Complementary Reinforcement Learning

Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome feedback but also from the agent's inability to leverage prior experience across episodes. While augmenting agents with historical experience offers a promising remedy, existing approaches suffer from a critical weakness: the experience distilled from history is either stored statically or fail to coevolve with the improving actor, causing a progressive misalignment between the experience and the actor's evolving capability that diminishes its utility over the course of training. Inspired by complementary learning systems in neuroscience, we present Complementary RL to achieve seamless co-evolution of an experience extractor and a policy actor within the RL optimization loop. Specifically, the actor is optimized via sparse outcome-based rewards, while the experience extractor is optimized according to whether its distilled experiences demonstrably contribute to the actor's success, thereby evolving its experience management strategy in lockstep with the actor's growing capabilities. Empirically, Complementary RL outperforms outcome-based agentic RL baselines that do not learn from experience, achieving 10% performance improvement in single-task scenarios and exhibits robust scalability in multi-task settings. These results establish Complementary RL as a paradigm for efficient experience-driven agent learning.

ADAPT: Adaptive Dual-projection Architecture for Perceptive Traversal

Agile humanoid locomotion in complex 3D en- vironments requires balancing perceptual fidelity with com- putational efficiency, yet existing methods typically rely on rigid sensing configurations. We propose ADAPT (Adaptive dual-projection architecture for perceptive traversal), which represents the environment using a horizontal elevation map for terrain geometry and a vertical distance map for traversable- space constraints. ADAPT further treats its spatial sensing range as a learnable action, enabling the policy to expand its perceptual horizon during fast motion and contract it in cluttered scenes for finer local resolution. Compared with voxel-based baselines, ADAPT drastically reduces observation dimensionality and computational overhead while substantially accelerating training. Experimentally, it achieves successful zero-shot transfer to a Unitree G1 Humanoid and signifi- cantly outperforms fixed-range baselines, yielding highly robust traversal across diverse 3D environtmental challenges.

Overview and Comparison of AVS Point Cloud Compression Standard

Point cloud is a prevalent 3D data representation format with significant application values in immersive media, autonomous driving, digital heritage protection, etc. However, the large data size of point clouds poses challenges to transmission and storage, which influences the wide deployments. Therefore, point cloud compression plays a crucial role in practical applications for both human and machine perception optimization. To this end, the Moving Picture Experts Group (MPEG) has established two standards for point cloud compression, including Geometry-based Point Cloud Compression (G-PCC) and Video-based Point Cloud Compression (V-PCC). In the meantime, the Audio Video coding Standard (AVS) Workgroup of China also have launched and completed the development for its first generation point cloud compression standard, namely AVS PCC. This new standardization effort has adopted many new coding tools and techniques, which are different from the other counterpart standards. This paper reviews the AVS PCC standard from two perspectives, i.e., the related technologies and performance comparisons.

MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation

When embodied AI is expanding from traditional object detection and recognition to more advanced tasks of robot manipulation and actuation planning, visual spatial reasoning from the video inputs is necessary to perceive the spatial relationships of objects and guide device actions. However, existing visual language models (VLMs) have very weak capabilities in spatial reasoning due to the lack of knowledge about 3D spatial information, especially when the reasoning task involve complex spatial relations across multiple video frames. In this paper, we present a new inference-time computing technique for on-device embodied AI, namely \emph{MosaicThinker}, which enhances the on-device small VLM's spatial reasoning capabilities on difficult cross-frame reasoning tasks. Our basic idea is to integrate fragmented spatial information from multiple frames into a unified space representation of global semantic map, and further guide the VLM's spatial reasoning over the semantic map via a visual prompt. Experiment results show that our technique can greatly enhance the accuracy of cross-frame spatial reasoning on resource-constrained embodied AI devices, over reasoning tasks with diverse types and complexities.

Depth estimation of a monoharmonic source using a vertical linear array at fixed distance

Estimating the depth of a monoharmonic sound source at a fixed range using a vertical linear array (VLA) is challenging in the absence of seabed environmental parameters, and relevant research remains scarce. The orthogonality constrained modal search based depth estimation (OCMS-D) method is proposed in this paper, which enables the estimation of the depth of a monoharmonic source at a fixed range using a VLA under unknown seabed parameters. Using the sparsity of propagating normal modes and the orthogonality of mode depth functions, OCMS-D estimates the normal mode parameters under a fixed source-array distance at first. The estimated normal mode parameters are then used to estimate the source depth. To ensure the precision of the source depth estimation, the method utilizes information on both the amplitude distribution and the sign (positive/negative) patterns of the estimated mode depth functions at the inferred source depth. Numerical simulations evaluate the performance of OCMS-D under different conditions. The effectiveness of OCMS-D is also verified by the Yellow Sea experiment and the SWellEx-96 experiment. In the Yellow Sea experiment, the depth estimation absolute errors by OCMS-D with a 4-second time window are less than 2.4 m. And the depth estimation absolute errors in the SWellEx-96 experiment with a 10-second time window are less than 5.4 m for the shallow source and less than 10.8 m for the deep source.

DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression

Recently, deep learning has significantly advanced the performance of point cloud geometry compression. However, the learning-based lossless attribute compression of point clouds with varying densities is under-explored. In this paper, we develop a learning-based framework, namely DALD-PCAC that leverages Levels of Detail (LoD) to tailor for point cloud lossless attribute compression. We develop a point-wise attention model using a permutation-invariant Transformer to tackle the challenges of sparsity and irregularity of point clouds during context modeling. We also propose a Density-Adaptive Learning Descriptor (DALD) capable of capturing structure and correlations among points across a large range of neighbors. In addition, we develop a prior-guided block partitioning to reduce the attribute variance within blocks and enhance the performance. Experiments on LiDAR and object point clouds show that DALD-PCAC achieves the state-of-the-art performance on most data. Our method boosts the compression performance and is robust to the varying densities of point clouds. Moreover, it guarantees a good trade-off between performance and complexity, exhibiting great potential in real-world applications. The source code is available at https://github.com/zb12138/DALD_PCAC.

SKATER: Synthesized Kinematics for Advanced Traversing Efficiency on a Humanoid Robot via Roller Skate Swizzles

Although recent years have seen significant progress of humanoid robots in walking and running, the frequent foot strikes with ground during these locomotion gaits inevitably generate high instantaneous impact forces, which leads to exacerbated joint wear and poor energy utilization. Roller skating, as a sport with substantial biomechanical value, can achieve fast and continuous sliding through rational utilization of body inertia, featuring minimal kinetic energy loss. Therefore, this study proposes a novel humanoid robot with each foot equipped with a row of four passive wheels for roller skating. A deep reinforcement learning control framework is also developed for the swizzle gait with the reward function design based on the intrinsic characteristics of roller skating. The learned policy is first analyzed in simulation and then deployed on the physical robot to demonstrate the smoothness and efficiency of the swizzle gait over traditional bipedal walking gait in terms of Impact Intensity and Cost of Transport during locomotion. A reduction of $75.86\%$ and $63.34\%$ of these two metrics indicate roller skating as a superior locomotion mode for enhanced energy efficiency and joint longevity.

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its importance, the open-source community lacks a principled, end-to-end ecosystem to streamline agent development. We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimizes the production pipeline for agent LLMs. ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering. We release ROME (ROME is Obviously an Agentic Model), an open-source agent grounded by ALE and trained on over one million trajectories. Our approach includes data composition protocols for synthesizing complex behaviors and a novel policy optimization algorithm, Interaction-based Policy Alignment (IPA), which assigns credit over semantic interaction chunks rather than individual tokens to improve long-horizon training stability. Empirically, we evaluate ROME within a structured setting and introduce Terminal Bench Pro, a benchmark with improved scale and contamination control. ROME demonstrates strong performance across benchmarks like SWE-bench Verified and Terminal Bench, proving the effectiveness of the ALE infrastructure.

DriveExplorer: Images-Only Decoupled 4D Reconstruction with Progressive Restoration for Driving View Extrapolation

This paper presents an effective solution for view extrapolation in autonomous driving scenarios. Recent approaches focus on generating shifted novel view images from given viewpoints using diffusion models. However, these methods heavily rely on priors such as LiDAR point clouds, 3D bounding boxes, and lane annotations, which demand expensive sensors or labor-intensive labeling, limiting applicability in real-world deployment. In this work, with only images and optional camera poses, we first estimate a global static point cloud and per-frame dynamic point clouds, fusing them into a unified representation. We then employ a deformable 4D Gaussian framework to reconstruct the scene. The initially trained 4D Gaussian model renders degraded and pseudo-images to train a video diffusion model. Subsequently, progressively shifted Gaussian renderings are iteratively refined by the diffusion model,and the enhanced results are incorporated back as training data for 4DGS. This process continues until extrapolation reaches the target viewpoints. Compared with baselines, our method produces higher-quality images at novel extrapolated viewpoints.

Joint Link Adaptation and Device Scheduling Approach for URLLC Industrial IoT Network: A DRL-based Method with Bayesian Optimization

In this article, we consider an industrial internet of things (IIoT) network supporting multi-device dynamic ultra-reliable low-latency communication (URLLC) while the channel state information (CSI) is imperfect. A joint link adaptation (LA) and device scheduling (including the order) design is provided, aiming at maximizing the total transmission rate under strict block error rate (BLER) constraints. In particular, a Bayesian optimization (BO) driven Twin Delayed Deep Deterministic Policy Gradient (TD3) method is proposed, which determines the device served order sequence and the corresponding modulation and coding scheme (MCS) adaptively based on the imperfect CSI. Note that the imperfection of CSI, error sample imbalance in URLLC networks, as well as the parameter sensitivity nature of the TD3 algorithm likely diminish the algorithm's convergence speed and reliability. To address such an issue, we proposed a BO based training mechanism for the convergence speed improvement, which provides a more reliable learning direction and sample selection method to track the imbalance sample problem. Via extensive simulations, we show that the proposed algorithm achieves faster convergence and higher sum-rate performance compared to existing solutions.