experiments demonstrate that DiG significantly improves model performance across a variety of visual perception benchmarks and that the learned fine-grained perception skills transfer effectively to standard downstream tasks, including RefCOCO, RefCOCO+, RefCOCOg, and general multimodal perception benchmarks. Our results highlight differential grounding as a scalable and robust approach for advancing fine-grained visual reasoning in MLLMs.