Xijun Wang

Tianrui Guan, Fuxiao Liu, Xiyang Wu et al. · uw

We introduce HallusionBench, a comprehensive benchmark designed for the evaluation of image-context reasoning. This benchmark presents significant challenges to advanced large visual-language models (LVLMs), such as GPT-4V(Vision), Gemini Pro Vision, Claude 3, and LLaVA-1.5, by emphasizing nuanced understanding and interpretation of visual data. The benchmark comprises 346 images paired with 1129 questions, all meticulously crafted by human experts. We introduce a novel structure for these visual questions designed to establish control groups. This structure enables us to conduct a quantitative analysis of the models' response tendencies, logical consistency, and various failure modes. In our evaluation on HallusionBench, we benchmarked 15 different models, highlighting a 31.42% question-pair accuracy achieved by the state-of-the-art GPT-4V. Notably, all other evaluated models achieve accuracy below 16%. Moreover, our analysis not only highlights the observed failure modes, including language hallucination and visual illusion, but also deepens an understanding of these pitfalls. Our comprehensive case studies within HallusionBench shed light on the challenges of hallucination and illusion in LVLMs. Based on these insights, we suggest potential pathways for their future improvement. The benchmark and codebase can be accessed at https://github.com/tianyi-lab/HallusionBench.

Tianrui Guan, Aswath Muthuselvam, Montana Hoover et al.

We present CrossLoc3D, a novel 3D place recognition method that solves a large-scale point matching problem in a cross-source setting. Cross-source point cloud data corresponds to point sets captured by depth sensors with different accuracies or from different distances and perspectives. We address the challenges in terms of developing 3D place recognition methods that account for the representation gap between points captured by different sources. Our method handles cross-source data by utilizing multi-grained features and selecting convolution kernel sizes that correspond to most prominent features. Inspired by the diffusion models, our method uses a novel iterative refinement process that gradually shifts the embedding spaces from different sources to a single canonical space for better metric learning. In addition, we present CS-Campus3D, the first 3D aerial-ground cross-source dataset consisting of point cloud data from both aerial and ground LiDAR scans. The point clouds in CS-Campus3D have representation gaps and other features like different views, point densities, and noise patterns. We show that our CrossLoc3D algorithm can achieve an improvement of 4.74% - 15.37% in terms of the top 1 average recall on our CS-Campus3D benchmark and achieves performance comparable to state-of-the-art 3D place recognition method on the Oxford RobotCar. The code and CS-CAMPUS3D benchmark will be available at github.com/rayguan97/crossloc3d.

Xin Li, Jiachao Gong, Xijun Wang et al.

This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utilizes a new short-form UGC (S-UGC) video restoration benchmark, termed KwaiVIR, which is contributed by USTC and Kuaishou Technology. It contains both synthetically distorted videos and real-world short-form UGC videos in the wild. For this edition, the released data include 200 synthetic training videos, 48 wild training videos, 11 validation videos, and 20 testing videos. The primary goal of this challenge is to establish a strong and practical benchmark for restoring short-form UGC videos under complex real-world degradations, especially in the emerging paradigm of generative-model-based S-UGC video restoration. This challenge has two tracks: (i) the primary track is a subjective track, where the evaluation is based on a user study; (ii) the second track is an objective track. These two tracks enable a comprehensive assessment of restoration quality. In total, 95 teams have registered for this competition. And 12 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the KwaiVIR benchmark, demonstrating encouraging progress in short-form UGC video restoration in the wild.

Divya Kothandaraman, Tianrui Guan, Xijun Wang et al.

We present an algorithm, Fourier Activity Recognition (FAR), for UAV video activity recognition. Our formulation uses a novel Fourier object disentanglement method to innately separate out the human agent (which is typically small) from the background. Our disentanglement technique operates in the frequency domain to characterize the extent of temporal change of spatial pixels, and exploits convolution-multiplication properties of Fourier transform to map this representation to the corresponding object-background entangled features obtained from the network. To encapsulate contextual information and long-range space-time dependencies, we present a novel Fourier Attention algorithm, which emulates the benefits of self-attention by modeling the weighted outer product in the frequency domain. Our Fourier attention formulation uses much fewer computations than self-attention. We have evaluated our approach on multiple UAV datasets including UAV Human RGB, UAV Human Night, Drone Action, and NEC Drone. We demonstrate a relative improvement of 8.02% - 38.69% in top-1 accuracy and up to 3 times faster over prior works.

Yu Yuan, Jianhao Yuan, Xijun Wang et al.

Video generation models are becoming a scalable form of world models, but they mainly generate plausible motion rather than proactively control or optimize the underlying dynamics. As a result, an object in the generated video may follow trajectories that are unsafe, not smooth, inefficient, or physically inconsistent. In this work, we propose \textbf{OptiWorld}, a framework that brings classical optimal control into video generation at inference time. OptiWorld first extracts a compact, task-relevant world state, then plans an optimal trajectory under physical constraints, and finally renders the video conditioned on this trajectory. We formulate planning as a geometric problem on a continuous manifold, which converts 3D geometry and task-dependent physical constraints into a unified planning geometry. By adding this optimal-control layer, OptiWorld generates videos with preferable dynamics, demonstrating strong potential in multiple tasks including goal-conditioned image-to-video generation, video dynamics editing, and counterfactual generation.

Xijun Wang, Ruiqi Xian, Tianrui Guan et al.

We propose a novel approach for aerial video action recognition. Our method is designed for videos captured using UAVs and can run on edge or mobile devices. We present a learning-based approach that uses customized auto zoom to automatically identify the human target and scale it appropriately. This makes it easier to extract the key features and reduces the computational overhead. We also present an efficient temporal reasoning algorithm to capture the action information along the spatial and temporal domains within a controllable computational cost. Our approach has been implemented and evaluated both on the desktop with high-end GPUs and on the low power Robotics RB5 Platform for robots and drones. In practice, we achieve 6.1-7.4% improvement over SOTA in Top-1 accuracy on the RoCoG-v2 dataset, 8.3-10.4% improvement on the UAV-Human dataset and 3.2% improvement on the Drone Action dataset.

Ruiqi Xian, Xijun Wang, Dinesh Manocha

We present a novel approach for action recognition in UAV videos. Our formulation is designed to handle occlusion and viewpoint changes caused by the movement of a UAV. We use the concept of mutual information to compute and align the regions corresponding to human action or motion in the temporal domain. This enables our recognition model to learn from the key features associated with the motion. We also propose a novel frame sampling method that uses joint mutual information to acquire the most informative frame sequence in UAV videos. We have integrated our approach with X3D and evaluated the performance on multiple datasets. In practice, we achieve 18.9% improvement in Top-1 accuracy over current state-of-the-art methods on UAV-Human(Li et al., 2021), 7.3% improvement on Drone-Action(Perera et al., 2019), and 7.16% improvement on NEC Drones(Choi et al., 2020).

Ruiqi Xian, Xijun Wang, Divya Kothandaraman et al.

We present a new algorithm for selection of informative frames in video action recognition. Our approach is designed for aerial videos captured using a moving camera where human actors occupy a small spatial resolution of video frames. Our algorithm utilizes the motion bias within aerial videos, which enables the selection of motion-salient frames. We introduce the concept of patch mutual information (PMI) score to quantify the motion bias between adjacent frames, by measuring the similarity of patches. We use this score to assess the amount of discriminative motion information contained in one frame relative to another. We present an adaptive frame selection strategy using shifted leaky ReLu and cumulative distribution function, which ensures that the sampled frames comprehensively cover all the essential segments with high motion salience. Our approach can be integrated with any action recognition model to enhance its accuracy. In practice, our method achieves a relative improvement of 2.2 - 13.8% in top-1 accuracy on UAV-Human, 6.8% on NEC Drone, and 9.0% on Diving48 datasets.

Yuxuan Zhang, Chao Xu, Howard H. Yang et al.

This paper proposes a client selection (CS) method to tackle the communication bottleneck of federated learning (FL) while concurrently coping with FL's data heterogeneity issue. Specifically, we first analyze the effect of CS in FL and show that FL training can be accelerated by adequately choosing participants to diversify the training dataset in each round of training. Based on this, we leverage data profiling and determinantal point process (DPP) sampling techniques to develop an algorithm termed Federated Learning with DPP-based Participant Selection (FL-DP$^3$S). This algorithm effectively diversifies the participants' datasets in each round of training while preserving their data privacy. We conduct extensive experiments to examine the efficacy of our proposed method. The results show that our scheme attains a faster convergence rate, as well as a smaller communication overhead than several baselines.

Xiang Chen, Zhiheng Guo, Xijun Wang et al.

Future wireless communication networks are in a position to move beyond data-centric, device-oriented connectivity and offer intelligent, immersive experiences based on multi-agent collaboration, especially in the context of the thriving development of pre-trained foundation models (PFM) and the evolving vision of 6G native artificial intelligence (AI). Therefore, redefining modes of collaboration between devices and agents, and constructing native intelligence libraries become critically important in 6G. In this paper, we analyze the challenges of achieving 6G native AI from the perspectives of data, AI models, and operational paradigm. Then, we propose a 6G native AI framework based on foundation models, provide an integration method for the expert knowledge, present the customization for two kinds of PFM, and outline a novel operational paradigm for the native AI framework. As a practical use case, we apply this framework for orchestration, achieving the maximum sum rate within a cell-free massive MIMO system, and presenting preliminary evaluation results. Finally, we outline research directions for achieving native AI in 6G.

Xijun Wang, Dongshan Ye, Chenyuan Feng et al.

Image semantic communication (ISC) has garnered significant attention for its potential to achieve high efficiency in visual content transmission. However, existing ISC systems based on joint source-channel coding face challenges in interpretability, operability, and compatibility. To address these limitations, we propose a novel trustworthy ISC framework. This approach leverages text extraction and segmentation mapping techniques to convert images into explainable semantics, while employing Generative Artificial Intelligence (GenAI) for multiple downstream inference tasks. We also introduce a multi-rate ISC transmission protocol that dynamically adapts to both the received explainable semantic content and specific task requirements at the receiver. Simulation results demonstrate that our framework achieves explainable learning, decoupled training, and compatible transmission in various application scenarios. Finally, some intriguing research directions and application scenarios are identified.

Peihao Wang, Shan Yang, Xijun Wang et al.

Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability that modern language models increasingly require but do not natively encode. While prior work uses reinforcement learning or test-time training, planning remains external to the model architecture. We formulate reasoning as optimal control and introduce the Test-Time Control (TTC) layer, which performs finite-horizon LQR planning over latent states at inference time, represents a value function within neural architectures, and leverages it as the nested objective to enable planning before prediction. To ensure scalability, we derive a hardware-efficient LQR solver based on a symplectic formulation and implement it as a fused CUDA kernel, enabling parallel execution with minimal overhead. Integrated as an adapter into pretrained LLMs, TTC layers improve mathematical reasoning performance by up to +27.8% on MATH-500 and 2-3x Pass@8 improvements on AMC and AIME, demonstrating that embedding optimal control as an architectural component provides an effective and scalable mechanism for reasoning beyond test-time training.

Ruiqi Xian, Xiyang Wu, Tianrui Guan et al.

We introduce SOAR, a novel Self-supervised pretraining algorithm for aerial footage captured by Unmanned Aerial Vehicles (UAVs). We incorporate human object knowledge throughout the pretraining process to enhance UAV video pretraining efficiency and downstream action recognition performance. This is in contrast to prior works that primarily incorporate object information during the fine-tuning stage. Specifically, we first propose a novel object-aware masking strategy designed to retain the visibility of certain patches related to objects throughout the pretraining phase. Second, we introduce an object-aware loss function that utilizes object information to adjust the reconstruction loss, preventing bias towards less informative background patches. In practice, SOAR with a vanilla ViT backbone, outperforms best UAV action recognition models, recording a 9.7% and 21.4% boost in top-1 accuracy on the NEC-Drone and UAV-Human datasets, while delivering an inference speed of 18.7ms per video, making it 2x to 5x faster. Additionally, SOAR obtains comparable accuracy to prior self-supervised learning (SSL) methods while requiring 87.5% less pretraining time and 25% less memory usage

Decheng Liu, Xijun Wang, Chunlei Peng et al.

Adversarial attacks involve adding perturbations to the source image to cause misclassification by the target model, which demonstrates the potential of attacking face recognition models. Existing adversarial face image generation methods still can't achieve satisfactory performance because of low transferability and high detectability. In this paper, we propose a unified framework Adv-Diffusion that can generate imperceptible adversarial identity perturbations in the latent space but not the raw pixel space, which utilizes strong inpainting capabilities of the latent diffusion model to generate realistic adversarial images. Specifically, we propose the identity-sensitive conditioned diffusion generative model to generate semantic perturbations in the surroundings. The designed adaptive strength-based adversarial perturbation algorithm can ensure both attack transferability and stealthiness. Extensive qualitative and quantitative experiments on the public FFHQ and CelebA-HQ datasets prove the proposed method achieves superior performance compared with the state-of-the-art methods without an extra generative model training process. The source code is available at https://github.com/kopper-xdu/Adv-Diffusion.

Xijun Wang, Shuying Gan, Yanzhi Huang et al.

There is a surge of need for fresh information with the overwhelming proliferation of the Internet of Things (IoT) applications. To characterize the information freshness perceived by the destination, the age of information (AoI) has been proposed. In this paper, we consider an IoT system with multiple devices sending status update packets to a central controller through time-correlated Markov channels and assume that the instantaneous channel states are not available to the central controller before making scheduling decisions. To ensure information freshness, we investigate a timely scheduling problem that minimizes the total expected time-average AoI under a strict communications bandwidth constraint. We formulate this problem as a partially observable restless multi-armed bandit problem. Using Lagrangian relaxation, we decouple the relaxed problem into multiple sub-problems and prove the threshold structure of their optimal policies. Armed with this property, we establish the indexability for the decoupled problem and design an algorithm to compute the Whittle's index. To reduce implementation complexity, we further derive the Whittle-like index in closed-form for low-complexity scheduling. Simulation results show that the proposed index-based policies outperform the baselines, remain close to the optimal policy or relaxed lower bound, and are especially effective when scheduling resources are limited or the network size is large.

Xijun Wang, Xiaojie Chu, Chunrui Han et al.

This paper presents a module, Spatial Cross-scale Convolution (SCSC), which is verified to be effective in improving both CNNs and Transformers. Nowadays, CNNs and Transformers have been successful in a variety of tasks. Especially for Transformers, increasing works achieve state-of-the-art performance in the computer vision community. Therefore, researchers start to explore the mechanism of those architectures. Large receptive fields, sparse connections, weight sharing, and dynamic weight have been considered keys to designing effective base models. However, there are still some issues to be addressed: large dense kernels and self-attention are inefficient, and large receptive fields make it hard to capture local features. Inspired by the above analyses and to solve the mentioned problems, in this paper, we design a general module taking in these design keys to enhance both CNNs and Transformers. SCSC introduces an efficient spatial cross-scale encoder and spatial embed module to capture assorted features in one layer. On the face recognition task, FaceResNet with SCSC can improve 2.7% with 68% fewer FLOPs and 79% fewer parameters. On the ImageNet classification task, Swin Transformer with SCSC can achieve even better performance with 22% fewer FLOPs, and ResNet with CSCS can improve 5.3% with similar complexity. Furthermore, a traditional network (e.g., ResNet) embedded with SCSC can match Swin Transformer's performance.

Xin Li, Kun Yuan, Bingchen Li et al.

This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement. The challenge comprises two tracks: (i) Efficient Video Quality Assessment (KVQ), and (ii) Diffusion-based Image Super-Resolution (KwaiSR). Track 1 aims to advance the development of lightweight and efficient video quality assessment (VQA) models, with an emphasis on eliminating reliance on model ensembles, redundant weights, and other computationally expensive components in the previous IQA/VQA competitions. Track 2 introduces a new short-form UGC dataset tailored for single image super-resolution, i.e., the KwaiSR dataset. It consists of 1,800 synthetically generated S-UGC image pairs and 1,900 real-world S-UGC images, which are split into training, validation, and test sets using a ratio of 8:1:1. The primary objective of the challenge is to drive research that benefits the user experience of short-form UGC platforms such as Kwai and TikTok. This challenge attracted 266 participants and received 18 valid final submissions with corresponding fact sheets, significantly contributing to the progress of short-form UGC VQA and image superresolution. The project is publicly available at https://github.com/lixinustc/KVQE- ChallengeCVPR-NTIRE2025.

Xijun Wang, Junbang Liang, Chun-Kai Wang et al.

In this work, we propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unified way. In our ViLA network, we design a new learnable text-guided Frame-Prompter together with a new cross-modal distillation (QFormer-Distiller) module. Pre-trained large image-language models have shown promising results on problems such as visual question answering (VQA). However, how to efficiently and effectively sample video frames when adapting pre-trained large image-language model to video-language alignment is still the major challenge. Compared with prior work, our ViLA model demonstrates the capability of selecting key frames with critical contents, thus improving the video-language alignment accuracy while reducing the inference latency +3.3% on NExT-QA Temporal with 3.0X speed up). Overall, our ViLA network outperforms the state-of-the-art methods on the video question-answering benchmarks: +4.6% on STAR Interaction, +2.2% on STAR average with 3.0X speed up, ours 2-frames out-perform SeViLA 4-frames on the VLEP dataset with 4.2X speed-up. The code will be available at https://github.com/xijun-cs/ViLA.

Yu Yuan, Xijun Wang, Yichen Sheng et al.

Image generation today can produce somewhat realistic images from text prompts. However, if one asks the generator to synthesize a specific camera setting such as creating different fields of view using a 24mm lens versus a 70mm lens, the generator will not be able to interpret and generate scene-consistent images. This limitation not only hinders the adoption of generative tools in professional photography but also highlights the broader challenge of aligning data-driven models with real-world physical settings. In this paper, we introduce Generative Photography, a framework that allows controlling camera intrinsic settings during content generation. The core innovation of this work are the concepts of Dimensionality Lifting and Differential Camera Intrinsics Learning, enabling smooth and consistent transitions across different camera settings. Experimental results show that our method produces significantly more scene-consistent photorealistic images than state-of-the-art models such as Stable Diffusion 3 and FLUX. Our code and additional results are available at https://generative-photography.github.io/project.

Xijun Wang, Anqi Liang, Junbang Liang et al.

Scene-aware Complementary Item Retrieval (CIR) is a challenging task which requires to generate a set of compatible items across domains. Due to the subjectivity, it is difficult to set up a rigorous standard for both data collection and learning objectives. To address this challenging task, we propose a visual compatibility concept, composed of similarity (resembling in color, geometry, texture, and etc.) and complementarity (different items like table vs chair completing a group). Based on this notion, we propose a compatibility learning framework, a category-aware Flexible Bidirectional Transformer (FBT), for visual "scene-based set compatibility reasoning" with the cross-domain visual similarity input and auto-regressive complementary item generation. We introduce a "Flexible Bidirectional Transformer (FBT)" consisting of an encoder with flexible masking, a category prediction arm, and an auto-regressive visual embedding prediction arm. And the inputs for FBT are cross-domain visual similarity invariant embeddings, making this framework quite generalizable. Furthermore, our proposed FBT model learns the inter-object compatibility from a large set of scene images in a self-supervised way. Compared with the SOTA methods, this approach achieves up to 5.3% and 9.6% in FITB score and 22.3% and 31.8% SFID improvement on fashion and furniture, respectively.

Yiran Qin, Zhelun Shi, Jiwen Yu et al.

Recent advancements in predictive models have demonstrated exceptional capabilities in predicting the future state of objects and scenes. However, the lack of categorization based on inherent characteristics continues to hinder the progress of predictive model development. Additionally, existing benchmarks are unable to effectively evaluate higher-capability, highly embodied predictive models from an embodied perspective. In this work, we classify the functionalities of predictive models into a hierarchy and take the first step in evaluating World Simulators by proposing a dual evaluation framework called WorldSimBench. WorldSimBench includes Explicit Perceptual Evaluation and Implicit Manipulative Evaluation, encompassing human preference assessments from the visual perspective and action-level evaluations in embodied tasks, covering three representative embodied scenarios: Open-Ended Embodied Environment, Autonomous, Driving, and Robot Manipulation. In the Explicit Perceptual Evaluation, we introduce the HF-Embodied Dataset, a video assessment dataset based on fine-grained human feedback, which we use to train a Human Preference Evaluator that aligns with human perception and explicitly assesses the visual fidelity of World Simulators. In the Implicit Manipulative Evaluation, we assess the video-action consistency of World Simulators by evaluating whether the generated situation-aware video can be accurately translated into the correct control signals in dynamic environments. Our comprehensive evaluation offers key insights that can drive further innovation in video generation models, positioning World Simulators as a pivotal advancement toward embodied artificial intelligence.

Tianrui Guan, Ruiqi Xian, Xijun Wang et al.

We present AGL-NET, a novel learning-based method for global localization using LiDAR point clouds and satellite maps. AGL-NET tackles two critical challenges: bridging the representation gap between image and points modalities for robust feature matching, and handling inherent scale discrepancies between global view and local view. To address these challenges, AGL-NET leverages a unified network architecture with a novel two-stage matching design. The first stage extracts informative neural features directly from raw sensor data and performs initial feature matching. The second stage refines this matching process by extracting informative skeleton features and incorporating a novel scale alignment step to rectify scale variations between LiDAR and map data. Furthermore, a novel scale and skeleton loss function guides the network toward learning scale-invariant feature representations, eliminating the need for pre-processing satellite maps. This significantly improves real-world applicability in scenarios with unknown map scales. To facilitate rigorous performance evaluation, we introduce a meticulously designed dataset within the CARLA simulator specifically tailored for metric localization training and assessment. The code and data can be accessed at https://github.com/rayguan97/AGL-Net.

Yu Yuan, Tharindu Wickremasinghe, Zeeshan Nadir et al.

Images and videos are discrete 2D projections of the 4D world (3D space + time). Most visual understanding, prediction, and generation operate directly on 2D observations, leading to suboptimal performance. We propose SeeU, a novel approach that learns the continuous 4D dynamics and generate the unseen visual contents. The principle behind SeeU is a new 2D$\to$4D$\to$2D learning framework. SeeU first reconstructs the 4D world from sparse and monocular 2D frames (2D$\to$4D). It then learns the continuous 4D dynamics on a low-rank representation and physical constraints (discrete 4D$\to$continuous 4D). Finally, SeeU rolls the world forward in time, re-projects it back to 2D at sampled times and viewpoints, and generates unseen regions based on spatial-temporal context awareness (4D$\to$2D). By modeling dynamics in 4D, SeeU achieves continuous and physically-consistent novel visual generation, demonstrating strong potentials in multiple tasks including unseen temporal generation, unseen spatial generation, and video editing.

Joonyeoup Kim, Yu Yuan, Xingguang Zhang et al.

Photography is the cornerstone of modern astronomical and space research. However, most astronomical images captured by ground-based telescopes suffer from atmospheric turbulence, resulting in degraded imaging quality. While multi-frame strategies like lucky imaging can mitigate some effects, they involve intensive data acquisition and complex manual processing. In this paper, we propose AstroDiff, a generative restoration method that leverages both the high-quality generative priors and restoration capabilities of diffusion models to mitigate atmospheric turbulence. Extensive experiments demonstrate that AstroDiff outperforms existing state-of-the-art learning-based methods in astronomical image turbulence mitigation, providing higher perceptual quality and better structural fidelity under severe turbulence conditions. Our code and additional results are available at https://web-six-kappa-66.vercel.app/

Xijun Wang, Zhaoyang Liu, Chenyuan Feng et al.

As 6G evolves, the radio access network must transcend traditional automation to embrace agentic AI capable of perception, reasoning, and evolution. A fundamental cognitive gap persists in current disaggregated architectures, where interfaces force the physical layer to compress high-dimensional states into low-dimensional metrics, trapping reasoning agents behind a semantic bottleneck. This article envisions a shift from interface-bound to memory-centric architectures. We propose a unified memory paradigm that dissolves the boundaries between sensing and reasoning by mapping biological memory hierarchies onto heterogeneous computing fabrics. Enabled by emerging coherent interconnects, this approach creates a cognitive continuum where microsecond-level reflexes, millisecond-level reasoning, and long-term evolution share state across time scales. By replacing message passing with zero-copy observability, we empower AI agents to bridge the gap between real-time responsiveness and long-horizon context for truly autonomous 6G networks.

Xiyang Wu, Tianrui Guan, Dianqi Li et al.

Large vision-language models (LVLMs) are prone to hallucinations, where certain contextual cues in an image can trigger the language module to produce overconfident and incorrect reasoning about abnormal or hypothetical objects. While some benchmarks have been developed to investigate LVLM hallucinations, they often rely on hand-crafted corner cases whose failure patterns may not generalize well. Additionally, fine-tuning on these examples could undermine their validity. To address this, we aim to scale up the number of cases through an automated approach, reducing human bias in crafting such corner cases. This motivates the development of AutoHallusion, the first automated benchmark generation approach that employs several key strategies to create a diverse range of hallucination examples. Our generated visual-question pairs pose significant challenges to LVLMs, requiring them to overcome contextual biases and distractions to arrive at correct answers. AutoHallusion enables us to create new benchmarks at the minimum cost and thus overcomes the fragility of hand-crafted benchmarks. It also reveals common failure patterns and reasons, providing key insights to detect, avoid, or control hallucinations. Comprehensive evaluations of top-tier LVLMs, e.g., GPT-4V(ision), Gemini Pro Vision, Claude 3, and LLaVA-1.5, show a 97.7% and 98.7% success rate of hallucination induction on synthetic and real-world datasets of AutoHallusion, paving the way for a long battle against hallucinations. The codebase and data can be accessed at https://github.com/wuxiyang1996/AutoHallusion.

Zhiheng Guo, Zhaoyang Liu, Zihan Cen et al.

The deployment of large-scale neural networks within the Open Radio Access Network (O-RAN) architecture is pivotal for enabling native edge intelligence. However, this paradigm faces two critical bottlenecks: the prohibitive memory footprint required for local training on resource-constrained gNBs, and the saturation of bandwidth-limited backhaul links during the global aggregation of high-dimensional model updates. To address these challenges, we propose CoCo-Fed, a novel Compression and Combination-based Federated learning framework that unifies local memory efficiency and global communication reduction. Locally, CoCo-Fed breaks the memory wall by performing a double-dimension down-projection of gradients, adapting the optimizer to operate on low-rank structures without introducing additional inference parameters/latency. Globally, we introduce a transmission protocol based on orthogonal subspace superposition, where layer-wise updates are projected and superimposed into a single consolidated matrix per gNB, drastically reducing the backhaul traffic. Beyond empirical designs, we establish a rigorous theoretical foundation, proving the convergence of CoCo-Fed even under unsupervised learning conditions suitable for wireless sensing tasks. Extensive simulations on an angle-of-arrival estimation task demonstrate that CoCo-Fed significantly outperforms state-of-the-art baselines in both memory and communication efficiency while maintaining robust convergence under non-IID settings.

Peng Kang, Xijun Wang, Yu Yuan

Recent text-to-video models have demonstrated strong temporal generation capabilities, yet their potential for image restoration remains underexplored. In this work, we repurpose CogVideo for progressive visual restoration tasks by fine-tuning it to generate restoration trajectories rather than natural video motion. Specifically, we construct synthetic datasets for super-resolution, deblurring, and low-light enhancement, where each sample depicts a gradual transition from degraded to clean frames. Two prompting strategies are compared: a uniform text prompt shared across all samples, and a scene-specific prompting scheme generated via LLaVA multi-modal LLM and refined with ChatGPT. Our fine-tuned model learns to associate temporal progression with restoration quality, producing sequences that improve perceptual metrics such as PSNR, SSIM, and LPIPS across frames. Extensive experiments show that CogVideo effectively restores spatial detail and illumination consistency while maintaining temporal coherence. Moreover, the model generalizes to real-world scenarios on the ReLoBlur dataset without additional training, demonstrating strong zero-shot robustness and interpretability through temporal restoration.

Xin Li, Xijun Wang, Bingchen Li et al.

In this work, we build the first benchmark dataset for short-form UGC Image Super-resolution in the wild, termed KwaiSR, intending to advance the research on developing image super-resolution algorithms for short-form UGC platforms. This dataset is collected from the Kwai Platform, which is composed of two parts, i.e., synthetic and wild parts. Among them, the synthetic dataset, including 1,900 image pairs, is produced by simulating the degradation following the distribution of real-world low-quality short-form UGC images, aiming to provide the ground truth for training and objective comparison in the validation/testing. The wild dataset contains low-quality images collected directly from the Kwai Platform, which are filtered using the quality assessment method KVQ from the Kwai Platform. As a result, the KwaiSR dataset contains 1800 synthetic image pairs and 1900 wild images, which are divided into training, validation, and testing parts with a ratio of 8:1:1. Based on the KwaiSR dataset, we organize the NTIRE 2025 challenge on a second short-form UGC Video quality assessment and enhancement, which attracts lots of researchers to develop the algorithm for it. The results of this competition have revealed that our KwaiSR dataset is pretty challenging for existing Image SR methods, which is expected to lead to a new direction in the image super-resolution field. The dataset can be found from https://lixinustc.github.io/NTIRE2025-KVQE-KwaSR-KVQ.github.io/.

Adnan Shahid, Adrian Kliks, Ahmed Al-Tahmeesschi et al.

This white paper discusses the role of large-scale AI in the telecommunications industry, with a specific focus on the potential of generative AI to revolutionize network functions and user experiences, especially in the context of 6G systems. It highlights the development and deployment of Large Telecom Models (LTMs), which are tailored AI models designed to address the complex challenges faced by modern telecom networks. The paper covers a wide range of topics, from the architecture and deployment strategies of LTMs to their applications in network management, resource allocation, and optimization. It also explores the regulatory, ethical, and standardization considerations for LTMs, offering insights into their future integration into telecom infrastructure. The goal is to provide a comprehensive roadmap for the adoption of LTMs to enhance scalability, performance, and user-centric innovation in telecom networks.

Xijun Wang, Prateek Chennuri, Yu Yuan et al.

While smartphone cameras today can produce astonishingly good photos, their performance in low light is still not completely satisfactory because of the fundamental limits in photon shot noise and sensor read noise. Generative image restoration methods have demonstrated promising results compared to traditional methods, but they suffer from hallucinatory content generation when the signal-to-noise ratio (SNR) is low. Recognizing the availability of personalized photo galleries on users' smartphones, we propose Personalized Generative Denoising (PGD) by building a diffusion model customized for different users. Our core innovation is an identity-consistent physical buffer that extracts the physical attributes of the person from the gallery. This ID-consistent physical buffer provides a strong prior that can be integrated with the diffusion model to restore the degraded images, without the need of fine-tuning. Over a wide range of low-light testing scenarios, we show that PGD achieves superior image denoising and enhancement performance compared to existing diffusion-based denoising approaches.

Xijun Wang, Santiago López-Tapia, Aggelos K. Katsaggelos

Atmospheric turbulence, a common phenomenon in daily life, is primarily caused by the uneven heating of the Earth's surface. This phenomenon results in distorted and blurred acquired images or videos and can significantly impact downstream vision tasks, particularly those that rely on capturing clear, stable images or videos from outdoor environments, such as accurately detecting or recognizing objects. Therefore, people have proposed ways to simulate atmospheric turbulence and designed effective deep learning-based methods to remove the atmospheric turbulence effect. However, these synthesized turbulent images can not cover all the range of real-world turbulence effects. Though the models have achieved great performance for synthetic scenarios, there always exists a performance drop when applied to real-world cases. Moreover, reducing real-world turbulence is a more challenging task as there are no clean ground truth counterparts provided to the models during training. In this paper, we propose a real-world atmospheric turbulence mitigation model under a domain adaptation framework, which links the supervised simulated atmospheric turbulence correction with the unsupervised real-world atmospheric turbulence correction. We will show our proposed method enhances performance in real-world atmospheric turbulence scenarios, improving both image quality and downstream vision tasks.

Zihao Peng, Xijun Wang, Shengbo Chen et al.

Diffusion models are powerful generative models that can produce highly realistic samples for various tasks. Typically, these models are constructed using centralized, independently and identically distributed (IID) training data. However, in practical scenarios, data is often distributed across multiple clients and frequently manifests non-IID characteristics. Federated Learning (FL) can leverage this distributed data to train diffusion models, but the performance of existing FL methods is unsatisfactory in non-IID scenarios. To address this, we propose FedDDPM-Federated Learning with Denoising Diffusion Probabilistic Models, which leverages the data generative capability of diffusion models to facilitate model training. In particular, the server uses well-trained local diffusion models uploaded by each client before FL training to generate auxiliary data that can approximately represent the global data distribution. Following each round of model aggregation, the server further optimizes the global model using the auxiliary dataset to alleviate the impact of heterogeneous data on model performance. We provide a rigorous convergence analysis of FedDDPM and propose an enhanced algorithm, FedDDPM+, to reduce training overheads. FedDDPM+ detects instances of slow model learning and performs a one-shot correction using the auxiliary dataset. Experimental results validate that our proposed algorithms outperform the state-of-the-art FL algorithms on the MNIST, CIFAR10 and CIFAR100 datasets.

Xingguang Zhang, Nicholas Chimitt, Xijun Wang et al.

Atmospheric turbulence is a major source of image degradation in long-range imaging systems. Although numerous deep learning-based turbulence mitigation (TM) methods have been proposed, many are slow, memory-hungry, and do not generalize well. In the spatial domain, methods based on convolutional operators have a limited receptive field, so they cannot handle a large spatial dependency required by turbulence. In the temporal domain, methods relying on self-attention can, in theory, leverage the lucky effects of turbulence, but their quadratic complexity makes it difficult to scale to many frames. Traditional recurrent aggregation methods face parallelization challenges. In this paper, we present a new TM method based on two concepts: (1) A turbulence mitigation network based on the Selective State Space Model (MambaTM). MambaTM provides a global receptive field in each layer across spatial and temporal dimensions while maintaining linear computational complexity. (2) Learned Latent Phase Distortion (LPD). LPD guides the state space model. Unlike classical Zernike-based representations of phase distortion, the new LPD map uniquely captures the actual effects of turbulence, significantly improving the model's capability to estimate degradation by reducing the ill-posedness. Our proposed method exceeds current state-of-the-art networks on various synthetic and real-world TM benchmarks with significantly faster inference speed.

Pedro Sandoval-Segura, Xijun Wang, Ashwinee Panda et al.

Attention is foundational to large language models (LLMs), enabling different heads to have diverse focus on relevant input tokens. However, learned behaviors like attention sinks, where the first token receives the most attention despite limited semantic importance, suggest some heads may be inactive, and point to a significant source of computational redundancy. To analyze this phenomenon, we propose a taxonomy of 13 score functions that measure different ways a head can be inactive. Thresholding these scores allows us to analyze different sets of potentially inactive attention heads. We evaluate whether identified heads are inactive through model interventions, finding that more than 12% of attention heads are inactive on average, and can be ablated in specific contexts while maintaining MMLU accuracy to within 1% of the pretrained LLM. Across 3 model families, our score functions that measure the average norm of a head's output consistently identify inactive heads that would not have been found by score functions that rely solely on attention weights. We establish that relying on a score function that measures a first token attention sink would underestimate the prevalence of inactive heads, failing to identify more than 7% of inactive heads on average. We also show how measuring score distributions can provide insights into attention behavior. For instance, we find evidence that finetuning causes little to no change in attention behavior, and that even within the same model family, large model scales present markedly different attention behaviors.

Kun Guo, Yun Shen, Xijun Wang et al.

Fast and accurate video object recognition, which relies on frame-by-frame video analytics, remains a challenge for resource-constrained devices such as traffic cameras. Recent advances in mobile edge computing have made it possible to offload computation-intensive object detection to edge servers equipped with high-accuracy neural networks, while lightweight and fast object tracking algorithms run locally on devices. This hybrid approach offers a promising solution but introduces a new challenge: deciding when to perform edge detection versus local tracking. To address this, we formulate two long-term optimization problems for both single-device and multi-device scenarios, taking into account the temporal correlation of consecutive frames and the dynamic conditions of mobile edge networks. Based on the formulation, we propose the LTED-Ada in single-device setting, a deep reinforcement learning-based algorithm that adaptively selects between local tracking and edge detection, according to the frame rate as well as recognition accuracy and delay requirement. In multi-device setting, we further enhance LTED-Ada using federated learning to enable collaborative policy training across devices, thereby improving its generalization to unseen frame rates and performance requirements. Finally, we conduct extensive hardware-in-the-loop experiments using multiple Raspberry Pi 4B devices and a personal computer as the edge server, demonstrating the superiority of LTED-Ada.

Kun Guo, Xuefei Li, Xijun Wang et al.

Federated learning (FL) and split learning (SL) are two effective distributed learning paradigms in wireless networks, enabling collaborative model training across mobile devices without sharing raw data. While FL supports low-latency parallel training, it may converge to less accurate model. In contrast, SL achieves higher accuracy through sequential training but suffers from increased delay. To leverage the advantages of both, hybrid split and federated learning (HSFL) allows some devices to operate in FL mode and others in SL mode. This paper aims to accelerate HSFL by addressing three key questions: 1) How does learning mode selection affect overall learning performance? 2) How does it interact with batch size? 3) How can these hyperparameters be jointly optimized alongside communication and computational resources to reduce overall learning delay? We first analyze convergence, revealing the interplay between learning mode and batch size. Next, we formulate a delay minimization problem and propose a two-stage solution: a block coordinate descent method for a relaxed problem to obtain a locally optimal solution, followed by a rounding algorithm to recover integer batch sizes with near-optimal performance. Experimental results demonstrate that our approach significantly accelerates convergence to the target accuracy compared to existing methods.

Xijun Wang, Tanay Sharma, Achin Kulshrestha et al.

As AR/VR technologies become integral to daily life, there's a growing need for AI that understands human social dynamics from an egocentric perspective. However, current LLMs often lack the social awareness to discern when to intervene as AI assistant. This leads to constant, socially unaware responses that may disrupt natural conversation and negatively impact user focus. To address these limitations, we introduce EgoSocial, a large-scale egocentric dataset with 13,500 social video-question pairs, specifically designed to benchmark intervention in social interaction perception. We also present an in-depth analysis of current omnimodal LLMs (OLLMs) to assess their effectiveness in detecting diverse social contextual cues. Experiments show that OLLMs still struggle to detect the intervention timing (14.4% for Gemini 2.5 Pro). We also propose EgoSoD (EgoSocial Detection), an end-to-end method for robustly discerning social dynamics. Informed by our OLLM analysis, EgoSoD integrates multimodal contextual cues (e.g., audio and visual cues) into a social thinking graph, dynamically modeling participants and interactions. Our method proactively detects intervention timing and social interactions, precisely determining when to intervene. Our EgoSoD improves Phi-4 by 45.6% and Gemini 2.5 Pro by 9.9% on Intervention Timing performance, and improves Phi-4 by 20.4% and Gemini 2.5 Pro by 6.9% on overall Social Interaction performance. We will release the dataset and code soon.

Yu Yuan, Xijun Wang, Tharindu Wickremasinghe et al.

A primary bottleneck in large-scale text-to-video generation today is physical consistency and controllability. Despite recent advances, state-of-the-art models often produce unrealistic motions, such as objects falling upward, or abrupt changes in velocity and direction. Moreover, these models lack precise parameter control, struggling to generate physically consistent dynamics under different initial conditions. We argue that this fundamental limitation stems from current models learning motion distributions solely from appearance, while lacking an understanding of the underlying dynamics. In this work, we propose NewtonGen, a framework that integrates data-driven synthesis with learnable physical principles. At its core lies trainable Neural Newtonian Dynamics (NND), which can model and predict a variety of Newtonian motions, thereby injecting latent dynamical constraints into the video generation process. By jointly leveraging data priors and dynamical guidance, NewtonGen enables physically consistent video synthesis with precise parameter control.

Xijun Wang, Junyun Huang, Rayyan Abdalla et al.

We address the critical gap between the computational demands of vision-language models and the possible ultra-low-bit weight precision (bitwidth $\leq2$ bits) we can use for higher efficiency. Our work is motivated by the substantial computational cost and memory requirements of VLMs, which restrict their applicability in hardware-constrained environments. We propose Bi-VLM, which separates model weights non-uniformly based on the Gaussian quantiles. Our formulation groups the model weights into outlier (salient) and multiple inlier (unsalient) subsets, ensuring that each subset contains a proportion of weights corresponding to its quantile in the distribution. We propose a saliency-aware hybrid quantization algorithm and use it to quantize weights by imposing different constraints on the scaler and binary matrices based on the saliency metric and compression objective. We have evaluated our approach on different VLMs. For the language model part of the VLM, our Bi-VLM outperforms the SOTA by 3%-47% on the visual question answering task in terms of four different benchmarks and three different models. For the overall VLM, our Bi-VLM outperforms the SOTA by 4%-45%. We also perform token pruning on the quantized models and observe that there is redundancy of image tokens 90% - 99% in the quantized models. This helps us to further prune the visual tokens to improve efficiency.

Xijun Wang, Xin Li, Bingchen Li et al.

Diffusion models have significantly advanced video super-resolution (VSR) by enhancing perceptual quality, largely through elaborately designed temporal modeling to ensure inter-frame consistency. However, existing methods usually suffer from limited temporal coherence and prohibitively high computational costs (e.g., typically requiring over 8 NVIDIA A100-80G GPUs), especially for long videos. In this work, we propose LiftVSR, an efficient VSR framework that leverages and elevates the image-wise diffusion prior from PixArt-$α$, achieving state-of-the-art results using only 4$\times$RTX 4090 GPUs. To balance long-term consistency and efficiency, we introduce a hybrid temporal modeling mechanism that decomposes temporal learning into two complementary components: (i) Dynamic Temporal Attention (DTA) for fine-grained temporal modeling within short frame segment ($\textit{i.e.}$, low complexity), and (ii) Attention Memory Cache (AMC) for long-term temporal modeling across segments ($\textit{i.e.}$, consistency). Specifically, DTA identifies multiple token flows across frames within multi-head query and key tokens to warp inter-frame contexts in the value tokens. AMC adaptively aggregates historical segment information via a cache unit, ensuring long-term coherence with minimal overhead. To further stabilize the cache interaction during inference, we introduce an asymmetric sampling strategy that mitigates feature mismatches arising from different diffusion sampling steps. Extensive experiments on several typical VSR benchmarks have demonstrated that LiftVSR achieves impressive performance with significantly lower computational costs.

Xiang Chen, Shuying Gan, Chenyuan Feng et al.

The growing demand for efficient semantic communication systems capable of managing diverse tasks and adapting to fluctuating channel conditions has driven the development of robust, resource-efficient frameworks. This article introduces a novel channel-adaptive and multi-task-aware semantic communication framework based on a masked auto-encoder architecture. Our framework optimizes the transmission of meaningful information by incorporating a multi-task-aware scoring mechanism that identifies and prioritizes semantically significant data across multiple concurrent tasks. A channel-aware extractor is employed to dynamically select relevant information in response to real-time channel conditions. By jointly optimizing semantic relevance and transmission efficiency, the framework ensures minimal performance degradation under resource constraints. Experimental results demonstrate the superior performance of our framework compared to conventional methods in tasks such as image reconstruction and object detection. These results underscore the framework's adaptability to heterogeneous channel environments and its scalability for multi-task applications, positioning it as a promising solution for next-generation semantic communication networks.

Xijun Wang, Pedro Sandoval-Segura, Chengyuan Zhang et al.

Most existing traffic video datasets including Waymo are structured, focusing predominantly on Western traffic, which hinders global applicability. Specifically, most Asian scenarios are far more complex, involving numerous objects with distinct motions and behaviors. Addressing this gap, we present a new dataset, DAVE, designed for evaluating perception methods with high representation of Vulnerable Road Users (VRUs: e.g. pedestrians, animals, motorbikes, and bicycles) in complex and unpredictable environments. DAVE is a manually annotated dataset encompassing 16 diverse actor categories (spanning animals, humans, vehicles, etc.) and 16 action types (complex and rare cases like cut-ins, zigzag movement, U-turn, etc.), which require high reasoning ability. DAVE densely annotates over 13 million bounding boxes (bboxes) actors with identification, and more than 1.6 million boxes are annotated with both actor identification and action/behavior details. The videos within DAVE are collected based on a broad spectrum of factors, such as weather conditions, the time of day, road scenarios, and traffic density. DAVE can benchmark video tasks like Tracking, Detection, Spatiotemporal Action Localization, Language-Visual Moment retrieval, and Multi-label Video Action Recognition. Given the critical importance of accurately identifying VRUs to prevent accidents and ensure road safety, in DAVE, vulnerable road users constitute 41.13% of instances, compared to 23.71% in Waymo. DAVE provides an invaluable resource for the development of more sensitive and accurate visual perception algorithms in the complex real world. Our experiments show that existing methods suffer degradation in performance when evaluated on DAVE, highlighting its benefit for future video recognition research.

Xijun Wang, Santiago López-Tapia, Alice Lucas et al.

Generative Adversarial Networks (GANs) have shown great performance on super-resolution problems since they can generate more visually realistic images and video frames. However, these models often introduce side effects into the outputs, such as unexpected artifacts and noises. To reduce these artifacts and enhance the perceptual quality of the results, in this paper, we propose a general method that can be effectively used in most GAN-based super-resolution (SR) models by introducing essential spatial information into the training process. We extract spatial information from the input data and incorporate it into the training loss, making the corresponding loss a spatially adaptive (SA) one. After that, we utilize it to guide the training process. We will show that the proposed approach is independent of the methods used to extract the spatial information and independent of the SR tasks and models. This method consistently guides the training process towards generating visually pleasing SR images and video frames, substantially mitigating artifacts and noise, ultimately leading to enhanced perceptual quality.

Xijun Wang, Dongyang Liu, Meina Kan et al.

In Knowledge Distillation, the teacher is generally much larger than the student, making the solution of the teacher likely to be difficult for the student to learn. To ease the mimicking difficulty, we introduce a triplet knowledge distillation mechanism named TriKD. Besides teacher and student, TriKD employs a third role called anchor model. Before distillation begins, the pre-trained anchor model delimits a subspace within the full solution space of the target problem. Solutions within the subspace are expected to be easy targets that the student could mimic well. Distillation then begins in an online manner, and the teacher is only allowed to express solutions within the aforementioned subspace. Surprisingly, benefiting from accurate but easy-to-mimic hints, the student can finally perform well. After the student is well trained, it can be used as the new anchor for new students, forming a curriculum learning strategy. Our experiments on image classification and face recognition with various models clearly demonstrate the effectiveness of our method. Furthermore, the proposed TriKD is also effective in dealing with the overfitting issue. Moreover, our theoretical analysis supports the rationality of our triplet distillation.

Xijun Wang, Ruiqi Xian, Tianrui Guan et al.

We present a new learning approach, Soft Conditional Prompt Learning (SCP), which leverages the strengths of prompt learning for aerial video action recognition. Our approach is designed to predict the action of each agent by helping the models focus on the descriptions or instructions associated with actions in the input videos for aerial/robot visual perception. Our formulation supports various prompts, including learnable prompts, auxiliary visual information, and large vision models to improve the recognition performance. We present a soft conditional prompt method that learns to dynamically generate prompts from a pool of prompt experts under different video inputs. By sharing the same objective with the task, our proposed SCP can optimize prompts that guide the model's predictions while explicitly learning input-invariant (prompt experts pool) and input-specific (data-dependent) prompt knowledge. In practice, we observe a 3.17-10.2% accuracy improvement on the aerial video datasets (Okutama, NECDrone), which consist of scenes with single-agent and multi-agent actions. We further evaluate our approach on ground camera videos to verify the effectiveness and generalization and achieve a 1.0-3.6% improvement on dataset SSV2. We integrate our method into the ROS2 as well.

Xijun Wang, Santiago López-Tapia, Aggelos K. Katsaggelos

Atmospheric Turbulence (AT) correction is a challenging restoration task as it consists of two distortions: geometric distortion and spatially variant blur. Diffusion models have shown impressive accomplishments in photo-realistic image synthesis and beyond. In this paper, we propose a novel deep conditional diffusion model under a variational inference framework to solve the AT correction problem. We use this framework to improve performance by learning latent prior information from the input and degradation processes. We use the learned information to further condition the diffusion model. Experiments are conducted in a comprehensive synthetic AT dataset. We show that the proposed framework achieves good quantitative and qualitative results.

Xijun Wang, Aggelos K. Katsaggelos

Weakly-supervised temporal action localization aims to identify and localize the action instances in the untrimmed videos with only video-level action labels. When humans watch videos, we can adapt our abstract-level knowledge about actions in different video scenarios and detect whether some actions are occurring. In this paper, we mimic how humans do and bring a new perspective for locating and identifying multiple actions in a video. We propose a network named VQK-Net with a video-specific query-key attention modeling that learns a unique query for each action category of each input video. The learned queries not only contain the actions' knowledge features at the abstract level but also have the ability to fit this knowledge into the target video scenario, and they will be used to detect the presence of the corresponding action along the temporal dimension. To better learn these action category queries, we exploit not only the features of the current input video but also the correlation between different videos through a novel video-specific action category query learner worked with a query similarity loss. Finally, we conduct extensive experiments on three commonly used datasets (THUMOS14, ActivityNet1.2, and ActivityNet1.3) and achieve state-of-the-art performance.

Rohan Chandra, Xijun Wang, Mridul Mahajan et al.

We present a new traffic dataset, METEOR, which captures traffic patterns and multi-agent driving behaviors in unstructured scenarios. METEOR consists of more than 1000 one-minute videos, over 2 million annotated frames with bounding boxes and GPS trajectories for 16 unique agent categories, and more than 13 million bounding boxes for traffic agents. METEOR is a dataset for rare and interesting, multi-agent driving behaviors that are grouped into traffic violations, atypical interactions, and diverse scenarios. Every video in METEOR is tagged using a diverse range of factors corresponding to weather, time of the day, road conditions, and traffic density. We use METEOR to benchmark perception methods for object detection and multi-agent behavior prediction. Our key finding is that state-of-the-art models for object detection and behavior prediction, which otherwise succeed on existing datasets such as Waymo, fail on the METEOR dataset. METEOR marks the first step towards the development of more sophisticated perception models for dense, heterogeneous, and unstructured scenarios.

Chao Xu, Yiping Xie, Xijun Wang et al.

Recently, we have struck the balance between the information freshness, in terms of age of information (AoI), experienced by users and energy consumed by sensors, by appropriately activating sensors to update their current status in caching enabled Internet of Things (IoT) networks [1]. To solve this problem, we cast the corresponding status update procedure as a continuing Markov Decision Process (MDP) (i.e., without termination states), where the number of state-action pairs increases exponentially with respect to the number of considered sensors and users. Moreover, to circumvent the curse of dimensionality, we have established a methodology for designing deep reinforcement learning (DRL) algorithms to maximize (resp. minimize) the average reward (resp. cost), by integrating R-learning, a tabular reinforcement learning (RL) algorithm tailored for maximizing the long-term average reward, and traditional DRL algorithms, initially developed to optimize the discounted long-term cumulative reward rather than the average one. In this technical report, we would present detailed discussions on the technical contributions of this methodology.