20 citations · 61 across the 32 of their papers we have counts for
33 papers
MAC-I: Learned Metrics-Aware Covariance for Robust Visual-Inertial Fusion in Initialization and Calibration
Xiang Fei, Yuheng Qiu, Can Xu +5
Visual-Inertial (VI) fusion is fundamental to accurate and robust state estimation, where camera and IMU measurements are combined according to their respective uncertainties. Exis…
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +398
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…
RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring
Renbiao Jin, Mingxin Yang, Yutian Chen +8
Real-world video deblurring remains challenging due to diverse motion patterns, complex degradations, and the scarcity of realistic training data, yet robust restoration is critica…
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
Sirui Chen, Lei Xu, Yuying Zhao +6
Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewar…
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
Tianshuo Yang, Guanyu Chen, Yutian Chen +8
While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound rea…
AsyncEvGS: Asynchronous Event-Assisted Gaussian Splatting for Handheld Motion-Blurred Scenes
Jun Dai, Renbiao Jin, Bo Xu +5
3D reconstruction methods such as 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) achieve impressive photorealism but fail when input images suffer from severe motio…
AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model
Yutian Chen, Shi Guo, Renbiao Jin +7
Sparse-view 3D reconstruction is essential for modeling scenes from casual captures, but remain challenging for non-generative reconstruction. Existing diffusion-based approaches m…
Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting
Yixing Lao, Xuyang Bai, Xiaoyang Wu +7
Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally l…
Attention Residuals
Kimi Team, Guangyu Chen, Yu Zhang +34
Residual connections with PreNorm are standard in modern LLMs, yet they accumulate all layer outputs with fixed unit weights. This uniform aggregation causes uncontrolled hidden-st…
Kimi K2.5: Visual Agentic Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +333
We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that…
Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers
Yutian Chen, Yuheng Qiu, Ruogu Li +4
We propose Confidence-Guided Token Merging (Co-Me), an acceleration mechanism for visual geometric transformers without retraining or finetuning the base model. Co-Me distilled a l…
Kimi Linear: An Expressive, Efficient Attention Architecture
Kimi Team, Yu Zhang, Zongyu Lin +57
We introduce Kimi Linear, a hybrid linear attention architecture that, for the first time, outperforms full attention under fair comparisons across various scenarios -- including s…
Virtual Community: An Open World for Humans, Robots, and Society
Qinhong Zhou, Hongxin Zhang, Xiangye Lin +16
The rapid progress in AI and Robotics may lead to a profound societal transformation, as humans and robots begin to coexist within shared communities, introducing both opportunitie…
Kimi K2: Open Agentic Intelligence
Kimi Team, Yifan Bai, Yiping Bao +195
We introduce Kimi K2, a Mixture-of-Experts (MoE) large language model with 32 billion activated parameters and 1 trillion total parameters. We propose the MuonClip optimizer, which…
4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture
Yutian Chen, Shi Guo, Tianshuo Yang +4
Reconstructing fast-dynamic scenes from multi-view videos is crucial for high-speed motion analysis and realistic 4D reconstruction. However, the majority of 4D capture systems are…
UFM: A Simple Path towards Unified Dense Correspondence with Flow
Yuchen Zhang, Nikhil Keetha, Chenwei Lyu +9
Dense image correspondence is central to many applications, such as visual odometry, 3D reconstruction, object association, and re-identification. Historically, dense correspondenc…
AirIO: Learning Inertial Odometry with Enhanced IMU Feature Observability
Yuheng Qiu, Can Xu, Yutian Chen +3
Inertial odometry (IO) using only Inertial Measurement Units (IMUs) offers a lightweight and cost-effective solution for Unmanned Aerial Vehicle (UAV) applications, yet existing le…
Event-assisted 12-stop HDR Imaging of Dynamic Scene
Shi Guo, Zixuan Chen, Ziran Zhang +3
High dynamic range (HDR) imaging is a crucial task in computational photography, which captures details across diverse lighting conditions. Traditional HDR fusion methods face limi…
TRecViT: A Recurrent Video Transformer
Viorica Pătrăucean, Xu Owen He, Joseph Heyward +10
We propose a novel block for \emph{causal} video modelling. It relies on a time-space-channel factorisation with dedicated blocks for each dimension: gated linear recurrent units (…
Language Model Embeddings Can Be Sufficient for Bayesian Optimization
Tung Nguyen, Qiuyi Zhang, Bangding Yang +6
Bayesian Optimization is ubiquitous in experimental design and black-box optimization for improving search efficiency. However, most existing approaches rely on regression models w…
MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry
Yuheng Qiu, Yutian Chen, Zihao Zhang +2
We propose the MAC-VO, a novel learning-based stereo VO that leverages the learned metrics-aware matching uncertainty for dual purposes: selecting keypoint and weighing the residua…
Position: Leverage Foundational Models for Black-Box Optimization
Xingyou Song, Yingtao Tian, Robert Tjarko Lange +3
Undeniably, Large Language Models (LLMs) have stirred an extraordinary wave of innovation in the machine learning research domain, resulting in substantial impact across diverse fi…
RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
Aleksandar Botev, Soham De, Samuel L Smith +59
We introduce RecurrentGemma, a family of open language models which uses Google's novel Griffin architecture. Griffin combines linear recurrences with local attention to achieve ex…
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Soham De, Samuel L. Smith, Anushan Fernando +14
Recurrent neural networks (RNNs) have fast inference and scale efficiently on long sequences, but they are difficult to train and hard to scale. We propose Hawk, an RNN with gated…