Related papers: Kimi K2: Open Agentic Intelligence

The reproduction of state-of-the-art multimodal LLM pre-training faces barriers at every stage of the pipeline, including high-quality data filtering, multimodal data mixture strategies, sequence packing techniques, and training frameworks.…

Large models recently are widely applied in artificial intelligence, so efficient training of large models has received widespread attention. More recently, a useful Muon optimizer is specifically designed for matrix-structured parameters…

The effectiveness of LLM-based agents is often limited not by model capacity alone, but by how efficiently contextual information is utilized at runtime. Existing agent frameworks rely on rigid, syntax-heavy state representations such as…

We evaluate five state-of-the-art open-weights coding language models -- Kimi-K2.5 (at Q3 and Q4 quantizations), GLM-5.1, Qwen3-Coder-480B, and DeepSeek-V3.2 -- on a single multi-file React Native application generation task on NVIDIA GH200…

Fully-parametric language models generally require a huge number of model parameters to store the necessary knowledge for solving multiple natural language tasks in zero/few-shot settings. In addition, it is hard to adapt to the evolving…

Multimodal large language models (MLLMs) have demonstrated strong capabilities in visual understanding, yet they remain limited in complex, multi-step reasoning that requires deep searching and integrating visual evidence with external…

CLIP is a seminal multimodal model that maps images and text into a shared representation space through contrastive learning on billions of image-caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate…

Recent advances in generalist multi-agent systems (MAS) have largely followed a context-engineering plus centralized paradigm, where a planner agent coordinates multiple worker agents through unidirectional prompt passing. While effective…

We introduce MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. MiniMax-M1 is powered by a hybrid Mixture-of-Experts (MoE) architecture combined with a lightning attention mechanism. The model is…

This report introduces \texttt{EEVE-Korean-v1.0}, a Korean adaptation of large language models that exhibit remarkable capabilities across English and Korean text understanding. Building on recent highly capable but English-centric LLMs,…

Conventional algorithmic trading systems are grounded in deterministic heuristics or offline-trained statistical models that cannot adapt to the semantic complexity of rapidly shifting market regimes. This paper introduces AGENTICAITA, an…

Acoustic-to-word (A2W) models that allow direct mapping from acoustic signals to word sequences are an appealing approach to end-to-end automatic speech recognition due to their simplicity. However, prior works have shown that modelling A2W…

Mixture of Experts (MoE) offers remarkable performance and computational efficiency by selectively activating subsets of model parameters. Traditionally, MoE models use homogeneous experts, each with identical capacity. However, varying…

The human ability to easily solve multimodal tasks in context (i.e., with only a few demonstrations or simple instructions), is what current multimodal systems have largely struggled to imitate. In this work, we demonstrate that the…

Mixture-of-Experts(MoE) Vision-Language Models (VLMs) offer remarkable performance but incur prohibitive memory and computational costs, making compression essential. Post-Training Quantization (PTQ) is an effective training-free technique…

Communication is essential in coordinating the behaviors of multiple agents. However, existing methods primarily emphasize content, timing, and partners for information sharing, often neglecting the critical aspect of integrating shared…

Machine learning has been widely used to optimize complex engineering workflows across numerous domains. In integrated circuit design, modern flows (e.g., register-transfer level to physical layout) involve extensive configuration via…

We introduce MiniMax-01 series, including MiniMax-Text-01 and MiniMax-VL-01, which are comparable to top-tier models while offering superior capabilities in processing longer contexts. The core lies in lightning attention and its efficient…

A multimodal AI agent is characterized by its ability to process and learn from various types of data, including natural language, visual, and audio inputs, to inform its actions. Despite advancements in large language models that…

This paper introduces KLong, an open-source LLM agent trained to solve extremely long-horizon tasks. The principle is to first cold-start the model via trajectory-splitting SFT, then scale it via progressive RL training. Specifically, we…