Active-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO

Active vision, also known as active perception, refers to the process of actively selecting where and how to look in order to gather task-relevant information. It is a critical component of efficient perception and decision-making in humans and advanced embodied agents. Recently, the use of Multimodal Large Language Models (MLLMs) as central planning and decision-making modules in robotic systems has gained extensive attention. However, despite the importance of active perception in embodied intelligence, there is little to no exploration of how MLLMs can be equipped with or learn active perception capabilities. In this paper, we first provide a systematic definition of MLLM-based active perception tasks. We point out that the recently proposed GPT-o3 model's zoom-in search strategy can be regarded as a special case of active perception; however, it still suffers from low search efficiency and inaccurate region selection. To address these issues, we propose ACTIVE-O3, a purely reinforcement learning based training framework built on top of GRPO, designed to equip MLLMs with active perception capabilities. We further establish a comprehensive benchmark suite to evaluate ACTIVE-O3 across both general open-world tasks, such as small-object and dense object grounding, and domain-specific scenarios, including small object detection in remote sensing and autonomous driving, as well as fine-grained interactive segmentation. In addition, ACTIVE-O3 also demonstrates strong zero-shot reasoning abilities on the V* Benchmark, without relying on any explicit reasoning data. We hope that our work can provide a simple codebase and evaluation protocol to facilitate future research on active perception in MLLMs.

Automated Text-to-Table for Reasoning-Intensive Table QA: Pipeline Design and Benchmarking Insights

Reasoning with tabular data holds increasing importance in modern applications, yet comprehensive evaluation methodologies for reasoning-intensive Table Question Answering (QA) tasks remain nascent. Existing research is constrained by two primary bottlenecks: 1) Reliance on costly manually annotated real-world data, which is difficult to cover complex reasoning scenarios; 2) The heterogeneity of table structures hinders systematic analysis of the intrinsic mechanisms behind the underperformance of LLMs, especially in reasoning-intensive tasks. To address these issues, we propose an automated generation pipeline AutoT2T that transforms mathematical word problems into table-based reasoning tasks, eliminating the need for manual annotation. The pipeline can generate multiple variants of a table for the same reasoning problem, including noisy versions to support robustness evaluation. Based on this, we construct a new benchmark TabularGSM, which systematically spans a range of table complexities and trap problems. Experimental analyses through AutoT2T and TabularGSM reveal that the tight coupling between reasoning and retrieval or identification processes is a key factor underlying the failure of LLMs in complex Table QA tasks. This highlights the necessity for models to develop synergistic reasoning capabilities in order to perform effectively in complex Table QA tasks.

Weather-Magician: Reconstruction and Rendering Framework for 4D Weather Synthesis In Real Time

For tasks such as urban digital twins, VR/AR/game scene design, or creating synthetic films, the traditional industrial approach often involves manually modeling scenes and using various rendering engines to complete the rendering process. This approach typically requires high labor costs and hardware demands, and can result in poor quality when replicating complex real-world scenes. A more efficient approach is to use data from captured real-world scenes, then apply reconstruction and rendering algorithms to quickly recreate the authentic scene. However, current algorithms are unable to effectively reconstruct and render real-world weather effects. To address this, we propose a framework based on gaussian splatting, that can reconstruct real scenes and render them under synthesized 4D weather effects. Our work can simulate various common weather effects by applying Gaussians modeling and rendering techniques. It supports continuous dynamic weather changes and can easily control the details of the effects. Additionally, our work has low hardware requirements and achieves real-time rendering performance. The result demos can be accessed on our project homepage: weathermagician.github.io

GMatch: Geometry-Constrained Feature Matching for RGB-D Object Pose Estimation

We present GMatch, a learning-free feature matcher designed for robust 6DoF object pose estimation, addressing common local ambiguities in sparse feature matching. Unlike traditional methods that rely solely on descriptor similarity, GMatch performs a guided, incremental search, enforcing SE(3)-invariant geometric consistency throughout the matching process. It leverages a provably complete set of geometric features that uniquely determine 3D keypoint configurations, ensuring globally consistent correspondences without the need for training or GPU support. When combined with classical descriptors such as SIFT, GMatch-SIFT forms a general-purpose pose estimation pipeline that offers strong interpretability and generalization across diverse objects and scenes. Experiments on the HOPE dataset show that GMatch outperforms both traditional and learning-based matchers, with GMatch-SIFT achieving or surpassing the performance of instance-level pose networks. On the YCB-Video dataset, GMatch-SIFT demonstrates high accuracy and low variance on texture-rich objects. These results not only validate the effectiveness of GMatch-SIFT for object pose estimation but also highlight the broader applicability of GMatch as a general-purpose feature matcher. Code will be released upon acceptance.

FedSaaS: Class-Consistency Federated Semantic Segmentation via Global Prototype Supervision and Local Adversarial Harmonization

Federated semantic segmentation enables pixel-level classification in images through collaborative learning while maintaining data privacy. However, existing research commonly overlooks the fine-grained class relationships within the semantic space when addressing heterogeneous problems, particularly domain shift. This oversight results in ambiguities between class representation. To overcome this challenge, we propose a novel federated segmentation framework that strikes class consistency, termed FedSaaS. Specifically, we introduce class exemplars as a criterion for both local- and global-level class representations. On the server side, the uploaded class exemplars are leveraged to model class prototypes, which supervise global branch of clients, ensuring alignment with global-level representation. On the client side, we incorporate an adversarial mechanism to harmonize contributions of global and local branches, leading to consistent output. Moreover, multilevel contrastive losses are employed on both sides to enforce consistency between two-level representations in the same semantic space. Extensive experiments on several driving scene segmentation datasets demonstrate that our framework outperforms state-of-the-art methods, significantly improving average segmentation accuracy and effectively addressing the class-consistency representation problem.

JAEGER: Dual-Level Humanoid Whole-Body Controller

This paper presents JAEGER, a dual-level whole-body controller for humanoid robots that addresses the challenges of training a more robust and versatile policy. Unlike traditional single-controller approaches, JAEGER separates the control of the upper and lower bodies into two independent controllers, so that they can better focus on their distinct tasks. This separation alleviates the dimensionality curse and improves fault tolerance. JAEGER supports both root velocity tracking (coarse-grained control) and local joint angle tracking (fine-grained control), enabling versatile and stable movements. To train the controller, we utilize a human motion dataset (AMASS), retargeting human poses to humanoid poses through an efficient retargeting network, and employ a curriculum learning approach. This method performs supervised learning for initialization, followed by reinforcement learning for further exploration. We conduct our experiments on two humanoid platforms and demonstrate the superiority of our approach against state-of-the-art methods in both simulation and real environments.

From Mapping to Composing: A Two-Stage Framework for Zero-shot Composed Image Retrieval

Composed Image Retrieval (CIR) is a challenging multimodal task that retrieves a target image based on a reference image and accompanying modification text. Due to the high cost of annotating CIR triplet datasets, zero-shot (ZS) CIR has gained traction as a promising alternative. Existing studies mainly focus on projection-based methods, which map an image to a single pseudo-word token. However, these methods face three critical challenges: (1) insufficient pseudo-word token representation capacity, (2) discrepancies between training and inference phases, and (3) reliance on large-scale synthetic data. To address these issues, we propose a two-stage framework where the training is accomplished from mapping to composing. In the first stage, we enhance image-to-pseudo-word token learning by introducing a visual semantic injection module and a soft text alignment objective, enabling the token to capture richer and fine-grained image information. In the second stage, we optimize the text encoder using a small amount of synthetic triplet data, enabling it to effectively extract compositional semantics by combining pseudo-word tokens with modification text for accurate target image retrieval. The strong visual-to-pseudo mapping established in the first stage provides a solid foundation for the second stage, making our approach compatible with both high- and low-quality synthetic data, and capable of achieving significant performance gains with only a small amount of synthetic data. Extensive experiments were conducted on three public datasets, achieving superior performance compared to existing approaches.

Single-loop Algorithms for Stochastic Non-convex Optimization with Weakly-Convex Constraints

Constrained optimization with multiple functional inequality constraints has significant applications in machine learning. This paper examines a crucial subset of such problems where both the objective and constraint functions are weakly convex. Existing methods often face limitations, including slow convergence rates or reliance on double-loop algorithmic designs. To overcome these challenges, we introduce a novel single-loop penalty-based stochastic algorithm. Following the classical exact penalty method, our approach employs a {\bf hinge-based penalty}, which permits the use of a constant penalty parameter, enabling us to achieve a {\bf state-of-the-art complexity} for finding an approximate Karush-Kuhn-Tucker (KKT) solution. We further extend our algorithm to address finite-sum coupled compositional objectives, which are prevalent in artificial intelligence applications, establishing improved complexity over existing approaches. Finally, we validate our method through experiments on fair learning with receiver operating characteristic (ROC) fairness constraints and continual learning with non-forgetting constraints.

Knowledge Rectification for Camouflaged Object Detection: Unlocking Insights from Low-Quality Data

Low-quality data often suffer from insufficient image details, introducing an extra implicit aspect of camouflage that complicates camouflaged object detection (COD). Existing COD methods focus primarily on high-quality data, overlooking the challenges posed by low-quality data, which leads to significant performance degradation. Therefore, we propose KRNet, the first framework explicitly designed for COD on low-quality data. KRNet presents a Leader-Follower framework where the Leader extracts dual gold-standard distributions: conditional and hybrid, from high-quality data to drive the Follower in rectifying knowledge learned from low-quality data. The framework further benefits from a cross-consistency strategy that improves the rectification of these distributions and a time-dependent conditional encoder that enriches the distribution diversity. Extensive experiments on benchmark datasets demonstrate that KRNet outperforms state-of-the-art COD methods and super-resolution-assisted COD approaches, proving its effectiveness in tackling the challenges of low-quality data in COD.

Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Survey

Learning-based 3D reconstruction has emerged as a transformative technique in autonomous driving, enabling precise modeling of both dynamic and static environments through advanced neural representations. Despite augmenting perception, 3D reconstruction inspires pioneering solution for vital tasks in the field of autonomous driving, such as scene understanding and closed-loop simulation. Commencing with an examination of input modalities, we investigates the details of 3D reconstruction and conducts a multi-perspective, in-depth analysis of recent advancements. Specifically, we first provide a systematic introduction of preliminaries, including data formats, benchmarks and technical preliminaries of learning-based 3D reconstruction, facilitating instant identification of suitable methods based on hardware configurations and sensor suites. Then, we systematically review learning-based 3D reconstruction methods in autonomous driving, categorizing approaches by subtasks and conducting multi-dimensional analysis and summary to establish a comprehensive technical reference. The development trends and existing challenges is summarized in the context of learning-based 3D reconstruction in autonomous driving. We hope that our review will inspire future researches.