Publications (25)
OneTrans: Unified Feature Interaction and Sequence Modeling with One Transformer in Industrial Recommender
Zhaoqi Zhang, Haolei Pei, Jun Guo +5
In recommendation systems, scaling up feature-interaction modules (e.g., Wukong, RankMixer) or user-behavior sequence modules (e.g., LONGER) has achieved notable success. However,…
DexMV: Imitation Learning for Dexterous Manipulation from Human Videos
Yuzhe Qin, Yueh-Hua Wu, Shaowei Liu +4
While significant progress has been made on understanding hand-object interactions in computer vision, it is still very challenging for robots to perform complex dexterous manipula…
Muon is Scalable for LLM Training
Jingyuan Liu, Jianlin Su, Xingcheng Yao +25
Recently, the Muon optimizer based on matrix orthogonalization has demonstrated strong results in training small-scale language models, but the scalability to larger models has not…
Hand-Object Contact Consistency Reasoning for Human Grasps Generation
Hanwen Jiang, Shaowei Liu, Jiashun Wang +1
While predicting robot grasps with parallel jaw grippers have been well studied and widely applied in robot manipulation tasks, the study on natural human grasp generation with a m…
Kimi K2.5: Visual Agentic Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +322
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…
Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation
Siyi Chen, Shaowei Liu, Yixuan Jia +4
Recent progress has shown promise in distilling multi-step video diffusion models into efficient few-step students. Among them, Distribution Matching Distillation (DMD) and its suc…
CTR is not Enough: a Novel Reinforcement Learning based Ranking Approach for Optimizing Session Clicks
Shaowei Liu, Yangjun Liu
Ranking is a crucial module using in the recommender system. In particular, the ranking module using in our YoungTao recommendation scenario is to provide an ordered list of items…
PhysGen3D: Crafting a Miniature Interactive World from a Single Image
Boyuan Chen, Hanxiao Jiang, Shaowei Liu +4
Envisioning physically plausible outcomes from a single image requires a deep understanding of the world's dynamics. To address this, we introduce PhysGen3D, a novel framework that…
PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation
Shaowei Liu, Zhongzheng Ren, Saurabh Gupta +1
We present PhysGen, a novel image-to-video generation method that converts a single image and an input condition (e.g., force and torque applied to an object in the image) to produ…
Boosting Continuous Emotion Recognition with Self-Pretraining using Masked Autoencoders, Temporal Convolutional Networks, and Transformers
Weiwei Zhou, Jiada Lu, Chenkun Ling +2
Human emotion recognition holds a pivotal role in facilitating seamless human-computer interaction. This paper delineates our methodology in tackling the Valence-Arousal (VA) Estim…
Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time
Shaowei Liu, Hanwen Jiang, Jiarui Xu +2
Estimating 3D hand and object pose from a single image is an extremely challenging problem: hands and objects are often self-occluded during interactions, and the 3D annotations ar…
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…
Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos
Shaowei Liu, Subarna Tripathi, Somdeb Majumdar +1
We propose to forecast future hand-object interactions given an egocentric video. Instead of predicting action labels or pixels, we directly predict the hand motion trajectory and…
Kimi-VL Technical Report
Kimi Team, Angang Du, Bohong Yin +92
We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong…
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Kimi Team, Angang Du, Bofei Gao +93
Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learni…
ContactGen: Generative Contact Modeling for Grasp Generation
Shaowei Liu, Yang Zhou, Jimei Yang +2
This paper presents a novel object-centric contact representation ContactGen for hand-object interaction. The ContactGen comprises three components: a contact map indicates the con…
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…
MoBA: Mixture of Block Attention for Long-Context LLMs
Enzhe Lu, Zhejun Jiang, Jingyuan Liu +22
Scaling the effective context length is essential for advancing large language models (LLMs) toward artificial general intelligence (AGI). However, the quadratic increase in comput…
Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Clouds
Shaowei Liu, Saurabh Gupta, Shenlong Wang
We build rearticulable models for arbitrary everyday man-made objects containing an arbitrary number of parts that are connected together in arbitrary ways via 1 degree-of-freedom…
MoRight: Motion Control Done Right
Shaowei Liu, Xuanchi Ren, Tianchang Shen +5
Generating motion-controlled videos--where user-specified actions drive physically plausible scene dynamics under freely chosen viewpoints--demands two capabilities: (1) disentangl…
Visual Sync: Multi-Camera Synchronization via Cross-View Object Motion
Shaowei Liu, David Yifan Yao, Saurabh Gupta +1
Today, people can easily record memorable moments, ranging from concerts, sports events, lectures, family gatherings, and birthday parties with multiple consumer cameras. However,…
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…
CASA: Category-agnostic Skeletal Animal Reconstruction
Yuefan Wu, Zeyuan Chen, Shaowei Liu +2
Recovering the skeletal shape of an animal from a monocular video is a longstanding challenge. Prevailing animal reconstruction methods often adopt a control-point driven animation…
Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation
Shaowei Liu, Chuan Guo, Bing Zhou +1
Close-proximity human-human interactive poses convey rich contextual information about interaction dynamics. Given such poses, humans can intuitively infer the context and anticipa…
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…