AAAI 2026 论文列表

Open-vocabulary 3D scene understanding (OV-3D) aims to localize and classify novel objects beyond the closed set of object classes. However, existing approaches and benchmarks primarily focus on the open vocabulary problem within the context of object classes, which is insufficient in providing a holistic evaluation to what extent a model understands the 3D scene. In this paper, we introduce a more challenging task called Generalized Open-Vocabulary 3D Scene Understanding (GOV-3D) to explore the open vocabulary problem beyond object classes. It encompasses an open and diverse set of generalized knowledge, expressed as linguistic queries of fine-grained and object-specific attributes. To this end, we contribute a new benchmark named OpenScan, which consists of 3D object attributes across eight representative linguistic aspects, including affordance, property, and material. We further evaluate state-of-the-art OV-3D methods on our OpenScan benchmark and discover that these methods struggle to comprehend the abstract vocabularies of the GOV-3D task, a challenge that cannot be addressed simply by scaling up object classes during training. We highlight the limitations of existing methodologies and explore promising directions to overcome the identified shortcomings.

Existing state-of-the-art image tokenization methods leverage diverse semantic features from pre-trained vision models for additional supervision, to expand the distribution of latent representations and thereby improve the quality of image reconstruction and generation. These methods employ a locally supervised approach for semantic supervision, which limits the uniformity of semantic distribution. However, VA-VAE proves that a more uniform feature distribution yields better generation performance. In this work, we introduce a Global Perspective Tokenizer (GloTok), which utilizes global relational information to model a more uniform semantic distribution of tokenized features. Specifically, a codebook-wise histogram relation learning method is proposed to transfer the semantics, which are modeled by pre-trained models on the entire dataset, to the semantic codebook. Then, we design a residual learning module which recovers the fine-grained details to minimize the reconstruction error caused by quantization. Through the above design, GloTok delivers more uniformly distributed semantic latent representations, which facilitates the training of autoregressive (AR) models for generating high-quality images without requiring direct access to pre-trained models during the training process. Experiments on the standard ImageNet-1k benchmark clearly show that our proposed method achieves state-of-the-art reconstruction performance and generation quality.

Classifier-free guidance has become a staple for conditional generation with denoising diffusion models. However, a comprehensive understanding of classifier-free guidance is still missing. In this work, we carry out an empirical study to provide a fresh perspective on classifier-free guidance. Concretely, instead of solely focusing on classifier-free guidance, we trace back to the root, i.e., classifier guidance, pinpoint the key assumption for the derivation, and conduct a systematic study to understand the role of the classifier. On 1D data, we find that both classifier guidance and classifier-free guidance achieve conditional generation by pushing the denoising diffusion trajectories away from decision boundaries, i.e., areas where conditional information is usually entangled and is hard to learn. To validate this classifier-centric perspective on high-dimensional data, we assess whether a flow-matching postprocessing step that is designed to narrow the gap between a pre-trained diffusion model’s learned distribution and the real data distribution, especially near decision boundaries, can improve the performance. Experiments on various datasets verify our classifier-centric understanding.

Federated learning (FL) allows for collaborative model training while preserving data privacy, but its distributed nature makes it vulnerable to poisoning attacks. Existing defense methods typically rely on using gradients from multiple clients to define a trusted region, selecting only the trustworthy update (good gradients) within this region for aggregation. Mainstream defense boundaries are categorized as hard boundaries, soft boundaries, and semi-soft boundaries. However, we argue that even good gradients within these boundaries can still be exploited by attackers to poison the model. To tackle this challenge, we introduce a boundary-adaptive attack method that leverages the directional properties of optimization techniques to derive baseline poisoned gradients. Through iterative perturbation, it generates seemingly innocent gradients that subtly deviate from the global model. Our extensive study on benchmark datasets and mainstream defensive mechanisms confirms that the proposed attack raises a significantly threat to the integrity and security of FL practices, regardless of the flourishing of robust FL methods.

We propose DialoGen, a novel framework for generating realistic gestures for both interlocutors in dialog scenarios, conditioned on conversational audios. Unlike most existing methods that focus solely on a single speaker, DialoGen simultaneously generates synchronized gestures for both participants while also embedding identity-decoupled style into generated gestures that enhance realism and expressiveness. To ensure precise synchronization between interlocutors, DialoGen adopts an interactive dual-diffusion model with mutual interaction estimation, which integrates interaction correlation into the diffusion process. More importantly, by leveraging supervised contrastive learning, we develop the identity-decoupled style guidance to adaptively decompose the identity-specific style of interlocutors into latent space, enabling multi-style dialog gesture generation. Extensive experimental results demonstrate that our model significantly outperforms existing methods in generating realistic, speech-aligned, identity-specific gestures, offering a high-quality solution for various dialog scenarios.

Full-body motion tracking plays an essential role in AR/VR applications, bridging physical and virtual interactions. However, it is challenging to reconstruct realistic and diverse full-body poses based on sparse signals obtained by head-mounted displays, which are the main devices in AR/VR scenarios. Existing methods for pose reconstruction often incur high computational costs or rely on separately modeling spatial and temporal dependencies, making it difficult to balance accuracy, temporal coherence, and efficiency. To address this problem, we propose KineST, a novel kinematics-guided state space model, which effectively extracts spatiotemporal dependencies while integrating local and global pose perception. The innovation comes from two core ideas. Firstly, in order to better capture intricate joint relationships, the scanning strategy within the State Space Duality framework is reformulated into kinematics-guided bidirectional scanning, which embeds kinematic priors. Secondly, a mixed spatiotemporal representation learning approach is employed to tightly couple spatial and temporal contexts, balancing accuracy and smoothness. Additionally, a geometric angular velocity loss is introduced to impose physically meaningful constraints on rotational variations for further improving motion stability. Extensive experiments demonstrate that KineST has superior performance in both accuracy and temporal consistency within a lightweight framework.

Unrestricted adversarial attacks aim to fool DNNs by generating effective yet photorealistic examples. However, previous methods usually rely on global perturbations to enhance attack performance, which inevitably introduces visual distortions. To reduce visual distortions in the background, we propose a diffusion-based framework that focuses on local perturbations to generate object-level unrestricted adversarial examples (ObjectAdv). Since the cross-attention maps of Stable Diffusion contain the object information, we directly leverage the attention maps to localize the semantic region of object where for attacking. Second, a prompt-switching strategy is proposed for both imperceptibility and attack capacity. Specifically, to preserve layout and object shape of clean image, a prompt of true category is used at early denoising steps. At the later steps, we propose a well-designed prompt to guide the diffusion model to generate transferable adversarial examples. This local attack may cause inconsistency between the perturbed object and the background in adversarial examples. An FFT-based edge smoother is utilized to ensure seamless blending of the edges. ObjectAdv achieves an average ASR of 99.2% in white-box test on the ImageNet-compatible dataset, and outperforms existing methods on defense performance (+5%) and image quality metrics, e.g., SSIM of 0.9140 (+0.1048) and FID of 25.63 (-19.27).

Unsupervised domain adaptation for LiDAR-based 3D object detection (3D UDA) based on the teacher-student architecture with pseudo labels has achieved notable improvements in recent years. Although it is quite popular to collect point clouds and images simultaneously, little attention has been paid to the usefulness of image data in 3D UDA when training the models. In this paper, we propose an approach named MMAssist that improves the performance of 3D UDA with multi-modal assistance. A method is designed to align 3D features between the source domain and the target domain by using image and text features as bridges. More specifically, we project the ground truth labels or pseudo labels to the images to get a set of 2D bounding boxes. For each 2D box, we extract its image feature from a pre-trained vision backbone. A large vision-language model (LVLM) is adopted to extract the box's text description, and a pre-trained text encoder is used to obtain its text feature. During the training of the model in the source domain and the student model in the target domain, we align the 3D features of the predicted boxes with their corresponding image and text features, and the 3D features and the aligned features are fused with learned weights for the final prediction. The features between the student branch and the teacher branch in the target domain are aligned as well. To enhance the pseudo labels, we use an off-the-shelf 2D object detector to generate 2D bounding boxes from images and estimate their corresponding 3D boxes with the aid of point cloud, and these 3D boxes are combined with the pseudo labels generated by the teacher model. Experimental results show that our approach achieves promising performance compared with state-of-the-art methods in three domain adaptation tasks on three popular 3D object detection datasets.

Multi-view 3D object detection has garnered increasing attention, particularly due to its success in autonomous driving systems. Although multi-view systems possess rich semantic information, their spatial-geometric reasoning capabilities remain limited. Recent studies employ simulated point cloud generation mechanisms to facilitate LiDAR-camera multi-modal knowledge distillation, achieving formal structural consistency. Despite advancements, these methods still face two main issues: i) alignment challenges caused by discrepancies between LiDAR and camera data, and ii) prediction errors from simulated point clouds that compromise the semantic information extracted from images during fusion. To address these problems, we propose adaptive-smooth distillation to optimize alignment granularity based on feature discrepancies for improved LiDAR-camera knowledge distillation. Specifically, this work considers both LIDAR-to-camera cross-modal distillation and LiDAR-camera fusion to simulated point cloud-camera fusion multi-modal distillation. Then, we introduce a heterogeneous fusion module to strategically bias the fusion process toward the extracted camera features, thereby enhancing the robustness of the fusion feature. Additionally, soft-weighted response distillation is proposed to facilitate the student model to selectively mimic the high-quality output of the teacher model. Extensive experiments have demonstrated the superiority of our method, achieving statistically significant improvements of 4.9% in mean Average Precision (mAP) and 4.5% in NuScenes Detection Score (NDS) over the benchmark.

Unsupervised video Object-Centric Learning (OCL) is promising as it enables object-level scene representation and understanding as we humans do. Mainstream video OCL methods adopt a recurrent architecture: An aggregator aggregates current video frame into object features, termed slots, under some queries; A transitioner transits current slots to queries for the next frame. This is an effective architecture but all existing implementations both (i1) neglect to incorporate next frame features, the most informative source for query prediction, and (i2) fail to learn transition dynamics, the knowledge essential for query prediction. To address these issues, we propose Random Slot-Feature pair for learning Query prediction (RandSF.Q): (t1) We design a new transitioner to incorporate both slots and features, which provides more information for query prediction; (t2) We train the transitioner to predict queries from slot-feature pairs randomly sampled from available recurrences, which drives it to learn transition dynamics. Experiments on scene representation demonstrate that our method surpass existing video OCL methods significantly, e.g., up to 10 points on object discovery, setting new state-of-the-art. Such superiority also benefits downstream tasks like scene understanding.

Infrared and Visible Image Fusion (IVIF) produces enhanced images by fusing complementary visual information. However, most existing methods generate fixed outputs and cannot flexibly adapt to user-specific requirements. Recent text-guided approaches offer partial control but are limited to global or semantic levels, lacking instance-level control. This limitation arises from two challenges: first, the lack of datasets that directly link textual instructions with corresponding spatial annotations, and second, the use of coarse cross-modal alignment methods that struggle to precisely match textual instructions with visual features. To overcome these challenges, we propose ControlFuse, a controllable IVIF framework enabling multi-granularity fusion across global, semantic, and instance levels, guided by user instructions. First, we construct an automated multi-granularity dataset that provides explicit textual-mask correspondences at these three levels. Second, inspired by manifold geometry, we design a Multimodal Feature Interaction Module (MFIM) comprising Feature Manifold Converter (FMC) and Curvature-Guided Interaction (CGI). FMC projects textual and visual features into a unified manifold space, while CGI leverages manifold curvature as a geometric cue to refine cross-modal alignment. Extensive experiments validate ControlFuse, outperforming state-of-the-art methods in robustness and flexibility.

Though deep neural models adopted to realize the perception of autonomous driving have proven vulnerable to adversarial examples, known attacks often leverage 2D patches and target mostly monocular perception. Therefore, the effectiveness of Physical Adversarial Examples (PAEs) on stereo-based binocular depth estimation remains largely unexplored. To this end, we propose the first texture-enabled physical adversarial attack against stereo matching models in the context of autonomous driving. Our method employs a 3D PAE with global camouflage texture rather than a local 2D patch-based one, ensuring both visual consistency and attack effectiveness across different viewpoints of stereo cameras. To cope with the disparity effect of these cameras, we also propose a new 3D stereo matching rendering module that allows the PAE to be aligned with real-world positions and headings in binocular vision. We further propose a novel merging attack that seamlessly blends the target into the environment through fine-grained PAE optimization. It has significantly enhanced stealth and lethality upon existing hiding attacks that fail to get seamlessly merged into the background. Extensive evaluations show that our PAEs can successfully fool the stereo models into producing erroneous depth information.

Images are typically sampled on a uniform grid,despite their non-uniform information distribution—some regions are rich in content while others are not. The mismatch leads to inefficient computation allocation in deep learning models. To address this, recent studies have proposed predictive downsampling methodsthat adaptively downsample images based on predicted per-pixel importance, allocating more pixels to informative areas. However,these methods require high-resolution processing to accurately estimate importance, which undermines their efficiency:the prediction itself must process the full-resolution image,consuming most of the computational budget. This high-resolution importance prediction is necessary because each input may differ significantly in structure and content. In this paper, we take a different approach and introduce a learn-to-downsample paradigmtailored for aligned vision recognition tasks, such as face recognition and palmprint recognition, where input alignment ensures consistent spatial structure across images. This alignment ensures structural consistency across images, allowing a shared, input-agnostic downsampling template applicable to all inputs. Furthermore, instead of relying on implicit importance maps, we introduce a flow-based representation that explicitly models the spatial warping from the original image to the downsampled version. The flow representation is not only more efficient but also more controllable: we regularize the flow using its Jacobian determinant to precisely control the sampling density and coverage,enabling interpretable and tunable sampling patterns. Extensive experiments on two aligned recognition tasks, face and palmprint recognition, demonstrate that our method substantially reduces computational cost with minimal accuracy degradation, achieving a significantly better performance-efficiency trade-off than existing predictive downsampling methods.

Learning procedural-aware video representations is a key step towards building agents that can reason about and execute complex tasks. Existing methods typically address this problem by aligning visual content with textual descriptions at the task and step levels to inject procedural semantics into video representations. However, due to their high level of abstraction, "task" and "step" descriptions fail to form a robust alignment with the concrete, observable details in visual data. To address this, we introduce "states", i.e., textual snapshots of object configurations, as a visually-grounded semantic layer that anchors abstract procedures to what a model can actually see. We formalize this insight in a novel Task-Step-State (TSS) framework, where tasks are achieved via steps that drive transitions between observable states. To enforce this structure, we propose a progressive pre-training strategy that unfolds the TSS hierarchy, forcing the model to first ground representations in states before associating them with steps and, ultimately, high-level tasks. Extensive experiments on the COIN and CrossTask datasets show that our method outperforms baseline models on multiple downstream tasks, including task recognition, step recognition, and next step prediction. Ablation studies show that introducing state supervision is a key driver of performance gains across all tasks. Additionally, our progressive pretraining strategy proves more effective than standard joint training, as it better enforces the intended hierarchical structure.

Facial expression captioning has found widespread application across various domains. Recently, the emergence of video Multimodal Large Language Models (MLLMs) has shown promise in general video understanding tasks. However, describing facial expressions within videos poses two major challenges for these models: (1) the lack of adequate datasets and benchmarks, and (2) the limited visual token capacity of video MLLMs. To address these issues, this paper introduces a new instruction-following dataset tailored for dynamic facial expression caption. The dataset comprises 5,033 high-quality video clips annotated manually, containing over 700,000 tokens. Its purpose is to improve the capability of video MLLMs to discern subtle facial nuances. Furthermore, we propose FaceTrack-MM, which leverages a limited number of tokens to encode the main character’s face. This model demonstrates superior performance in tracking faces and focusing on the facial expressions of the main characters, even in intricate multiperson scenarios. Additionally, we introduce a novel evaluation metric combining event extraction, relation classification, and the longest common subsequence (LCS) algorithm to assess the content consistency and temporal sequence consistency of generated text. Moreover, we present FECBench, a benchmark designed to assess the performance of existing video MLLMs in this specific task.

Multi-view 3D object detection plays a vital role in autonomous driving systems due to its ability to perceive complex scenes accurately. However, real-world driving data often exhibits a long-tailed distribution, causing significant drops in detection accuracy for rare categories in existing methods. To mitigate this issue, we propose CLIPDet3D, a novel vision-language collaborative framework for multi-view 3D object detection. First, to tackle the difficulty of capturing the semantic information of rare categories, a Vision-Language Collaborative Learning strategy is proposed to incorporate class-level semantic priors from CLIP. Second, a Depth Feature Contrastive Distillation module is designed to overcome the large depth estimation error for rare categories by aligning depth features between a teacher and a student network. Furthermore, to alleviate the difficulty in focusing on regions of rare categories, a Dual-Stream Prompt Attention mechanism is devised to inject learnable prompts and compute attention along both horizontal and vertical BEV directions. Evaluations on the nuScenes dataset demonstrate that CLIPDet3D achieves state-of-the-art accuracy while maintaining efficient inference.

Lifelong person re-identification (LReID) aims to retrieve the target person from sequentially collected data. Due to significant domain gaps between datasets and the continuous increase of training data from different scenarios, weak inter-domain generalization and catastrophic forgetting issues have remained major challenges for LReID. To tackle these issues, a novel LReID method called Unified Representation Causal Prompt Distillation (URCPD) is proposed. Specifically, to reduce domain gaps among different scene datasets and improve model inter-domain generalization capability, a Feature Decoupling Style Transfer module (FDST) is proposed to map new features into a unified feature space. Furthermore, to reduce the accumulated forgetting of old knowledge during the training stage, a Causal Prompt Distillation module (CPD) is introduced. This module eliminates the re-inference process for distillation and embeds memory prompts to combat catastrophic forgetting. Extensive experiments on five classic LReID seen datasets and seven unseen datasets demonstrate that our method significantly outperforms state-of-the-art methods.

While current state-of-the-art Remote Sensing Change Detection (RSCD) methods can achieve impressive results on individual datasets, they become unreliable in unseen environments and imaging conditions, with performance metrics declining by as much as 60% to 80%. Simultaneously, variable environments and complex imaging conditions are the main characteristics of remote sensing data, calling for generalizable RSCD methods. To address this issue, we propose a novel RSCD method capable of domain generalization—CDDGNet. This method is based on causal decoupling theory, which progressively decouples invariant change features from variable domain features to extract generalizable characteristics. This enables a network trained on a single domain to accurately identify change regions in other domains. Specifically, firstly, the Causal Feature Adaptation Module is proposed to preliminarily decouple and simplify feature information during the encoding process by using wavelet transformation and feature energy spectralization methods. Secondly, the Causal Feature Fusion Module is presented to fully decouple features and aggregate significant change features during the decoding process through frequency domain processing and feature re-attention mechanisms. Thirdly, the Decoupling Effect Loss Function is proposed to optimize the process by evaluating the effectiveness of causal decoupling. Extensive experiments have shown that our model significantly outperforms existing methods across multiple groups of generalization tasks with varying levels of difficulty.

A dexterous hand capable of generalizable grasping objects is fundamental for the development of general-purpose embodied AI. However, previous methods focus narrowly on low-level grasp stability metrics, neglecting affordance-aware positioning and human-like poses which are crucial for downstream manipulation. To address these limitations, we propose AffordDex, a novel framework with two-stage training that learns a universal grasping policy with an inherent understanding of both motion priors and object affordances. In the first stage, a trajectory imitator is pre-trained on a large corpus of human hand motions to instill a strong prior for natural movement. In the second stage, a residual module is trained to adapt these general human-like motions to specific object instances. This refinement is critically guided by two components: our Negative Affordance-aware Segmentation (NAA) module, which identifies functionally inappropriate contact regions, and a privileged teacher-student distillation process that ensures the final vision-based policy is highly successful. Extensive experiments demonstrate that AffordDex not only achieves universal dexterous grasping but also remains remarkably human-like in posture and functionally appropriate in contact location. As a result, AffordDex significantly outperforms state-of-the-art baselines across seen objects, unseen instances, and even entirely novel categories.