Recent advances in generalizable 3D Gaussian Splatting have demonstrated promising results in real-time high-fidelity rendering without per-scene optimization, yet existing approaches still struggle to handle unfamiliar visual content during inference on novel scenes due to limited generalizability. To address this challenge, we introduce MonoSplat, a novel framework that leverages rich visual priors from pre-trained monocular depth foundation models for robust Gaussian reconstruction. Our approach consists of two key components: a Mono-Multi Feature Adapter that transforms monocular features into multi-view representations, coupled with an Integrated Gaussian Prediction module that effectively fuses both feature types for precise Gaussian generation. Through the Adapter’s lightweight attention mechanism, features are seamlessly aligned and aggregated across views while preserving valuable monocular priors, enabling the Prediction module to generate Gaussian primitives with accurate geometry and appearance. Through extensive experiments on diverse real-world datasets, we convincingly demonstrate that MonoSplat achieves superior reconstruction quality and generalization capability compared to existing methods while maintaining computational efficiency with minimal trainable parameters. Codes are available at https://github.com/CUHK-AIM-Group/MonoSplat.

With the great popularity of Sora, video-based audio generation has become indispensable. While numerous video-to-audio generation models have emerged, they frequently face difficulties including semantic incompatibilities and synchronization problems, especially in situations with multiple objects. To address these difficulties, we introduce TAGMO, a novel training-free audio generation method that offers precise time control for multi-object video scenarios. Our approach first employs object detection to obtain the class labels and temporal labels of each object, which are then structured and utilized as control conditions within a latent diffusion model (LDM) to generate multi-object audio. Additionally, we innovatively design a time mask based on the corresponding temporal labels and integrate it into the denoising process of the pre-trained audio generation model to achieve accurate temporal control. Experimental results demonstrate that our method enhances temporal alignment accuracy and semantic consistency. Audio demonstrations are available at https://coco-create.github.io/.

Visual SLAM algorithms have been enhanced through the exploration of Gaussian Splatting representations, particularly in generating high-fidelity dense maps. While existing methods perform reliably in static environments, they often encounter camera tracking drift and fuzzy mapping when dealing with the disturbances caused by moving objects. This paper presents DyPho-SLAM, a real-time, resource-efficient visual SLAM system designed to address the challenges of localization and photorealistic mapping in environments with dynamic objects. Specifically, the proposed system integrates prior image information to generate refined masks, effectively minimizing noise from mask misjudgment. Additionally, to enhance constraints for optimization after removing dynamic obstacles, we devise adaptive feature extraction strategies significantly improving the system’s resilience. Experiments conducted on publicly dynamic RGB-D datasets demonstrate that the proposed system achieves state-of-the-art performance in camera pose estimation and dense map reconstruction, while operating in real-time in dynamic scenes.

Catching flying objects with a cushioning process is a skill commonly performed by humans, yet it remains a significant challenge for robots. In this paper, we present a framework that combines optimization and learning to achieve compliant catching on mobile manipulators (CCMM). First, we propose a high-level capture planner for mobile manipulators (MM) that calculates the optimal capture point and joint configuration. Next, the pre-catching (PRC) planner ensures the robot reaches the target joint configuration as quickly as possible. To learn compliant catching strategies, we propose a network that leverages the strengths of LSTM for capturing temporal dependencies and positional encoding for spatial context (P-LSTM). This network is designed to effectively learn compliant strategies from human demonstrations. Following this, the post-catching (POC) planner tracks the compliant sequence output by the P-LSTM while avoiding potential collisions due to structural differences between humans and robots. We validate the CCMM framework through both simulated and real-world ball-catching scenarios, achieving a success rate of 98.70% in simulation, 92.59% in real-world tests, and a 28.7% reduction in impact torques. The open source code will be released for the reference of the community1.

Reinforcement learning (RL) has garnered increasing attention in text-to-image (T2I) generation. However, most existing RL approaches are tailored to either diffusion models or autoregressive models, overlooking an important alternative: masked generative models. In this work, we propose Mask-GRPO, the first method to incorporate Group Relative Policy Optimization (GRPO)-based RL into this overlooked paradigm. Our core insight is to redefine the transition probability, which is different from current approaches, and formulate the unmasking process as a multi-step decision-making problem. To further enhance our method, we explore several useful strategies, including removing the Kullback–Leibler constraint, applying the reduction strategy, and filtering out low-quality samples. Using Mask-GRPO, we improve a base model, Show-o, with substantial improvements on standard T2I benchmarks and preference alignment, outperforming existing state-of-the-art approaches.