9 accepted papers
Personalized Federated Learning (PFL) aims to train customized models for clients with highly heterogeneous data distributions while preserving data privacy. Existing approaches often rely on heuristics like clustering or model interpolation, which lack principled mechanisms for balancing heterogene
Recent Progress in post-training flow matching for text-to-image (T2I) generation with Group Relative Policy Optimization (GRPO) has demonstrated strong potential. However, it is hindered by a critical limitation: inaccurate advantage attribution. In this work, we argue that aggregating consecutive …
Scene graph generation is a pivotal task in computer vision, focusing on comprehensive identification of visual relation tuples embedded within images. The advancement of methods involving triplets has sought to enhance task performance by integrating triplets as contextual features for more precise…
Monocular visual-inertial odometry can effectively solve the problem of unobservable metric scale in monocular odometry. However, due to differences in sensor observation noise and redundant constraints, the positioning accuracy of a general monocular visual-inertial odometer may decline compared wi
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,…
For AR applications, the present monocular VO methods can be further improved to provide more real-time and accurate self-localization in a dynamic environment with motion disturbance. This letter proposes the CCVO (Cascaded CNNs for Visual Odometry) which is a monocular VO approach to realize end-t
Co-design of morphology and control of a Voxel-based Soft Robot (VSR) is challenging due to the notorious bi-level optimization. In this paper, we present a Curriculum-based Co-design (CuCo) method for learning to design and control VSRs through an easy-to-difficult process. Specifically, we expand…
In spoken dialog system, transcription errors in Automated Speech Recognition (ASR) impact downstream task, especially dialog state tracking (DST). Approaches to alleviate such errors involve using richer information such as word-lattices and word confusion networks. However, in some cases, this inf…
Brain-body co-design, which involves the collaborative design of control strategies and morphologies, has emerged as a promising approach to enhance a robot's adaptability to its environment. However, the conventional co-design process often starts from scratch, lacking the utilization of prior know…