Yanzi Wang

GLM-V Team, Wenyi Hong, Wenmeng Yu et al.

We present GLM-4.1V-Thinking and GLM-4.5V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. We then propose Reinforcement Learning with Curriculum Sampling (RLCS) to unlock the full potential of the model, leading to comprehensive capability enhancement across a diverse range of tasks, including STEM problem solving, video understanding, content recognition, coding, grounding, GUI-based agents, and long document interpretation. In a comprehensive evaluation across 42 public benchmarks, GLM-4.5V achieves state-of-the-art performance on nearly all tasks among open-source models of similar size, and demonstrates competitive or even superior results compared to closed-source models such as Gemini-2.5-Flash on challenging tasks including Coding and GUI Agents. Meanwhile, the smaller GLM-4.1V-9B-Thinking remains highly competitive-achieving superior results to the much larger Qwen2.5-VL-72B on 29 benchmarks. We open-source both GLM-4.1V-9B-Thinking and GLM-4.5V. Code, models and more information are released at https://github.com/zai-org/GLM-V.

Xiaoqi Li, Yanzi Wang, Yan Shen et al.

In the realm of future home-assistant robots, 3D articulated object manipulation is essential for enabling robots to interact with their environment. Many existing studies make use of 3D point clouds as the primary input for manipulation policies. However, this approach encounters challenges due to data sparsity and the significant cost associated with acquiring point cloud data, which can limit its practicality. In contrast, RGB images offer high-resolution observations using cost effective devices but lack spatial 3D geometric information. To overcome these limitations, we present a novel image-based robotic manipulation framework. This framework is designed to capture multiple perspectives of the target object and infer depth information to complement its geometry. Initially, the system employs an eye-on-hand RGB camera to capture an overall view of the target object. It predicts the initial depth map and a coarse affordance map. The affordance map indicates actionable areas on the object and serves as a constraint for selecting subsequent viewpoints. Based on the global visual prior, we adaptively identify the optimal next viewpoint for a detailed observation of the potential manipulation success area. We leverage geometric consistency to fuse the views, resulting in a refined depth map and a more precise affordance map for robot manipulation decisions. By comparing with prior works that adopt point clouds or RGB images as inputs, we demonstrate the effectiveness and practicality of our method. In the project webpage (https://sites.google.com/view/imagemanip), real world experiments further highlight the potential of our method for practical deployment.

Yaohua Zha, Yanzi Wang, Tao Dai et al.

The pre-trained point cloud model based on Masked Point Modeling (MPM) has exhibited substantial improvements across various tasks. However, two drawbacks hinder their practical application. Firstly, the positional embedding of masked patches in the decoder results in the leakage of their central coordinates, leading to limited 3D representations. Secondly, the excessive model size of existing MPM methods results in higher demands for devices. To address these, we propose to pre-train Point cloud Compact Model with Partial-aware \textbf{R}econstruction, named Point-CPR. Specifically, in the decoder, we couple the vanilla masked tokens with their positional embeddings as randomly masked queries and introduce a partial-aware prediction module before each decoder layer to predict them from the unmasked partial. It prevents the decoder from creating a shortcut between the central coordinates of masked patches and their reconstructed coordinates, enhancing the robustness of models. We also devise a compact encoder composed of local aggregation and MLPs, reducing the parameters and computational requirements compared to existing Transformer-based encoders. Extensive experiments demonstrate that our model exhibits strong performance across various tasks, especially surpassing the leading MPM-based model PointGPT-B with only 2% of its parameters.

Yaohua Zha, Yanzi Wang, Hang Guo et al.

Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightforward, utilizing only the final output of the pre-trained model for various task heads. It neglects the rich complementary information in the intermediate layer, thereby failing to fully unlock the potential of pre-trained models. To overcome this limitation, we propose an orthogonal solution: Point Mamba Adapter (PMA), which constructs an ordered feature sequence from all layers of the pre-trained model and leverages Mamba to fuse all complementary semantics, thereby promoting comprehensive point cloud understanding. Constructing this ordered sequence is non-trivial due to the inherent isotropy of 3D space. Therefore, we further propose a geometry-constrained gate prompt generator (G2PG) shared across different layers, which applies shared geometric constraints to the output gates of the Mamba and dynamically optimizes the spatial order, thus enabling more effective integration of multi-layer information. Extensive experiments conducted on challenging point cloud datasets across various tasks demonstrate that our PMA elevates the capability for point cloud understanding to a new level by fusing diverse complementary intermediate features. Code is available at https://github.com/zyh16143998882/PMA.

V Team, Wenyi Hong, Xiaotao Gu et al.

We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in real environments, agentic capability depends not only on language reasoning, but also on the ability to perceive, interpret, and act over heterogeneous contexts such as images, videos, webpages, documents, GUIs. GLM-5V-Turbo is built around this objective: multimodal perception is integrated as a core component of reasoning, planning, tool use, and execution, rather than as an auxiliary interface to a language model. This report summarizes the main improvements behind GLM-5V-Turbo across model design, multimodal training, reinforcement learning, toolchain expansion, and integration with agent frameworks. These developments lead to strong performance in multimodal coding, visual tool use, and framework-based agentic tasks, while preserving competitive text-only coding capability. More importantly, our development process offers practical insights for building multimodal agents, highlighting the central role of multimodal perception, hierarchical optimization, and reliable end-to-end verification.

Runqi Qiao, Qiuna Tan, Peiqing Yang et al.

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various tasks, but still struggle with complex mathematical reasoning. Existing research primarily focuses on dataset construction and method optimization, often overlooking two critical aspects: comprehensive knowledge-driven design and model-centric data space modeling. In this paper, we introduce We-Math 2.0, a unified system that integrates a structured mathematical knowledge system, model-centric data space modeling, and a reinforcement learning (RL)-based training paradigm to comprehensively enhance the mathematical reasoning abilities of MLLMs. The key contributions of We-Math 2.0 are fourfold: (1) MathBook Knowledge System: We construct a five-level hierarchical system encompassing 491 knowledge points and 1,819 fundamental principles. (2) MathBook-Standard & Pro: We develop MathBook-Standard, a dataset that ensures broad conceptual coverage and flexibility through dual expansion. Additionally, we define a three-dimensional difficulty space and generate 7 progressive variants per problem to build MathBook-Pro, a challenging dataset for robust training. (3) MathBook-RL: We propose a two-stage RL framework comprising: (i) Cold-Start Fine-tuning, which aligns the model with knowledge-oriented chain-of-thought reasoning; and (ii) Progressive Alignment RL, leveraging average-reward learning and dynamic data scheduling to achieve progressive alignment across difficulty levels. (4) MathBookEval: We introduce a comprehensive benchmark covering all 491 knowledge points with diverse reasoning step distributions. Experimental results show that MathBook-RL performs competitively with existing baselines on four widely-used benchmarks and achieves strong results on MathBookEval, suggesting promising generalization in mathematical reasoning.

Yaohua Zha, Tao Dai, Hang Guo et al.

Point clouds, as a primary representation of 3D data, can be categorized into scene domain point clouds and object domain point clouds. Point cloud self-supervised learning (SSL) has become a mainstream paradigm for learning 3D representations. However, existing point cloud SSL primarily focuses on learning domain-specific 3D representations within a single domain, neglecting the complementary nature of cross-domain knowledge, which limits the learning of 3D representations. In this paper, we propose to learn a comprehensive Point cloud Mixture-of-Domain-Experts model (Point-MoDE) via a block-to-scene pre-training strategy. Specifically, we first propose a mixture-of-domain-expert model consisting of scene domain experts and multiple shared object domain experts. Furthermore, we propose a block-to-scene pretraining strategy, which leverages the features of point blocks in the object domain to regress their initial positions in the scene domain through object-level block mask reconstruction and scene-level block position regression. By integrating the complementary knowledge between object and scene, this strategy simultaneously facilitates the learning of both object-domain and scene-domain representations, leading to a more comprehensive 3D representation. Extensive experiments in downstream tasks demonstrate the superiority of our model.