ERNIE 5.0 Technical Report

In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio. All modalities are trained from scratch under a unified next-group-of-tokens prediction objective, based on an ultra-sparse mixture-of-experts (MoE) architecture with modality-agnostic expert routing. To address practical challenges in large-scale deployment under diverse resource constraints, ERNIE 5.0 adopts a novel elastic training paradigm. Within a single pre-training run, the model learns a family of sub-models with varying depths, expert capacities, and routing sparsity, enabling flexible trade-offs among performance, model size, and inference latency in memory- or time-constrained scenarios. Moreover, we systematically address the challenges of scaling reinforcement learning to unified foundation models, thereby guaranteeing efficient and stable post-training under ultra-sparse MoE architectures and diverse multimodal settings. Extensive experiments demonstrate that ERNIE 5.0 achieves strong and balanced performance across multiple modalities. To the best of our knowledge, among publicly disclosed models, ERNIE 5.0 represents the first production-scale realization of a trillion-parameter unified autoregressive model that supports both multimodal understanding and generation. To facilitate further research, we present detailed visualizations of modality-agnostic expert routing in the unified model, alongside comprehensive empirical analysis of elastic training, aiming to offer profound insights to the community.

Geometry without Position? When Positional Embeddings Help and Hurt Spatial Reasoning

This paper revisits the role of positional embeddings (PEs) within vision transformers (ViTs) from a geometric perspective. We show that PEs are not mere token indices but effectively function as geometric priors that shape the spatial structure of the representation. We introduce token-level diagnostics that measure how multi-view geometric consistency in ViT representation depends on consitent PEs. Through extensive experiments on 14 foundation ViT models, we reveal how PEs influence multi-view geometry and spatial reasoning. Our findings clarify the role of PEs as a causal mechanism that governs spatial structure in ViT representations. Our code is provided in https://github.com/shijianjian/vit-geometry-probes

Feasibility Study Regarding Self-sustainable Reconfigurable Intelligent Surfaces

Without requiring operational costs such as cabling and powering while maintaining reconfigurable phase-shift capability, self-sustainable reconfigurable intelligent surfaces (ssRISs) can be deployed in locations inaccessible to conventional relays or base stations, offering a novel approach to enhance wireless coverage. This study assesses the feasibility of ssRIS deployment by analyzing two harvest-and-reflect (HaR) schemes: element-splitting (ES) and time-splitting (TS). We examine how element requirements scale with key system parameters, transmit power, data rate demands, and outage constraints under both line-of-sight (LOS) and non-line-of-sight (NLOS) ssRIS-to-user equipment (UE) channels. Analytical and numerical results reveal distinct feasibility characteristics. The TS scheme demonstrates better channel hardening gain, maintaining stable element requirements across varying outage margins, making it advantageous for indoor deployments with favorable harvesting conditions and moderate data rates. However, TS exhibits an element requirement that exponentially scales to harvesting difficulty and data rate. Conversely, the ES scheme shows only linear growth with harvesting difficulty, providing better feasibility under challenging outdoor scenarios. These findings establish that TS excels in benign environments, prioritizing reliability, while ES is preferable for demanding conditions requiring operational robustness.

SpatiaLoc: Leveraging Multi-Level Spatial Enhanced Descriptors for Cross-Modal Localization

Cross-modal localization using text and point clouds enables robots to localize themselves via natural language descriptions, with applications in autonomous navigation and interaction between humans and robots. In this task, objects often recur across text and point clouds, making spatial relationships the most discriminative cues for localization. Given this characteristic, we present SpatiaLoc, a framework utilizing a coarse-to-fine strategy that emphasizes spatial relationships at both the instance and global levels. In the coarse stage, we introduce a Bezier Enhanced Object Spatial Encoder (BEOSE) that models spatial relationships at the instance level using quadratic Bezier curves. Additionally, a Frequency Aware Encoder (FAE) generates spatial representations in the frequency domain at the global level. In the fine stage, an Uncertainty Aware Gaussian Fine Localizer (UGFL) regresses 2D positions by modeling predictions as Gaussian distributions with a loss function aware of uncertainty. Extensive experiments on KITTI360Pose demonstrate that SpatiaLoc significantly outperforms existing state-of-the-art (SOTA) methods.

$A^2$GC: $A$symmetric $A$ggregation with Geometric Constraints for Locally Aggregated Descriptors

Visual Place Recognition (VPR) aims to match query images against a database using visual cues. State-of-the-art methods aggregate features from deep backbones to form global descriptors. Optimal transport-based aggregation methods reformulate feature-to-cluster assignment as a transport problem, but the standard Sinkhorn algorithm symmetrically treats source and target marginals, limiting effectiveness when image features and cluster centers exhibit substantially different distributions. We propose an asymmetric aggregation VPR method with geometric constraints for locally aggregated descriptors, called $A^2$GC-VPR. Our method employs row-column normalization averaging with separate marginal calibration, enabling asymmetric matching that adapts to distributional discrepancies in visual place recognition. Geometric constraints are incorporated through learnable coordinate embeddings, computing compatibility scores fused with feature similarities, thereby promoting spatially proximal features to the same cluster and enhancing spatial awareness. Experimental results on MSLS, NordLand, and Pittsburgh datasets demonstrate superior performance, validating the effectiveness of our approach in improving matching accuracy and robustness.

Depth Anything 3: Recovering the Visual Space from Any Views

We present Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from an arbitrary number of visual inputs, with or without known camera poses. In pursuit of minimal modeling, DA3 yields two key insights: a single plain transformer (e.g., vanilla DINO encoder) is sufficient as a backbone without architectural specialization, and a singular depth-ray prediction target obviates the need for complex multi-task learning. Through our teacher-student training paradigm, the model achieves a level of detail and generalization on par with Depth Anything 2 (DA2). We establish a new visual geometry benchmark covering camera pose estimation, any-view geometry and visual rendering. On this benchmark, DA3 sets a new state-of-the-art across all tasks, surpassing prior SOTA VGGT by an average of 44.3% in camera pose accuracy and 25.1% in geometric accuracy. Moreover, it outperforms DA2 in monocular depth estimation. All models are trained exclusively on public academic datasets.

MyGO: Make your Goals Obvious, Avoiding Semantic Confusion in Prostate Cancer Lesion Region Segmentation

Early diagnosis and accurate identification of lesion location and progression in prostate cancer (PCa) are critical for assisting clinicians in formulating effective treatment strategies. However, due to the high semantic homogeneity between lesion and non-lesion areas, existing medical image segmentation methods often struggle to accurately comprehend lesion semantics, resulting in the problem of semantic confusion. To address this challenge, we propose a novel Pixel Anchor Module, which guides the model to discover a sparse set of feature anchors that serve to capture and interpret global contextual information. This mechanism enhances the model's nonlinear representation capacity and improves segmentation accuracy within lesion regions. Moreover, we design a self-attention-based Top_k selection strategy to further refine the identification of these feature anchors, and incorporate a focal loss function to mitigate class imbalance, thereby facilitating more precise semantic interpretation across diverse regions. Our method achieves state-of-the-art performance on the PI-CAI dataset, demonstrating 69.73% IoU and 74.32% Dice scores, and significantly improving prostate cancer lesion detection.

Kwai Keye-VL Technical Report

While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form videos, a dominant medium in today's digital landscape. To bridge this gap, we introduce \textbf{Kwai Keye-VL}, an 8-billion-parameter multimodal foundation model engineered for leading-edge performance in short-video understanding while maintaining robust general-purpose vision-language abilities. The development of Keye-VL rests on two core pillars: a massive, high-quality dataset exceeding 600 billion tokens with a strong emphasis on video, and an innovative training recipe. This recipe features a four-stage pre-training process for solid vision-language alignment, followed by a meticulous two-phase post-training process. The first post-training stage enhances foundational capabilities like instruction following, while the second phase focuses on stimulating advanced reasoning. In this second phase, a key innovation is our five-mode ``cold-start'' data mixture, which includes ``thinking'', ``non-thinking'', ``auto-think'', ``think with image'', and high-quality video data. This mixture teaches the model to decide when and how to reason. Subsequent reinforcement learning (RL) and alignment steps further enhance these reasoning capabilities and correct abnormal model behaviors, such as repetitive outputs. To validate our approach, we conduct extensive evaluations, showing that Keye-VL achieves state-of-the-art results on public video benchmarks and remains highly competitive on general image-based tasks (Figure 1). Furthermore, we develop and release the \textbf{KC-MMBench}, a new benchmark tailored for real-world short-video scenarios, where Keye-VL shows a significant advantage.

RIS-Assisted Survivable Fronthaul Design in Cell-Free Massive MIMO System

This paper investigates the application of reconfigurable intelligent surfaces (RISs) to improve fronthaul link survivability in cell-free massive MIMO (CF mMIMO) systems. To enhance the fronthaul survivability, two complementary mechanisms are considered. Firstly, RIS is set to provide reliable line-of-sight (LOS) connectivity and enhance the mmWave backup link. Secondly, a resource-sharing scheme that leverages redundant cable capacity through neighboring master access points (APs) to guarantee availability is considered. We formulate the redundant capacity minimization problem as a RIS-assisted multi-user MIMO rate control optimization problem, developing a novel solution that combines a modified weighted minimum mean square error (WMMSE) algorithm for precoding design with Riemannian gradient descent for RIS phase shift optimization. Our numerical evaluations show that RIS reduces the required redundant capacity by 65.6% compared to the no RIS case to reach a 99% survivability. The results show that the most substantial gains of RIS occur during complete outages of the direct disconnected master AP-CPU channel. These results demonstrate RIS's potential to significantly enhance fronthaul reliability while minimizing infrastructure costs in next-generation wireless networks.

Place Recognition: A Comprehensive Review, Current Challenges and Future Directions

Place recognition is a cornerstone of vehicle navigation and mapping, which is pivotal in enabling systems to determine whether a location has been previously visited. This capability is critical for tasks such as loop closure in Simultaneous Localization and Mapping (SLAM) and long-term navigation under varying environmental conditions. In this survey, we comprehensively review recent advancements in place recognition, emphasizing three representative methodological paradigms: Convolutional Neural Network (CNN)-based approaches, Transformer-based frameworks, and cross-modal strategies. We begin by elucidating the significance of place recognition within the broader context of autonomous systems. Subsequently, we trace the evolution of CNN-based methods, highlighting their contributions to robust visual descriptor learning and scalability in large-scale environments. We then examine the emerging class of Transformer-based models, which leverage self-attention mechanisms to capture global dependencies and offer improved generalization across diverse scenes. Furthermore, we discuss cross-modal approaches that integrate heterogeneous data sources such as Lidar, vision, and text description, thereby enhancing resilience to viewpoint, illumination, and seasonal variations. We also summarize standard datasets and evaluation metrics widely adopted in the literature. Finally, we identify current research challenges and outline prospective directions, including domain adaptation, real-time performance, and lifelong learning, to inspire future advancements in this domain. The unified framework of leading-edge place recognition methods, i.e., code library, and the results of their experimental evaluations are available at https://github.com/CV4RA/SOTA-Place-Recognitioner.