MM
Michael Bi Mi
cs.CVcs.AIcs.LGcs.CLcs.MMAlgorithmscs.GTcs.ROcs.SDeess.AS
On Valency
published · living versionsW_v62ya8jw·v1 · currentpublished
TinyAstral: Transferring Self-Evolving Harnesses to Tiny Generalist Manipulation Agents
with Kehong Gong, Xiaoxu Zheng, Guanli Hou, Seunghun Lee +6
1 version
W_863tmwxz·v1published
Preprints & journals
22 papers in the corpus · 2022–2026Fast-VLA: You Only Think Once for Robot Manipulation2610.21389v1 · Kehong Gong, Guanli Hou, Xiaoxu Zheng et al.2026 · 0 citationsarXiv
DuoRate: Two-Rate Per-Expert Precision Allocation for Mixture-of-Experts Serving2610.13328v1 · Mengqi Guo, Zhe Wei, Yuan Yuan et al.2026 · 0 citationsarXiv
StagQ: Constraint-Driven Multi-Precision Weight Quantization for LLMs2610.05977v1 · Zhe Wei, Mengqi Guo, Yuan Yuan et al.2026 · 0 citationsarXiv
Breaking the Horizontal Prior: From Long-Tailed Orientation Bias to Roll-Robust Monocular Depth Estimation2608.00678v1 · Kaihua Tang, Ziqing Xia, Xiaoxu Zheng et al.2026 · 0 citationsarXiv
GhostRNN: Reducing State Redundancy in RNN with Cheap Operations2411.14489v1 · Hang Zhou, Xiaoxu Zheng, Yunhe Wang et al.2024 · 1 citationProc. INTERSPEECH 2023, 226-230
Vista3D: Unravel the 3D Darkside of a Single Image2409.12193v1 · Qiuhong Shen, Xingyi Yang, Michael Bi Mi et al.2024 · 1 citationarXiv
Isomorphic Pruning for Vision Models2407.04616v1 · Gongfan Fang, Xinyin Ma, Michael Bi Mi et al.2024 · 24 citationsarXiv
MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation2401.11115v3 · Nhat M. Hoang, Kehong Gong, Chuan Guo et al.2024 · 6 citationsarXiv
Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention2401.07459v1 · Xin Yang, Wending Yan, Yuan Yuan et al.2024 · 13 citationsarXiv
HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping2312.17492v2 · Xin Zhang, Jinheng Xie, Yuan Yuan et al.2023 · 3 citationsarXiv
DreamDrone: Text-to-Image Diffusion Models are Zero-shot Perpetual View Generators2312.08746v3 · Hanyang Kong, Dongze Lian, Michael Bi Mi et al.2023 · 1 citationarXiv
Learning Unorthogonalized Matrices for Rotation Estimation2312.00462v1 · Kerui Gu, Zhihao Li, Shiyong Liu et al.2023 · 1 citationarXiv
Priority-Centric Human Motion Generation in Discrete Latent Space2308.14480v2 · Hanyang Kong, Kehong Gong, Dongze Lian et al.2023 · 46 citationsarXiv
Bias-Compensated Integral Regression for Human Pose Estimation.37018104 · Gu, Kerui, Yang, Linlin, Mi, Michael Bi et al.2023 · 23 citationsIEEE transactions on pattern analysis and machine intelligence. 2023;45(9):10687-10702
Overcoming the Trade-off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction2305.00646v1 · Ziwei Yu, Chen Li, Linlin Yang et al.2023 · 10 citationsarXiv
Enhancing Video Super-Resolution via Implicit Resampling-based Alignment2305.00163v2 · Kai Xu, Ziwei Yu, Xin Wang et al.2023 · 39 citationsarXiv
TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration2304.02419v2 · Kehong Gong, Dongze Lian, Heng Chang et al.2023 · 65 citationsarXiv
DepGraph: Towards Any Structural Pruning2301.12900v2 · Gongfan Fang, Xinyin Ma, Mingli Song et al.2023 · 537 citationsarXiv
Improving Deep Regression with Ordinal Entropy2301.08915v3 · Shihao Zhang, Linlin Yang, Michael Bi Mi et al.2023 · 22 citationsarXiv
Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation2211.13409v1 · Xin Yang, Michael Bi Mi, Yuan Yuan et al.2022 · 10 citationsarXiv
PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision2203.15625v1 · Kehong Gong, Bingbing Li, Jianfeng Zhang et al.2022 · 40 citationsarXiv
Point2Seq: Detecting 3D Objects as Sequences2203.13394v1 · Yujing Xue, Jiageng Mao, Minzhe Niu et al.2022 · 28 citationsarXiv
Career total: 26 works. 22 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.