The rapid advancement of large reasoning models has saturated existing math benchmarks, underscoring the urgent need for more challenging evaluation frameworks.To address this, we introduce OlymMATH, a rigorously curated, Olympiad-level math benchmark comprising 350 problems, each with parallel English and Chinese versions.OlymMATH is the first benchmark to unify dual evaluation paradigms within a single suite: (1) natural language evaluation through OlymMATH-EASY and OlymMATH-HARD, comprising 200 computational problems with numerical answers for objective rule-based assessment, and (2) formal verification through OlymMATH-LEAN, offering 150 problems formalized in Lean 4 for rigorous process-level evaluation.All problems are manually sourced from printed publications to minimize data contamination, verified by experts, and span four core domains.Extensive experiments reveal the benchmark's significant challenge, and our analysis also uncovers consistent performance gaps between languages and identifies cases where models employ heuristic "guessing" rather than rigorous reasoning.To further support community research, we release 582k+ reasoning trajectories, a visualization tool, and expert solutions at https://github.com/RUCAIBox/OlymMATH.

Model alignment methods like Direct Preference Optimization and Contrastive Preference Optimization have enhanced machine translation performance by leveraging preference data to enable models to reject suboptimal outputs. During preference data construction, previous approaches primarily rely on humans, strong models like GPT4 or model self-sampling. In this study, we first explain the shortcomings of this practice. Then, we propose Self-Supervised Preference Optimization (SSPO), a novel framework which efficiently constructs translation preference data for iterative DPO training. Applying SSPO to 14B parameters large language models (LLMs) achieves comparable or better performance than GPT-4o on FLORES and multi-domain test datasets. We release an augmented MQM dataset in https://github.com/sunny-sjtu/MQM-aug.

Plant point cloud completion is essential for tasks like segmentation and surface reconstruction in plant phenotyping. Unlike the relatively simpler Computer-Aided Design models found in datasets like ShapeNet, plant point clouds are characterized by their rich geometric shapes and intricate edge features, making the task of completion significantly more challenging. In response to this, we propose a learnable uniform-edge dual sampling feature extractor that efficiently captures complex geometric features in plant point clouds by ensuring comprehensive coverage of overall structures while focusing on edge regions with critical geometric details. Additionally, we propose a multi-level geometry-aware contrastive regularization method to improve the alignment between the predicted point clouds and the missing regions, enhancing their distributional similarity to the ground truth. Experiments on the PlantPCC dataset show our model outperforms state-of-the-art methods, improving Chamfer Distance by 6.4% over the second-best model. Relevant datasets and codes are available at https://github.com/liqingque/PlantPCC.

Point cloud classification is critical for understanding three-dimensional shapes. While current methods focus on coarse-grained category recognition, real-world applications require identifying fine-grained subcategories with subtle differences. Existing deep learning-based methods struggle to effectively capture discriminative features. To address this challenge, we developed a Feature Representation Point Sampling (FRPS) module using attention mechanisms and feature correlation coefficients. Based on this module, we proposed a novel two-branch network SFRP, that simultaneously processes spatial and feature representation point information. By integrating these types of information, our SFRP model effectively captures and learns subtle shape differences in point clouds. Furthermore, we have collected and released the first fine-grained point cloud classification dataset, FG3DPoint, as a benchmark for evaluating models’ abilities to recognize fine-grained point clouds. Experiments on FG3DPoint demonstrate that SFRP achieves SOTA performance. Additionally, experiments on the coarse-grained ModelNet40 dataset confirm that the SFRP model exhibits robust generalization performance. Our code and data are available at https://github.com/foreshadowx/SFRP.

Deep learning draws heavily on the latest progress in semantic communications. The present paper aims to examine the security aspect of this cutting-edge technique from a novel shuffling perspective. Our goal is to improve upon the conventional secure coding scheme to strike a desirable tradeoff between transmission rate and leakage rate. To be more specific, for a wiretap channel, we seek to maximize the transmission rate while minimizing the semantic error probability under the given leakage rate constraint. Toward this end, we devise a novel semantic security communication system wherein the random shuffling pattern plays the role of the shared secret key. Intuitively, the permutation of feature sequences via shuffling would distort the semantic essence of the target data to a sufficient extent so that eavesdroppers cannot access it anymore. The proposed random shuffling method also exhibits its flexibility in working for the existing semantic communication system as a plugin. Simulations demonstrate the significant advantage of the proposed method over the benchmark in boosting secure transmission, especially when channels are prone to strong noise and unpredictable fading.

Simultaneous localization and mapping (SLAM) is a fundamental task for numerous applications such as autonomous navigation and exploration. Despite many SLAM datasets have been released, current SLAM solutions still struggle to have sustained and resilient performance. One major issue is the absence of high-quality datasets including diverse all-weather conditions and a reliable metric for assessing robustness. This limitation significantly restricts the scalability and generalizability of SLAM technologies, impacting their development, validation, and deployment. To address this problem, we present SubT-MRS, an ex-tremely challenging real-world dataset designed to push SLAM towards all-weather environments to pursue the most robust SLAM performance. It contains multi-degraded en-vironments including over 30 diverse scenes such as structureless corridors, varying lighting conditions, and perceptual obscurants like smoke and dust; multimodal sensors such as LiDAR, fisheye camera, IMU, and thermal camera; and multiple locomotions like aerial, legged, and wheeled robots. We developed accuracy and robustness evaluation tracks for SLAM and introduced novel robustness metrics. Comprehensive studies are performed, revealing new obser-vations, challenges, and opportunities for future research.

Multi-sensor fusion systems have been widely applied in various fields, including mobile robot, simultaneous localization and mapping (SLAM), and autonomous driving. For a tightly coupled multi-sensor fusion system, strict time synchronization between sensors will improve the accuracy of the system. However, there is currently a lack of open-source and general-purpose hardware synchronization systems for Cameras, IMUs, LiDARs, GNSS/RTK in the academic community. Therefore, we propose EverySync, an open hardware time synchronization system to address this gap. The synchronization accuracy of the system was evaluated through multiple experiments, achieving an accuracy of less than 1 ms. And, real-world experiments proved that hardware time synchronization improves the accuracy of the SLAM system. This open-source system is available on GitHub.

Aerial-ground vehicles have shown great potential in various fields due to their superior mobility and outstanding endurance. However, most of morphing aerial-ground vehicles consider little about controllability and traversability in ground mode. We present a novel aerial-ground vehicle called TransRotor. By proposing a differential gear joint, we equip TransRotor with omnidirectional mobility in both air and ground mode. Besides, using a four-wheel-steering model in ground mode provides better traversability and ground flexibility. Moreover, we design mid-mode transformation for Trans-Rotor, which provides smooth and rapid mode switching. In this work, we firstly propose a novel design of an aerial-ground vehicle. Then, we propose a decoupled controller considering the four-wheel-steer model to achieve autonomous navigation of the vehicle. Comprehensive experiments and a benchmark comparison are carried out to validate the outstanding performance of the proposed system, where the system shows ground flexibility and saves energy up to more than 95%.