While Mamba-based models have shown strong potential for long sequence modeling, adapting them to vision is challenging due to the requirement of local neighborhood correlations and multi-directional spatial contexts for visual understanding. In this paper, we present LiAuto-MindViT, a novel hybrid vision backbone that...
Chain-of-Thought (CoT) reasoning is increasingly incorporated into Vision-Language-Action (VLA) models, yet it can degrade the performance of stronger embodied agents. We investigate this capability-dependent effect by distinguishing explicit reasoning from latent decision computation, i.e., perception-grounded computa...
Yuan-Peng Lin, Zi-Yu Zhou, Jin-Long Zhao et al.· 0 citations
MachEmbodied-Brain (ME-Brain) is introduced, a self-evolving embodied system organized around a closed loop of action execution, experience acquisition, experience evolution, and improved execution that shifts embodied intelligence from train-and-freeze to deploy-and-evolve without model retraining.
Wei He, Heng-Tao Li, Chen-Feng Wang et al.· 1 citation
MachEmbodied-U0, a unified embodied foundation model connecting understanding and generation experts through a Mixture-of-Transformers architecture, is presented, a unified embodied foundation model connecting understanding and generation experts through a Mixture-of-Transformers architecture that combines competitive...
Hao-Ran Wen, Wen-Fu Wang, Kun-Song Shi et al.· 1 citation
RLVR has substantially improved the reasoning capabilities of LLMs. However, existing methods typically parameterize temporal progression in the Markov Decision Process by token-by-token generation, despite the highly non-uniform information flow along autoregressive trajectories. In this paper, we propose InfoPPO, whi...
Yong-Cheng Zeng, Xin-Yu Cui, Yan Song et al.· 0 citations
The behavioral analysis reveals three recurring failure patterns: agents may fail to recognize the risk, recognize it but fail to intervene before acting, or follow skill instructions beyond the user's intended scope, which highlights the need to improve both risk reasoning and execution control in agent frameworks.
Qi-Yuan Liu, Tingfeng Hui, Kun Zhan et al.· arXiv.org· 3 citations· ⚡1
The introduction of ChainSpace, a chained-reasoning paradigm that structures spatial reasoning as a state-preserving multi-round process, is introduced as an effective paradigm for more faithful evaluation and more data-efficient learning of spatial intelligence.
Xiao-Han Zhang, Feng Gu, Xudong Rao et al.· 0 citations
SpeechAgent-R, an audio agent that coordinates its intrinsic multimodal understanding with external skills and tools, is developed and HIU-Bench is introduced to jointly evaluate task performance, interaction quality and generalization to diverse task settings.
Yuwen Wang, Tian-Hao Zhang, Ming Cai et al.· 0 citations
ParaIntent is introduced, a Chinese benchmark comprising 14 intent categories with balanced explicit and implicit samples, together with a multidimensional evaluation protocol covering intent fulfillment, response quality, and emotional expression, which improves over standard GRPO on most automatic metrics and achieve...
Xiangning Lin, Tian-Hao Zhang, Chunfeng Wang et al.· 1 citation
Results indicate that selective internalization through reward filtering and policy support shaping is effective for open-ended reinforcement learning.
FoMoVLA is proposed, a framework that augments VLA representations with explicit spatio-temporal supervision by jointly learning future feature foresight and sparse 2D point tracking, enhancing the continuous action policy.
Wei Li, Peijin Jia, Yuan Ma et al.· arXiv.org· 0 citations
LaCache is proposed, a training-free acceleration framework that alleviates operator-level redundancy through lossless caching and mixed precision, and inegrates a per-group FP8 quantization strategy for FFN layers, tailored to step-dependent activation distributions across the diffusion process.
Xingru Chen, Zelang Liang, Yongjia Ma et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
