Open library
The essential reading of generative AI and agents, open in a clean reading view, with Meow and Standard summaries when available. No account needed to read.
563 papers · 561 with a Meow summary · 333 posts
Every paper prepared on Reading + AI, newest first.
Idan Shenfeld, Mehul Damani, Jonas Hübotter et al.
Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models. While on-policy reinforcement learning can reduce forgetting, it requires explicit reward functions that are often unavailable. Learning from expert de…
Looped Transformers increase effective depth by iterating a shared block of layers, but most evaluations compare at fixed model size, conflating architectural advantage with extra FLOPs. We study looping on Mixture-of-Experts Transformers while closely matching per-token FLOPs, total non-embedding parameters, and KV c…
Yushi Bai, Qian Dong, Ting Jiang et al.
Long-context agentic workflows have emerged as a defining use case for large language models, making attention efficiency critical for both inference speed and serving cost. Sparse attention addresses this challenge effectively, and DeepSeek Sparse Attention (DSA) is a representative production-grade solution: a light…
Shaobo Wang Xuan Ouyang Tianyi Xu Yuzheng Hu Jialin Liu, Guo Chen Tianyu Zhang Junhao Zheng Kexin Yang Xingzhang Ren, Dayiheng Liu Linfeng Zhang
As high-quality public text approaches exhaustion, a phenomenon known as the Data Wall ([Villalobos et al., 2022](#bib.bib21)), pre-training is shifting from more tokens to better tokens. However, existing methods either rely on heuristic static filters that ignore training dynamics, or use dynamic yet optimizer-agnos…
Jianuo Huang Yaojie Zhang Qituan Zhang Hao Lin Hanlin Xu Linfeng Zhang
Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in parallel with the target model. However, its practical speedup is constrained by the trade-off between draft quality and drafting cost: autoregressive drafters model causal dependencies among draft tokens but incur sequent…
John Yang, Carlos E. Jimenez, Alexander Wettig et al.
Language model (LM) agents are increasingly being used to automate complicated tasks in digital environments. Just as humans benefit from powerful software applications, such as integrated development environments, for complex tasks like software engineering, we posit that LM agents represent a new category of end use…
Edoardo Debenedetti, Ilia Shumailov, Tianqi Fan et al.
Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an untrusted environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data. In this paper we propose CaMeL, a robust defense that creates a protective system layer around the LLM, sec…
GLM-V Team
We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundat…
Peng Wang*Shuai Bai*Sinan Tan*Shijie Wang*Zhihao Fan*, Jinze Bai* Keqin ChenXuejing LiuJialin WangWenbin GeYang FanKai DangMengfei Du Xuancheng RenRui MenDayiheng LiuChang ZhouJingren Zhou, Junyang Lin Qwen Team Alibaba Group
We present the Qwen2-VL Series, an advanced upgrade of the previous Qwen-VL models that redefines the conventional predetermined-resolution approach in visual processing. Qwen2-VL introduces the Naive Dynamic Resolution mechanism, which enables the model to dynamically process images of varying resolutions into differ…
Physical Intelligence
Robot learning holds tremendous promise to unlock the full potential of flexible, general, and dexterous robot systems, as well as to address some of the deepest questions in artificial intelligence. However, bringing robot learning to the level of generality required for effective real-world systems faces major obsta…
Gemini Team, Google
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and re…
Chameleon Team
We present Chameleon, a family of early-fusion token-based mixed-modal models capable of understanding and generating images and text in any arbitrary sequence. We outline a stable training approach from inception, an alignment recipe, and an architectural parameterization tailored for the early-fusion, token-based, m…
Jake Bruce, Michael Dennis, Ashley Edwards et al.
We introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters,…
Igor Slinko, Yaroslav Golubev, Sergey Titov
The evaluation of coding agents generally strives to be as realistic as possible. In our study, we collect 4,782 agent sessions of real software engineers in JetBrains IDEs, which we call Production Sessions. Since our subject is interactive agents, we study the sessions with at least three user messages (33% of the s…
Gemma Team, Google DeepMind\authfootnotemark1
We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision understanding abilities, a wider coverage of languages and longer context – at least 128K tokens. We also change the architecture of the model to…
Grégoire Mialon, Clémentine Fourrier, Craig Swift et al.
We introduce GAIA, a benchmark for General AI Assistants that, if solved, would represent a milestone in AI research. GAIA proposes real-world questions that require a set of fundamental abilities such as reasoning, multi-modality handling, web browsing, and generally tool-use proficiency. GAIA questions are conceptua…
Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani et al.
The rapid advancement of chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autono…
Jonathan Ho, Ajay Jain, Pieter Abbeel
We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion pro…
Microsoft
We introduce **phi-3-mini**, a 3.8 billion parameter language model trained on 3.3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3.5 (e.g., **phi-3-mini** achieves 69% on MMLU and 8.38 on MT-bench), despite b…
StepFun Team
We introduce **Step 3.5 Flash**, a sparse Mixture-of-Experts (MoE) model that bridges the gap between frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: reasoning that’s sharp, and execution that’s fast and reliable. Reflecting these priorities, Step 3…
We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 is a Transformer-based model trained using a mixture of objectives. Through extensive evaluations on English and multilingual language, and…
BigScience Workshop, Major Contributors, Dataset et al.
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democr…
Weihan Wang, Qingsong Lv, Wenmeng Yu et al.
We introduce CogVLM, a powerful open-source visual language foundation model. Different from the popular shallow alignment method which maps image features into the input space of language model, CogVLM bridges the gap between the frozen pretrained language model and image encoder by a trainable visual expert module i…
We present OLMo 2, the next generation of our fully open language models. OLMo 2 includes a family of dense autoregressive language models at 7B, 13B and 32B scales with fully released artifacts—model weights, full training data, training code and recipes, training logs and thousands of intermediate checkpoints. In th…
Marah Abdin Jyoti Aneja Harkirat Behl Sébastien Bubeck Ronen Eldan Suriya Gunasekar Michael Harrison Russell J. Hewett Mojan Javaheripi Piero Kauffmann James R. Lee Yin Tat Lee Yuanzhi Li Weishung Liu Caio C. T. Mendes Anh Nguyen Eric Price Gustavo de Rosa Olli Saarikivi Adil Salim Shital Shah Xin Wang Rachel Ward Yue Wu Dingli Yu Cyril Zhang Yi Zhang
We present **phi-4**, a 14-billion parameter language model developed with a training recipe that is centrally focused on data quality. Unlike most language models, where pre-training is based primarily on organic data sources such as web content or code, phi-4 strategically incorporates synthetic data throughout the…
We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves $86.7$ on AIME $2024$, $55.0$ on Codeforces and $77.3$ on GPQA, demonstrating excellent reasoning abilities in STEM and coding. Beyond reaso…
NVIDIA
**Abstract.** We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemotron 3 Super is the first model in the Nemotron 3 family to 1) be pre-trained in NVFP4, 2) leverage LatentMoE, a new Mixture-…
Dirk Groeneveld Iz Beltagy, Pete Walsh Akshita Bhagia Rodney Kinney Oyvind Tafjord, Ananya Harsh Jha Hamish Ivison Ian Magnusson Yizhong Wang et al.
Language models (LMs) have become ubiquitous in both NLP research and in commercial product offerings. As their commercial importance has surged, the most powerful models have become closed off, gated behind proprietary interfaces, with important details of their training data, architectures, and development undisclos…
NVIDIA
We release the Nemotron-4 340B model family, including Nemotron-4-340B-Base, Nemotron-4-340B-Instruct, and Nemotron-4-340B-Reward. Our models are open access under the NVIDIA Open Model License Agreement, a permissive model license that allows distribution, modification, and use of the models and its outputs. These mo…
Kimi Team
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 agent capabilities**—all while activating only **2.8B** parameters in its language decoder (Kimi-VL-A3B). Kimi-VL demonstrates strong…
LLM-Core Xiaomi
We present MiMo-V2-Flash, a Mixture-of-Experts (MoE) model with 309B total parameters and 15B active parameters, designed for fast, strong reasoning and agentic capabilities. MiMo-V2-Flash adopts a hybrid attention architecture that interleaves **Sliding Window Attention (SWA)** with global attention, with a 128-token…
Tongyi DeepResearch Team
We present **Tongyi DeepResearch**, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking research tasks. To incentivize autonomous deep research agency, Tongyi DeepResearch is developed through an end-to-end training framework that combines agentic mid-training and…
MiniMax
We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series…
Kimi Team
We introduce Kimi Linear, a hybrid linear attention architecture that, for the first time, outperforms full attention under fair comparisons across various scenarios—including short-context, long-context, and reinforcement learning (RL) scaling regimes. At its core lies Kimi Delta Attention (KDA), an expressive linear…
MiniMax
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 developed based on our previous MiniMax-Text-01 model ([MiniMax et al., 2025](#bib.bi…
Haoran Wei, Yaofeng Sun, Yukun Li
We present DeepSeek-OCR as an initial investigation into the feasibility of compressing long contexts via optical 2D mapping. DeepSeek-OCR consists of two components: DeepEncoder and DeepSeek3B-MoE-A570M as the decoder. Specifically, DeepEncoder serves as the core engine, designed to maintain low activations under hig…
Enzhe Lu, Zhejun Jiang, Jingyuan Liu et al.
Scaling the effective context length is essential for advancing large language models (LLMs) toward artificial general intelligence (AGI). However, the quadratic increase in computational complexity inherent in traditional attention mechanisms presents a prohibitive overhead. Existing approaches either impose strongly…
Kimi Team
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 improves upon Muon with a novel QK-clip technique to address training instability while enjoying the advanced token efficiency of Muon. Ba…