Text-guided image inpainting aims to inpaint masked image regions based on a textual prompt while preserving the background. Although diffusion-based methods have become dominant, their property of modeling the entire image in latent space makes it challenging for the results to align well with prompt details and maintain a consistent background. To address these issues, we explore Mask AutoRegressive (MAR) models for this task. MAR naturally supports image inpainting by generating latent tokens corresponding to mask regions, enabling better local controllability without altering the background. However, directly applying MAR to this task makes the inpainting content either ignore the prompts or be disharmonious with the background context. Through analysis of the attention maps from the inpainting images, we identify the impact of background tokens on text tokens during the MAR generation, and leverage this to designToken Painter, a training-free text-guided image inpainting method based on MAR. Our approach introduces two key components: (1) Dual-Stream Encoder Information Fusion (DEIF), which fuses the semantic and context information from text and background in frequency domain to produce novel guidance tokens, allowing MAR to generate text-faithful inpainting content while keeping harmonious with background context. (2) Adaptive Decoder Attention Score Enhancing (ADAE), which adaptively enhances attention scores on guidance tokens and inpainting tokens to further enhance the alignment of prompt details and the content visual quality. Extensive experiments demonstrate that our training-free method outperforms prior state-of-the-art methods across almost all metrics.

Referring Audio-Visual Segmentation (Ref-AVS) aims to segment target objects in audible videos based on given reference expressions. Prior works typically rely on learning latent embeddings via multimodal fusion to prompt a tunable SAM/SAM2 decoder for segmentation, which requires strong pixel-level supervision and lacks interpretability. From a novel perspective of explicit reference understanding, we propose TGS-Agent, which decomposes the task into a Think-Ground-Segment process, mimicking the human reasoning procedure by first identifying the referred object through multimodal analysis, followed by coarse-grained grounding and precise segmentation. To this end, we first propose Ref-Thinker, a multimodal language model capable of reasoning over textual, visual, and auditory cues. We construct an instruction-tuning dataset with explicit object-aware think-answer chains for Ref-Thinker fine-tuning. The object description inferred by Ref-Thinker is used as an explicit prompt for Grounding-DINO and SAM2, which perform grounding and segmentation without relying on pixel-level supervision. Additionally, we introduce R2-AVSBench, a new benchmark with linguistically diverse and reasoning-intensive references for better evaluating model generalization. Our approach achieves state-of-the-art results on both standard Ref-AVSBench and proposed R2-AVSBench.

Vision-language models (VLMs) have shown strong generalization across multimodal tasks, but adapting them to medical report generation (MRG) often demands extensive paired image-text data that are limited due to data privacy and annotation cost. In-context learning (ICL) offers a promising training-free alternative, yet standard ICL approaches rely on long demonstration prompts that are computationally inefficient and often yield inconsistent or clinically inaccurate descriptions. To address these challenges, we propose Principal In-Context Vectors (PCVs), a compact latent-guidance framework that distills multimodal demonstrations into stable semantic representations. By extracting hidden states from auto-regressive VLMs and applying principal component analysis (PCA), we identify robust semantic directions that remain stable under input perturbations. These PCVs are then injected into new queries to steer generation toward accurate and clinically meaningful outputs without any model tuning. Extensive experiments on four MRG benchmark datasets show that our approach can enhance both zero-shot and fully supervised generation quality across diverse settings, including cross-center, cross-disease, and longitudinal scenarios. This work provides a lightweight and scalable approach to adapt pre-trained VLMs for practical clinical deployment.

Recent studies have revealed the potential of training open-source Large Language Models (LLMs) to unleash LLMs' reasoning ability for enhancing vision-language navigation (VLN) performance, and simultaneously mitigate the domain gap between LLMs' training corpus and the VLN task. However, these approaches predominantly adopt straightforward input-output mapping paradigms, causing the mapping learning difficult and the navigational decisions unexplainable. Chain-of-Thought (CoT) training is a promising way to improve both navigational decision accuracy and interpretability, while the complexity of the navigation task makes the perfect CoT labels unavailable and may lead to overfitting through pure CoT supervised fine-tuning. To address these issues, we propose EvolveNav, a novel sElf-improving embodied reasoning paradigm that realizes adaptable and generalizable navigational reasoning for boosting LLM-based vision-language Navigation. Specifically, EvolveNav involves a two-stage training process: (1) Formalized CoT Supervised Fine-Tuning, where we train the model with curated formalized CoT labels to first activate the model's navigational reasoning capabilities, and simultaneously increase the reasoning speed; (2) Self-Reflective Post-Training, where the model is iteratively trained with its own reasoning outputs as self-enriched CoT labels to enhance the supervision diversity. A self-reflective auxiliary task is also designed to encourage the model to learn correct reasoning patterns by contrasting with wrong ones. Experimental results under both task-specific and cross-task training paradigms demonstrate the consistent superiority of EvolveNav over previous LLM-based VLN approaches on various popular benchmarks, including R2R, REVERIE, CVDN, and SOON. EvolveNav open avenues for exploring effective self-improving reasoning paradigms, enabling building agents capable of self-evolving for promoting LLM-based embodied AI research.

Recent advances in multimodal large language models (MLLMs) have enabled impressive progress in visual-language reasoning, yet long-video understanding remains a formidable challenge due to the need for coherent reasoning over ultra-long spatiotemporal dependencies. Existing methods struggle with the vast candidate space for relevant information in long videos, often failing to distinguish meaningful events from redundant content. We identify two critical and previously under-explored issues: absolute redundancy, where static visual content inflates token counts without adding narrative value, and relative redundancy, where task-irrelevant segments introduce noise that impairs reasoning. Compounding these issues is the weak spatiotemporal modeling in current MLLMs, which limits their ability to capture complex event dynamics. To address these multifaceted challenges, we introduce SELongVLM, a dynamically lenient-to-stringent selection long video language model. SELongVLM integrates two coordinated branches: a Residual Token Pruner (RTP) that removes repetitive background tokens via inter-frame residual modeling thus mitigating absolute redundancy while preserving motion cues, and a Semantic-aware Self-Correction Selector (SCSelector) that progressively refines query-relevant clip selection without frame-level annotations to reduce relative redundancy, guided by a stringent-to-lenient self-correcting mechanism during optimization. To ensure causal continuity and bolster spatiotemporal reasoning across disjoint clips, the framework further incorporates an action-aware operation for intra-clip dynamics and a temporal memory for cross-clip context, enabling robust spatiotemporal inference on long videos. Extensive experiments across eight benchmarks demonstrate that SELongVLM markedly outperforms existing models on both general and specialized long-video tasks. Specifically, it achieves 65.5% on VideoMME and 69.8% on MLVU for general benchmarks, and delivers strong performance on four specialized benchmarks - for example, 39.2% on TOMATO for fine-grained temporal reasoning and 69.2% on EventBench for event-level understanding.

Mainstream research in audio-visual learning has focused on designing task-specific expert models, primarily implemented through sophisticated multimodal fusion approaches. Recently, a few efforts have aimed to develop more task-independent or universal audiovisual embedding networks, encoding advanced representations for use in various audiovisual downstream tasks. This is typically achieved by fine-tuning large pretrained transformers, such as Swin-V2-L and HTS-AT, in a parameter-efficient manner through techniques such as tuning only a few adapter layers inserted into the pretrained transformer backbone. Although these methods are parameter-efficient, they suffer from significant training memory consumption due to gradient backpropagation through the deep transformer backbones, which limits accessibility for researchers with constrained computational resources. In this paper, we present Meta-Token Learning (Mettle), a simple and memory-efficient method for adapting large-scale pretrained transformer models to downstream audio-visual tasks. Instead of sequentially modifying the output feature distribution of the transformer backbone, Mettle utilizes a lightweight Layer-Centric Distillation (LCD) module to distill in parallel the intact audio or visual features embedded by each transformer layer into compact meta-tokens. This distillation process considers both pretrained knowledge preservation and task-specific adaptation. The obtained meta-tokens can be directly applied to classification tasks, such as audio-visual event localization and audio-visual video parsing. To further support fine-grained segmentation tasks, such as audio-visual segmentation, we introduce a Meta-Token Injection (MTI) module, which utilizes the audio and visual meta-tokens distilled from the top transformer layer to guide feature adaptation in earlier layers. Extensive experiments on multiple audiovisual benchmarks demonstrate that our method significantly reduces memory usage and training time while maintaining parameter efficiency and competitive accuracy.

Long-term time series forecasting (LTSF) is fundamental to various real-world applications, where Transformer-based models have become the dominant framework due to their ability to capture long-range dependencies. However, these models often experience overfitting due to data redundancy in rolling forecasting settings, limiting their generalization ability particularly evident in longer sequences with highly similar adjacent data. In this work, we introduce CLMFormer, a novel framework that mitigates redundancy through curriculum learning and a memory-driven decoder. Specifically, we progressively introduce Bernoulli noise to the training samples, which effectively breaks the high similarity between adjacent data points. This curriculum-driven noise introduction aids the memory-driven decoder by supplying more diverse and representative training data, enhancing the decoder’s ability to model seasonal tendencies and dependencies in the time series data. To further enhance forecasting accuracy, we introduce a memory-driven decoder. This component enables the model to capture seasonal tendencies and dependencies in the time series data and leverages temporal relationships to facilitate the forecasting process. Extensive experiments on six real-world LTSF benchmarks show that CLMFormer consistently improves Transformer-based models by up to 30%, demonstrating its effectiveness in long-horizon forecasting.

Vision-And-Language Navigation (VLN) suffers from the limited diversity and scale of training data, primarily constrained by the manual curation of existing simulators. To address this, we introduce RoomTour3D, a video-instruction dataset derived from web-based room tour videos that capture real-world indoor spaces and human walking demonstrations. Unlike existing VLN datasets, RoomTour3D leverages the scale and diversity of online videos to generate open-ended human walking trajectories and open-world navigable instructions. To compensate for the lack of navigation data in online videos, we perform 3D reconstruction and obtain 3D trajectories of walking paths augmented with additional information on the room types, object locations and 3D shape of surrounding scenes. Our dataset includes ~100K open-ended description-enriched trajectories with ~200K instructions, and 17K action-enriched trajectories from 1847 room tour environments. We demonstrate experimentally that RoomTour3D enables significant improvements across multiple VLN tasks including CVDN, SOON, R2R, and REVERIE. Moreover, Room-Tour3D facilitates the development of trainable zero-shot VLN agents, showcasing the potential and challenges of advancing towards open-world navigation.

A short clip of video may contain progression of multiple events and an interesting story line. A human need to capture both the event in every shot and associate them together to understand the story behind it. In this work, we present a new multi-shot video understanding benchmark \dataset with detailed shot-level captions, comprehensive video summaries and question-answering pairs. To facilitate better semantic understanding of videos, we provide captions for both visual signals and human narrations. We design several distinct tasks including single-shot video captioning, multi-shot video summarization, and multi-shot video question answering. Preliminary experiments show some challenges to generate a long and comprehensive video summary for multi-shot videos. Nevertheless, the generated imperfect summaries can already achieve competitive performance on existing video understanding tasks such as video question-answering, promoting an under-explored setting of video understanding with detailed summaries.

Large Language Models (LLMs) have demonstrated remarkable planning abilities across various domains, including robotic manipulation and navigation. While recent work in robotics deploys LLMs for high-level and low-level planning, existing methods often face challenges with failure recovery and suffer from hallucinations in long-horizon tasks. To address these limitations, we propose a novel multi-agent LLM framework, Multi-Agent Large Language Model for Manipulation (MALMM). Notably, MALMM distributes planning across three specialized LLM agents, namely high-level planning agent, low-level control agent, and a supervisor agent. Moreover, by incorporating environment observations after each step, our framework effectively handles intermediate failures and enables adaptive re-planning. Unlike existing methods, MALMM does not rely on pre-trained skill policies or in-context learning examples and generalizes to unseen tasks. In our experiments, MALMM demonstrates excellent performance in solving previously unseen long-horizon manipulation tasks, and outperforms existing zero-shot LLM-based methods in RLBench by a large margin. Experiments with the Franka robot arm further validate our approach in real-world settings.

While vision-language models (VLMs) have demonstrated promising capabilities in reasoning and planning for embodied agents, their ability to comprehend physical phenomena, particularly within structured 3D environments, remains severely limited. To close this gap, we introduce PhyBlock, a progressive benchmark designed to assess VLMs on physical understanding and planning through robotic 3D block assembly tasks. PhyBlock integrates a novel four-level cognitive hierarchy assembly task alongside targeted Visual Question Answering (VQA) samples, collectively aimed at evaluating progressive spatial reasoning and fundamental physical comprehension, including object properties, spatial relationships, and holistic scene understanding. PhyBlock includes 2600 block tasks (400 assembly tasks, 2200 VQA tasks) and evaluates models across three key dimensions: partial completion, failure diagnosis, and planning robustness. We benchmark 23 state-of-the-art VLMs, highlighting their strengths and limitations in physically grounded, multi-step planning. Our empirical findings indicate that the performance of VLMs exhibits pronounced limitations in high-level planning and reasoning capabilities, leading to a notable decline in performance for the growing complexity of the tasks.Error analysis reveals persistent difficulties in spatial orientation and dependency reasoning.We position PhyBlock as a unified testbed to advance embodied reasoning, bridging vision-language understanding and real-world physical problem-solving.

The creation of new datasets often presents new challenges for video recognition and can inspire novel ideas while addressing these challenges. While existing datasets mainly comprise landscape mode videos, our paper seeks to introduce portrait mode videos to the research community and highlight the unique challenges associated with this video format. With the growing popularity of smartphones and social media applications, recognizing portrait mode videos is becoming increasingly important. To this end, we have developed the first dataset dedicated to portrait mode video recognition, namely PortraitMode-400. The taxon-omy of PortraitMode-400 was constructed in a data-driven manner, comprising 400 fine-grained categories, and rigorous quality assurance was implemented to ensure the accuracy of human annotations. In addition to the new dataset, we conducted a comprehensive analysis of the impact of video format (portrait mode versus landscape mode) on recognition accuracy and spatial bias due to the different formats. Furthermore, we designed extensive experiments to explore key aspects of portrait mode video recognition, including the choice of data augmentation, evaluation procedure, the importance of temporal information, and the role of audio modality. Building on the insights from our experimental results and the introduction of PortraitMode-400, our paper aims to inspire further research efforts in this emerging research direction.

In this paper, we focus on the weakly supervised video object detection problem, where each training video is only tagged with object labels, without any bounding box annotations of objects. To effectively train object detectors from such weakly-annotated videos, we propose a Progressive Frame-Proposal Mining (PFPM) framework by exploiting discriminative proposals in a coarse-to-fine manner. First, we design a flexible Multi-Level Selection (MLS) scheme, with explicit guidance of video tags. By selecting object-relevant frames and mining important proposals from these frames, the proposed MLS can effectively reduce frame redundancy as well as improve proposal effectiveness to boost weakly-supervised detectors. Moreover, we develop a novel Holistic-View Refinement (HVR) scheme, which can globally evaluate importance of proposals among frames, and thus correctly refine pseudo ground truth boxes for training video detectors in a self-supervised manner. Finally, we evaluate the proposed PFPM on a large-scale benchmark for video object detection, on ImageNet VID, under the setting of weak annotations. The experimental results demonstrate that our PFPM significantly outperforms the state-of-the-art weakly-supervised detectors.

Referring Video Object Segmentation (RVOS) is to segment the object instance from a given video, according to the textual description of this object. However, in the open world, the object descriptions are often diversified in contents and flexible in lengths. This leads to the key difficulty in RVOS, i.e., various descriptions of different objects are corresponding to different temporal scales in the video, which is ignored by most existing approaches with single stride of frame sampling. To tackle this problem, we propose a concise Hybrid Temporal-scale Multimodal Learning (HTML) framework, which can effectively align lingual and visual features to discover core object semantics in the video, by learning multimodal interaction hierarchically from different temporal scales. More specifically, we introduce a novel inter-scale multimodal perception module, where the language queries dynamically interact with visual features across temporal scales. It can effectively reduce complex object confusion by passing video context among different scales. Finally, we conduct extensive experiments on the widely used benchmarks, including Ref-Youtube-VOS, Ref-DAVIS17, A2D-Sentences and JHMDB-Sentences, where our HTML achieves state-of-the-art performance on all these datasets.

Video Semantic Segmentation (VSS) involves assigning a semantic label to each pixel in a video sequence. Prior work in this field has demonstrated promising results by extending image semantic segmentation models to exploit temporal relationships across video frames; however, these approaches often incur significant computational costs. In this paper, we propose an efficient mask propagation framework for VSS, called MPVSS. Our approach first employs a strong query-based image segmentor on sparse key frames to generate accurate binary masks and class predictions. We then design a flow estimation module utilizing the learned queries to generate a set of segment-aware flow maps, each associated with a mask prediction from the key frame. Finally, the mask-flow pairs are warped to serve as the mask predictions for the non-key frames. By reusing predictions from key frames, we circumvent the need to process a large volume of video frames individually with resource-intensive segmentors, alleviating temporal redundancy and significantly reducing computational costs. Extensive experiments on VSPW and Cityscapes demonstrate that our mask propagation framework achieves SOTA accuracy and efficiency trade-offs. For instance, our best model with Swin-L backbone outperforms the SOTA MRCFA using MiT-B5 by 4.0% mIoU, requiring only 26% FLOPs on the VSPW dataset. Moreover, our framework reduces up to 4× FLOPs compared to the per-frame Mask2Former baseline with only up to 2% mIoU degradation on the Cityscapes validation set. Code is available at https://github.com/ziplab/MPVSS.

Learning spatial-temporal relation among multiple actors is crucial for group activity recognition. Different group activities often show the diversified interactions between actors in the video. Hence, it is often difficult to model complex group activities from a single view of spatial-temporal actor evolution. To tackle this problem, we propose a distinct Dual-path Actor Interaction (Dual-AI) framework, which flexibly arranges spatial and temporal transformers in two complementary orders, enhancing actor relations by integrating merits from different spatio-temporal paths. Moreover, we introduce a novel Multi-scale Actor Contrastive Loss (MAC-Loss) between two interactive paths of Dual-AI. Via self-supervised actor consistency in both frame and video levels, MAC-Loss can effectively distinguish individual actor representations to reduce action confusion among different actors. Consequently, our Dual-AI can boost group activity recognition by fusing such discriminative features of different actors. To evaluate the proposed approach, we conduct extensive experiments on the widely used benchmarks, including Volleyball [21], Collective Activity [II], and NBA datasets [49]. The proposed Dual-AI achieves state-of-the-art performance on all these datasets. It is worth noting the proposed Dual-AI with 50% training data outperforms a number of recent approaches with 100% training data. This confirms the generalization power of Dual-AI for group activity recognition, even under the challenging scenarios of limited supervision.

As a new method of Earth observation, video satellite is capable of monitoring specific events on the Earth's surface continuously by providing high-temporal resolution remote sensing images. The video observations enable a variety of new satellite applications such as object tracking and road traffic monitoring. In this article, we address the problem of fast object tracking in satellite videos, by developing a novel tracking algorithm based on correlation filters embedded with motion estimations. Based on the kernelized correlation filter (KCF), the proposed algorithm provides the following improvements: 1) proposing a novel motion estimation (ME) algorithm by combining the Kalman filter and motion trajectory averaging and mitigating the boundary effects of KCF by using this ME algorithm and 2) solving the problem of tracking failure when a moving object is partially or completely occluded. The experimental results demonstrate that our algorithm can track the moving object in satellite videos with 95% accuracy.