Publications (19)
Memory Replay with Data Compression for Continual Learning
Liyuan Wang, Xingxing Zhang, Kuo Yang +7
Continual learning needs to overcome catastrophic forgetting of the past. Memory replay of representative old training samples has been shown as an effective solution, and achieves…
Multi-Teacher Knowledge Distillation for Incremental Implicitly-Refined Classification
Longhui Yu, Zhenyu Weng, Yuqing Wang +1
Incremental learning methods can learn new classes continually by distilling knowledge from the last model (as a teacher model) to the current model (as a student model) in the seq…
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…
Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning
Haiming Wang, Mert Unsal, Xiaohan Lin +37
We introduce Kimina-Prover Preview, a large language model that pioneers a novel reasoning-driven exploration paradigm for formal theorem proving, as showcased in this preview rele…
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
Longhui Yu, Weisen Jiang, Han Shi +7
Large language models (LLMs) have pushed the limits of natural language understanding and exhibited excellent problem-solving ability. Despite the great success, most existing open…
ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesis
Shoukang Hu, Kaichen Zhou, Kaiyu Li +6
Neural Radiance Fields (NeRF) has demonstrated remarkable 3D reconstruction capabilities with dense view images. However, its performance significantly deteriorates under sparse vi…
DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality
Yuqing Wang, Yizhi Wang, Longhui Yu +2
Vector font synthesis is a challenging and ongoing problem in the fields of Computer Vision and Computer Graphics. The recently-proposed DeepVecFont achieved state-of-the-art perfo…
Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap
Weiyang Liu, Longhui Yu, Adrian Weller +1
The neural collapse (NC) phenomenon describes an underlying geometric symmetry for deep neural networks, where both deeply learned features and classifiers converge to a simplex eq…
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…
: Intelligent Agent for Automated Pharmaceutical Patent Analysis
Xin Wang, Yifan Zhang, Xiaojing Zhang +5
Pharmaceutical patents play a vital role in biochemical industries, especially in drug discovery, providing researchers with unique early access to data, experimental results, and…
Forward-Backward Reasoning in Large Language Models for Mathematical Verification
Weisen Jiang, Han Shi, Longhui Yu +4
Self-Consistency samples diverse reasoning chains with answers and chooses the final answer by majority voting. It is based on forward reasoning and cannot further improve performa…
Continual Learning by Modeling Intra-Class Variation
Longhui Yu, Tianyang Hu, Lanqing Hong +3
It has been observed that neural networks perform poorly when the data or tasks are presented sequentially. Unlike humans, neural networks suffer greatly from catastrophic forgetti…
Dual-Curriculum Teacher for Domain-Inconsistent Object Detection in Autonomous Driving
Longhui Yu, Yifan Zhang, Lanqing Hong +2
Object detection for autonomous vehicles has received increasing attention in recent years, where labeled data are often expensive while unlabeled data can be collected readily, ca…
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…
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…
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…
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
Zhiqing Sun, Longhui Yu, Yikang Shen +4
Current AI alignment methodologies rely on human-provided demonstrations or judgments, and the learned capabilities of AI systems would be upper-bounded by human capabilities as a…
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
Weiyang Liu, Zeju Qiu, Yao Feng +11
Large foundation models are becoming ubiquitous, but training them from scratch is prohibitively expensive. Thus, efficiently adapting these powerful models to downstream tasks is…