C W

Yunchao Yao, Zhuxiu Xu, Tianqi Zhang et al.

Building general-purpose dexterous manipulation policies requires benchmarks that go beyond isolated tasks to systematically evaluate policies across diverse interaction modes, sensory conditions, and robot embodiments. However, existing benchmarks remain limited in task and data diversity, embodiment coverage, or controllable visual variation, hindering studies of cross-task and cross-embodiment generalization. We present DexVerse, a large-scale and modular benchmark for dexterous manipulation. DexVerse includes 100 tasks spanning a broad range of manipulation skills, including object grasping and relocation, articulated-object interaction, functional tool use, bimanual coordination, non-prehensile control, contact-rich behaviors, multi-goal execution, and long-horizon multi-stage task completion. It supports 3 robot arms and 6 dexterous hands, and is extensible to new tasks, assets, and embodiments. To evaluate visuomotor generalization, DexVerse provides configurable visual variations in textures, background, lighting, and camera viewpoints. We further provide a VR-based teleoperation interface and 3,180 demonstrations with synchronized proprioceptive, RGB, depth, point-cloud, and state observations. We benchmark representative methods, including Diffusion Policy, DP3, OpenVLA, and $π_{0.5}$, across 19 tasks. Results reveal substantial challenges in task generalization and visuomotor robustness, establishing DexVerse as a promising testbed for general-purpose dexterous manipulation. Project page: https://ycyao216.github.io/DexVerse.site

Gengluo Li, Xingyu Wan, Shangpin Peng et al.

We present HunyuanOCR-1.5, a lightweight end-to-end OCR-specialized vision-language model. HunyuanOCR unifies document parsing, text spotting, information extraction, text-image translation, and multi-image document understanding within a single end-to-end VLM. Building upon the lightweight architecture of HunyuanOCR-1.0, HunyuanOCR-1.5 does not redesign the backbone, but systematically improves both efficiency and capability. For efficiency, we adapt DFlash to OCR decoding, significantly reducing the latency of long structured outputs such as dense documents, tables, and formulas while preserving output distribution. Powered by DFlash, HunyuanOCR-1.5 achieves a 6.37x Transformer inference speedup and a 2.14x speedup under vLLM, delivering the fastest inference among lightweight OCR VLMs. For capability, we propose Agentic Data Flow, an agent-driven data construction system that transforms model weaknesses into executable data requirements and autonomously performs material search, quality verification, and pipeline development. It substantially improves long-tail capabilities in ancient-script OCR, fine-grained chart and table parsing, multi-image text-centric QA, low-resource multilingual parsing, and document hallucination evaluation. HunyuanOCR-1.5 ranks among the top-tier end-to-end OCR solutions on OmniDocBench v1.6 while achieving new performance milestones across these long-tail tasks. Combined with an upgraded pretraining and post-training recipe, HunyuanOCR-1.5 further extends its capability in high-resolution, long-context, and multi-task scenarios. Experiments demonstrate faster inference, broader OCR capability coverage, and the deployment advantages of a lightweight end-to-end model. We will release the model weights and training code to support future research and real-world OCR applications.

He Liang, Chenyang Ma, Yiming Zhang et al.

Existing 3D scene-grounded Large Language Models (3D-LLMs) focus on answering questions grounded in simplified single-room 3D scenes, lacking the ability to reason over real-world household environments containing multiple interconnected rooms and diverse object categories. We introduce CAIRN, a topology-aware 3D-LLM for multi-room 3D scene understanding. CAIRN aligns transformer attention with scene hierarchy, giving the model explicit awareness of object-level relations and room-level connectivity. It enriches object tokens with room-local relational context via a graph neural network, introduces learned room tokens for room-level abstraction, and applies a hierarchical attention mask with geometric bias to route information according to scene topology. CAIRN is developed on CAIRN-MR, a benchmark we introduce on HM3D for multi-room 3D scene understanding, covering grounding, captioning, and four question-answering tasks that progressively evaluate from intra-room perception to cross-room reasoning. Experiments show that CAIRN outperforms prior 3D-LLMs by a large margin across all CAIRN-MR tasks while remaining competitive on five single-room benchmarks.

Xue-Jian Gao, Deng Pan, Yueming Su et al.

AI agents are now capable of writing, compiling, and iteratively optimizing low-level operator kernels on different hardware platforms. Existing benchmarks, however, focus almost exclusively on CUDA and Triton, leaving hardware ecosystems with less-exposed programming models without a common evaluation baseline. We present CANN Bench, an open benchmark for AI-generated operator code on Huawei's Ascend NPU. The current release covers 53 operators and 1060 test cases organized into four difficulty tiers -- from simple elementwise primitives to MoE dispatch and FlashAttention kernels -- spanning FP16, BF16, FP32, and INT8 precision formats. Evaluation adopts a \textbf{three-dimensional weighted composite score} that treats compilation, functional correctness, and performance as independent axes, providing a principled reward signal for kernel-generation agents. Performance is graded against an out-of-the-box PyTorch-on-Ascend baseline and an analytical per-case Hardware-Anchored Performance (HAP) limit on real NPU hardware, ensuring scores reflect genuine optimization headroom rather than measurement artifacts. The evaluation harness is designed to resist reward hacking from the ground up. CANN Bench is versioned within the official CANN repository and is designed for long-term community co-construction, providing the Ascend ecosystem with a quantitative, reproducible, and sustainably maintained yardstick for AI operator-authoring capability.

Jian Zhu, Jianjun Zhang, Taiyi Su et al.

World Action Models (WAMs) provide a promising alternative to Vision-Language-Action (VLA) policies by using video-based world modeling as dense supervision for robot action learning. Existing WAMs excel at physically grounded execution, but typically lack the explicit language-level planning interface in VLM-based VLAs for decomposing coarse instructions. Such decomposition becomes important when household tasks involve complex multi-step goals, where coarse user commands need to be converted into sequences of fine-grained executable subtasks. Meanwhile, the field still lacks a fair real-robot comparison between VLA and WAM execution capabilities, since existing systems often differ in data, robot embodiments, and task protocols. To address both the decomposition gap and the need for a controlled WAM-VLA comparison, we introduce DSWAM, a Dual-System World Action Foundation Model for fine-grained robot manipulation. DSWAM keeps a System 1 WAM executor as the default control path and optionally activates a System 2 vision-language subtask planner only when task decomposition is useful. The planner predicts executable subtasks from short-term visual history and a global task prompt, while the WAM executor performs world-aware action generation for each instruction or subtask. The executor is trained with action prediction and video co-training, but inference directly predicts action chunks without explicit future video generation. To make this execution path practical on real robots, we further integrate TensorRT acceleration, asynchronous execution, and real-time chunking (RTC) so that policy queries do not block robot control. To provide a fair real-robot comparison with VLA policies, we build and evaluate DSWAM under the DeMaVLA real-world deformable manipulation setting with matched robot platform, pretraining data, post-training data, and evaluation criteria.

Jianjun Zhang, Jian Zhu, Taiyi Su et al.

World Action Models (WAMs) have shown strong potential for robotic manipulation by jointly modeling visual future dynamics and executable action sequences. However, existing video-action co-training methods primarily optimize appearance-oriented video latents, which may insufficiently capture the temporally evolving geometry required for precise manipulation. We propose MECo-WAM, a Multi-Expert Co-Training World Action Model that injects action-relevant 4D geometric priors into video-action representations while preserving the original lightweight inference graph. During training, MECo-WAM combines video and action experts with a lightweight 4D expert supervised by relational targets from a frozen VGGT encoder. Asymmetric expert visibility prevents non-causal shortcuts from auxiliary geometry to action generation. To transfer geometric knowledge into the deployed video-action pathway, we introduce decayed 4D read-mask attention, which provides restricted current-frame geometric guidance early in training and progressively removes this dependency. We further propose action-aware temporal geometric distillation, which aligns within-frame geometric relations and their temporal evolution while emphasizing visual regions most relevant to robot actions. At deployment, all auxiliary 4D components are removed. Experiments on LIBERO (98.2%), RoboTwin 2.0 (92.6%), and challenging real-world manipulation tasks show that MECo-WAM improves manipulation performance without increasing inference cost.

Pin Tang, Zhongdao Wang, Guoqing Wang et al.

Vision-based 3D semantic occupancy prediction is essential for autonomous driving, yet dense voxel representations waste computation on largely empty space, while BEV and TPV projections compromise fine-grained 3D structure. Fully sparse representations offer an attractive alternative, but existing methods, including SparseOcc, entangle scene completion with semantic prediction by indiscriminately propagating high-dimensional features into empty regions and applying voxel-wise classification. This creates excessive activations, computational overhead, and geometric ambiguity. We present SparseOcc++, a geometry-aware sparse framework that explicitly decouples scene completion from semantic segmentation. SparseOcc++ reformulates completion as signed-distance regression on sparse anchor voxels through a scene completion field (SCF). To model complex outdoor geometry robustly, it combines orthogonal decomposition with discretized distance learning. A geometry-guided propagation module then converts the SCF into a complete volumetric scene and restricts semantic segmentation to geometrically verified regions. Experiments establish new state of the art: SparseOcc++ improves IoU by 2.3 points and is 3.9x faster than SparseOcc on nuScenes, while achieving a 5.9x speedup over OccFormer on SemanticKITTI.

Sofia Gilardini, Chenfei Ma, Kianoush Nazarpour

Decoding hand kinematics from surface electromyography (EMG) is a core challenge in wearable biosignal processing with clinical relevance for prosthetic control and motor rehabilitation. Most representation learning approaches for EMG focus on discrete gesture classification, and few focus on continuous regression. We present KinEMbed, a cross-modal contrastive learning framework for hand kinematics regression that jointly trains dual encoders -- one for windowed EMG features and one for kinematic (joint angle) targets. The resulting embeddings inherit the geometric structure of the kinematic space without requiring kinematic signals at inference time. Evaluating on the NinaPro DB8 dataset that includes both able-bodied users and subjects with limb difference (N=11), KinEMbed outperforms PCA, PLS, autoencoder and contrastive (CEBRA) baselines on held-out sessions, with largest gains on the most challenging thumb degrees of articulation. We position this work as a first step toward contrastive representation learning for regression of hand kinematics from structured wearable biosignals.

Pin Tang, Guoqing Wang, Xiangxuan Ren et al.

Vision-Language-Action Models (VLAs), which leverage the advanced reasoning capabilities of Vision-Language Models (VLMs), show promising generalization in complex autonomous driving scenarios. Existing VLAs typically predict and optimize 3D trajectories from 2D images. While intuitive, this 2D-to-3D prediction is inherently entangled with camera parameters, leading to limited data scalability across heterogeneous driving datasets. Moreover, directly optimizing in 3D space induces severe convergence to trivial solutions, where VLAs rely on ego-status rather than visual scene understanding. To address these issues, we propose PixelPilot, a novel VLA featuring a decoupled planning and lifting paradigm. In the planning phase, PixelPilot reformulates scene understanding and trajectory prediction as sensor-agnostic 2D-to-2D tasks in the image plane, thereby facilitating scalable training across diverse datasets. The planned 2D trajectories are then deterministically lifted to 3D only during inference, ensuring the full exploitation of visual cues and generalization across different vehicles. To realize this paradigm, we propose a knowledge-instilled policy learning strategy that applies dense, intermediate rewards via Group Relative Policy Optimization (GRPO) to enforce a rigorous causal chain from visual perception to spatial planning. Extensive experiments demonstrate that PixelPilot achieves state-of-the-art performance in both open-loop and closed-loop settings, validating its superior scalability and visual reasoning capabilities.

Guoqing Wang, Pin Tang, Xiangxuan Ren et al.

Reconstructing 3D scene structures from sparse, low-overlap observations remains a fundamental challenge in autonomous driving. Recent state-of-the-art frameworks achieve promising results by incorporating voxel-based Gaussians, but incur substantial computational redundancy due to a uniform volumetric processing strategy. To bridge the gap between the efficiency of pixel-based Gaussian methods and the structural completeness of voxel-based Gaussian approaches, we propose FocusGS, a simple yet effective framework that shifts the paradigm from global densification to targeted structural completion. Our central insight is that structural completion should be decoupled from deterministic regions, with computation concentrated exclusively on areas exhibiting geometric ambiguity. Specifically, FocusGS addresses the localization challenge by deriving a 3D Geometric Ambiguity Manifold to accurately isolate localized areas prone to occlusion and high geometric uncertainty. To overcome the subsequent manifold completion challenge, we design a lightweight targeted structure completion module that selectively instantiates and optimizes continuous Gaussian queries strictly within this unstructured, sparse topological subspace. Extensive experiments demonstrate that FocusGS achieves a superior efficiency-quality trade-off, advancing state-of-the-art performance on driving-centric benchmarks while naturally reducing the total number of Gaussians by ~74% and decreasing rendering time by ~34%.

Changda Ma, Sunshiyu Wang, Canting Zhu et al.

Architecture and music have been linked through proportion and temporal structure, yet architectural geometry is rarely viewed as a source of generative music. Revisiting Xenakis' one-directional transformation from string glissandi in Metastaseis to the ruled surfaces of the Philips Pavilion, we invert this workflow and sonify the completed Pavilion as a temporal composition. We reconstruct the Pavilion as nine ruled surfaces, extract their governing ruling lines, and subdivide each surface into structural lines and spatial sampling points. Four evenly spaced ruling lines per surface generate continuous string glissandi, while 3357 sampled points develop five density-based energy blocks and a sparse brass and woodwind subsequence. Implemented in Python, the system produces MIDI rendered in Ableton Live, accompanied by a real-time 3D visualization that reveals architectural motion, stasis, and structural contrast through sound and image. In general, this work paves the way for the transfer of architectural geometry as a performable musical structure, extending Xenakis's architectural and musical thinking to sonification and interactive music practice.