GitHub ranking / frozen snapshot

The AI papers with the most GitHub stars.

Linked repositories ranked by their snapshot star count, highlighting the research code that attracted the largest developer communities.

Linked papers: 730
Showing: Top 100
Snapshot: Aug 9, 2026

100 papers ranked by GitHub stars

Star counts change over time

01

arXiv.org

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

MinerU2.5 is a 1.2B-parameter vision-language model for document parsing that achieves state-of-the-art accuracy with high efficiency. It uses a decoupled, two-stage strategy: first, global layout analysis on a downsampled 1036x1036 image; second, targeted content recognition on native-resolution crops guided by the layout. The model uses a 675M NaViT…

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, et al.

GitHub stars: 77K
Citations: 86
Published: Sep 2025

Read summary View on GitHub

02

arXiv.org

VibeVoice Technical Report

VIBEVOICE is a novel model from Microsoft Research for synthesizing long-form, multi-speaker speech (up to 90 minutes, 4 speakers) using next-token diffusion. It introduces a causal speech tokenizer with a 3200x compression rate (7.5 Hz frame rate), which is 80 times more efficient than Encodec while maintaining comparable performance. The model uses a…

Zhiliang Peng, Jianwei Yu, Wenhui Wang, Yaoyao Chang, et al.

GitHub stars: 52K
Citations: 36
Published: Aug 2025

Read summary View on GitHub

03

arXiv.org

AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

AgentScope 1.0 is a developer-centric framework for building agentic applications, grounded in the ReAct paradigm. It provides foundational components (message, model, memory, tool) with unified interfaces and extensible modules, supporting multimodal messages, diverse LLM providers, and MCP integration. The framework includes agent-level infrastructure…

Dawei Gao, Zitao Li, Yuexiang Xie, Weirui Kuang, et al.

GitHub stars: 29K
Citations: 11
Published: Aug 2025

Read summary View on GitHub

04

arXiv.org

MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

MiniCPM-V 4.5 is an 8B-parameter multimodal large language model (MLLM) designed for high efficiency and strong performance. It introduces three core improvements: a unified 3D-Resampler architecture that compresses images and videos into compact token sequences (up to 16x for images and an additional 6x for videos), a unified learning paradigm for…

Tianyu Yu, Zefan Wang, Chongyi Wang, Fuwei Huang, et al.

GitHub stars: 26K
Citations: 124
Published: Sep 2025

Read summary View on GitHub

05

arXiv.org

MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction

MiniCPM-o 4.5 is a 9B-parameter open-source multimodal large language model (MLLM) designed for real-time full-duplex omni-modal interaction, enabling simultaneous perception and response. It introduces Omni-Flow, a unified streaming framework that aligns multimodal inputs and outputs along a shared temporal axis, converting turn-based interaction into a…

Junbo Cui, Bokai Xu, Chongyi Wang, Tianyu Yu, et al.

GitHub stars: 26K
Citations: 16
Published: Apr 2026

Read summary View on GitHub

06

DeepSeek

DeepSeek-OCR: Contexts Optical Compression

DeepSeek-OCR is a vision-language model that explores optical compression of long contexts by mapping text to images and decoding them back to text. It consists of DeepEncoder, a novel vision encoder with low activation and high compression, and a DeepSeek3B-MoE decoder. On the Fox benchmark, it achieves 97% OCR precision at compression ratios under 10x,…

Haoran Wei, Yaofeng Sun, Yukun Li

GitHub stars: 24K
Citations: 159
Published: Oct 2025

Read summary View on GitHub

07

arXiv.org

RAG-Anything: All-in-One RAG Framework

RAG-Anything is a unified framework for multimodal Retrieval-Augmented Generation (RAG) that addresses the limitation of existing text-only RAG systems in handling real-world documents containing text, images, tables, and equations. The framework introduces dual-graph construction, which builds a cross-modal knowledge graph for non-textual content and a…

Zirui Guo, Xubin Ren, Lingrui Xu, Jiahao Zhang, et al.

GitHub stars: 23K
Citations: 18
Published: Oct 2025

Read summary View on GitHub

08

Independent research

Unlimited OCR Works

Baidu's Unlimited OCR introduces Reference Sliding Window Attention (R-SWA) to enable one-shot long-horizon document parsing. R-SWA replaces all attention layers in the decoder of DeepSeek OCR, allowing each generated token to attend to all reference tokens (visual and prompt) and a causal sliding window of the previous 128 output tokens. This maintains a…

Youyang Yin, Huanhuan Liu, YY, Qunyi Xie, et al.

GitHub stars: 22K
Citations: 4
Published: Jun 2026

Read summary View on GitHub

09

arXiv.org

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

COLLEAGUE.SKILL is an open-source system that automatically distills heterogeneous traces of a person or role (e.g., work documents, chat logs, public interviews) into portable, inspectable, and correctable AI skill packages. The system generates a versioned package with two tracks: a capability track for practices and decision heuristics, and a bounded…

Tianyi Zhou, Dongrui Liu, Leitao Yuan, Jing Shao, et al.

GitHub stars: 21K
Citations: 3
Published: May 2026

Read summary View on GitHub

10

Qwen

WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent

WebWatcher is a multimodal deep research agent introduced by Alibaba's Tongyi Lab to address the limitations of text-centric web agents by integrating visual information and complex reasoning. It uses high-quality synthetic multimodal trajectories for cold-start training, multiple tools (web search, image search, webpage visit, code interpreter, OCR), and…

Xinyu Geng, Peng Xia, Zhen Zhang, Xinyu Wang, et al.

GitHub stars: 20K
Citations: 101
Published: Aug 2025

Read summary View on GitHub

11

Qwen

Scaling Agents via Continual Pre-training

The paper introduces Agentic Continual Pre-training (Agentic CPT), a new training stage between pre-training and post-training, to build agentic foundation models for deep research agents. The authors argue that post-training on general-purpose models creates optimization conflicts, as models must simultaneously learn agentic behaviors and align to expert…

Liangcai Su, Zhen Zhang, Guangyu Li, Zhuo Chen, et al.

GitHub stars: 20K
Citations: 41
Published: Sep 2025

Read summary View on GitHub

12

Qwen

Qwen3-VL Technical Report

Qwen3-VL is a state-of-the-art vision-language model family from the Qwen team, released on December 1, 2025. It supports interleaved contexts up to 256K tokens and comes in dense (2B/4B/8B/32B) and MoE (30B-A3B/235B-A22B) variants. Key architectural innovations include interleaved-MRoPE for balanced spatial-temporal encoding, DeepStack for multi-level ViT…

Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, et al.

GitHub stars: 20K
Citations: 1.8K
Published: Nov 2025

Read summary View on GitHub

13

arXiv.org

Agent Lightning: Train ANY AI Agents with Reinforcement Learning

Agent Lightning is a framework that enables reinforcement learning (RL) training of large language models (LLMs) for any AI agent, achieving complete decoupling between agent execution and training with almost zero code modifications. It formulates agent execution as a Markov decision process (MDP), defining a unified data interface that abstracts agent…

Xufang Luo, Yuge Zhang, Zhiyuan He, Zilong Wang, et al.

GitHub stars: 17K
Citations: 58
Published: Aug 2025

Read summary View on GitHub

14

Qwen

Qwen3-Coder-Next Technical Report

Qwen3-Coder-Next is an 80-billion-parameter open-weight language model with only 3 billion active parameters per forward pass, designed for coding agents. It is built on Qwen3-Next with hybrid attention and Mixture-of-Experts, and trained via a staged pipeline: continued pretraining on code and agent-centric data, supervised fine-tuning, and reinforcement…

Ruisheng Cao, Mouxiang Chen, Jiawei Chen, Zeyu Cui, et al.

GitHub stars: 17K
Citations: 54
Published: Feb 2026

Read summary View on GitHub

15

arXiv.org

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

SkillOpt is a text-space optimizer that treats an agent's skill document as trainable external state, using a separate optimizer model to propose bounded add/delete/replace edits based on scored rollouts. Edits are accepted only if they improve a held-out validation score, with controls like a textual learning-rate budget, rejected-edit buffer, and…

Yifan Yang, Ziyang Gong, Weiquan Huang, Qihao Yang, et al.

GitHub stars: 16K
Citations: 29
Published: May 2026

Read summary View on GitHub

16

arXiv.org

ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration

ARIS is an open-source research harness for autonomous ML research, built on the assumption that single-agent long-horizon tasks are unreliable. It uses cross-model adversarial collaboration: an executor model (e.g., Claude) drives progress while a reviewer from a different model family (e.g., GPT-5.4) critiques artifacts and requests revisions. The system…

Ruofeng Yang, Yongcan Li, Shuai Li

GitHub stars: 14K
Citations: 9
Published: May 2026

Read summary View on GitHub

17

arXiv.org

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

AutoResearchClaw is a multi-agent autonomous research pipeline that addresses three key challenges in scientific discovery: hypothesis quality, execution robustness, and experience accumulation. It integrates five mechanisms: structured multi-agent debate for hypothesis generation and result analysis, a self-healing executor with a Pivot/Refine loop,…

Jiaqi Liu, Shi Qiu, Mairui Li, Bingzhou Li, et al.

GitHub stars: 14K
Citations: 13
Published: May 2026

Read summary View on GitHub

18

Qwen

Qwen3-TTS Technical Report

The Qwen3-TTS technical report introduces a family of multilingual, controllable, robust, and streaming text-to-speech models. Trained on over 5 million hours of speech data across 10 languages, Qwen3-TTS supports 3-second voice cloning, description-based voice design, and fine-grained control. It uses a dual-track LM architecture with two tokenizers:…

Hangrui Hu, Xinfa Zhu, Ting He, Dake Guo, et al.

GitHub stars: 13K
Citations: 88
Published: Jan 2026

Read summary View on GitHub

19

arXiv.org

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Z-Image is a 6B-parameter image generation foundation model from Alibaba Group, built on a Scalable Single-Stream Diffusion Transformer (S3-DiT). It challenges the 'scale-at-all-costs' paradigm by optimizing data infrastructure, architecture, training, and inference. The full training workflow costs 314K H800 GPU hours (~$628K). Z-Image-Turbo, a distilled…

Z-Image Team, Huanqia Cai, Sihan Cao, Ruoyi Du, et al.

GitHub stars: 12K
Citations: 206
Published: Nov 2025

Read summary View on GitHub

20

arXiv.org

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

UI-TARS-2 is a native GUI-centered agent model developed by ByteDance Seed, designed to handle both structured computer-use tasks and dynamic game environments. It addresses challenges in data scalability, multi-turn reinforcement learning (RL), GUI-only operation limits, and environment stability through a systematic methodology: a data flywheel for…

Haoming Wang, Haoyang Zou, Huatong Song, Jiazhan Feng, et al.

GitHub stars: 11K
Citations: 163
Published: Sep 2025

Read summary View on GitHub

21

Meta AI

SAM 3: Segment Anything with Concepts

SAM 3 is a unified model for promptable concept segmentation (PCS) in images and videos, accepting noun phrases, image exemplars, or both as prompts to detect, segment, and track all matching instances. It decouples recognition and localization via a presence head, improving detection accuracy. A data engine with human and AI verifiers produced 4M unique…

Nicolas Carion, Laura Gustafson, Yuan-Ting Hu, Shoubhik Debnath, et al.

GitHub stars: 11K
Citations: 711
Published: Nov 2025

Read summary View on GitHub

22

Meta AI

DINOv3

DINOv3 is a self-supervised vision foundation model that scales to 7B parameters, trained on a curated dataset of 1.689 billion images (LVD-1689M) from Instagram, combined with ImageNet-1k. The model uses a ViT architecture with RoPE embeddings and constant hyperparameter schedules. A key contribution is Gram anchoring, a regularization technique that…

Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, et al.

GitHub stars: 11K
Citations: 1.2K
Published: Aug 2025

Read summary View on GitHub

23

arXiv.org

Mobile-Agent-v3: Fundamental Agents for GUI Automation

The paper introduces GUI-Owl, a foundational GUI agent model built on Qwen2.5-VL, and Mobile-Agent-v3, a multi-agent framework. GUI-Owl-7B achieves state-of-the-art scores among open-source models, including 66.4 on AndroidWorld and 34.9 on OSWorld-Verified, while Mobile-Agent-v3 further improves these to 73.3 and 37.7, respectively. Key innovations…

Jiabo Ye, Xi Zhang, Haiyang Xu, Haowei Liu, et al.

GitHub stars: 9K
Citations: 150
Published: Aug 2025

Read summary View on GitHub

24

NVIDIA

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer

SANA-Video is a small diffusion model for efficient, high-resolution (up to 720×1280) and minute-long video generation, deployable on RTX 5090 GPUs. It uses a Linear DiT with linear attention (O(N) complexity) and a constant-memory KV cache for block linear attention, enabling long videos with fixed memory. Training cost is 12 days on 64 H100 GPUs (1% of…

Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, et al.

GitHub stars: 8.7K
Citations: 82
Published: Sep 2025

Read summary View on GitHub

25

arXiv.org

LTX-2: Efficient Joint Audio-Visual Foundation Model

LTX-2 is an open-source text-to-audio+video (T2AV) foundation model that jointly generates synchronized video and audio from text. It uses an asymmetric dual-stream transformer with a 14B-parameter video stream and a 5B-parameter audio stream, connected via bidirectional cross-attention layers with temporal positional embeddings and cross-modality AdaLN.…

Yoav HaCohen, Benny Brazowski, Nisan Chiprut, Yaki Bitterman, et al.

GitHub stars: 8.5K
Citations: 135
Published: Jan 2026

Read summary View on GitHub

26

arXiv.org

MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

MiroThinker v1.0 is an open-source research agent that introduces interaction scaling as a third performance dimension, alongside model size and context length. It trains models via reinforcement learning to handle deeper and more frequent agent–environment interactions, using a 256K context window and up to 600 tool calls per task. The 72B variant…

MiroMind Team, Song Bai, Lidong Bing, Carson Chen, et al.

GitHub stars: 8.4K
Citations: 62
Published: Nov 2025

Read summary View on GitHub

27

Qwen

Qwen-Image Technical Report

Qwen-Image is a new image generation foundation model from the Qwen team, designed to excel in complex text rendering and precise image editing. It uses a comprehensive data pipeline and a progressive curriculum learning strategy to enhance text rendering, especially for Chinese. For editing, it employs a multi-task training paradigm with dual-encoding…

Chenfei Wu, Jiahao Li, Jingren Zhou, Junyang Lin, et al.

GitHub stars: 8.2K
Citations: 875
Published: Aug 2025

Read summary View on GitHub

28

Moonshot AI

Kimi K3: Open Frontier Intelligence

Kimi K3 is a 2.8-trillion-parameter Mixture-of-Experts model with 104 billion activated parameters, native vision, and a 1-million-token context window. It uses Kimi Delta Attention, Attention Residuals, and Stable LatentMoE (16 of 896 routed experts active per token), achieving about 2.5× scaling efficiency over Kimi K2. Post-training includes…

Kimi Team, Tongtong Bai, Yifan Bai, Yiping Bao, et al.

GitHub stars: 8.1K
Citations: 2
Published: Jul 2026

Read summary View on GitHub

29

Meta AI

SAM 3D: 3Dfy Anything in Images

SAM 3D is a generative model for 3D object reconstruction from a single image, predicting geometry, texture, and layout. It excels in natural images with occlusion and clutter, using a human- and model-in-the-loop pipeline to create large-scale 3D annotation data. The model uses a multi-stage training framework: synthetic pretraining on 2.7M meshes…

SAM 3D Team, Xingyu Chen, Fu-Jen Chu, Pierre Gleize, et al.

GitHub stars: 7.2K
Citations: 197
Published: Nov 2025

Read summary View on GitHub

30

arXiv.org

DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI

DataFlow is a unified, LLM-driven framework for data preparation in the era of data-centric AI, addressing the fragmentation of ad-hoc scripts and workflows. It provides a PyTorch-style API with nearly 200 reusable operators and six domain-general pipelines (text, math, code, Text-to-SQL, agentic RAG, knowledge extraction). The framework includes a global…

Hao Liang, Xiaochen Ma, Zhou Liu, Zhen Hao Wong, et al.

GitHub stars: 7.2K
Citations: 19
Published: Dec 2025

Read summary View on GitHub

31

Z.ai / GLM

GLM-5: from Vibe Coding to Agentic Engineering

GLM-5, developed by Zhipu AI and Tsinghua University, is a next-generation foundation model that shifts from vibe coding to agentic engineering. It builds on the ARC (agentic, reasoning, coding) capabilities of its predecessor, GLM-4.7, and introduces DeepSeek Sparse Attention (DSA) to reduce training and inference costs while maintaining long-context…

GLM-5-Team, :, Aohan Zeng, Xin Lv, et al.

GitHub stars: 6.9K
Citations: 295
Published: Feb 2026

Read summary View on GitHub

32

Google DeepMind

PaperBanana: Automating Academic Illustration for AI Scientists

PaperBanana is an agentic framework that automates the generation of publication-ready academic illustrations, such as methodology diagrams and statistical plots. It uses five specialized agents—Retriever, Planner, Stylist, Visualizer, and Critic—powered by VLMs and image generation models. The Retriever selects relevant reference examples, the Planner…

Dawei Zhu, Rui Meng, Yale Song, Xiyu Wei, et al.

GitHub stars: 6.9K
Citations: 19
Published: Jan 2026

Read summary View on GitHub

33

DeepSeek

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

DSpark is a speculative decoding framework that combines a semi-autoregressive draft model with confidence-scheduled verification to accelerate LLM inference. The draft model uses a parallel backbone (based on DFlash) to generate tokens in one pass, followed by a lightweight sequential head (Markov or RNN) to model inter-token dependencies, mitigating…

Xin Cheng, Xingkai Yu, Chenze Shao, Jiashi Li, et al.

GitHub stars: 6.9K
Citations: 12
Published: Jul 2026

Read summary View on GitHub

34

arXiv (Cornell University)

Less is More: Recursive Reasoning with Tiny Networks

The paper introduces Tiny Recursive Model (TRM), a simplified recursive reasoning approach that outperforms the Hierarchical Reasoning Model (HRM) and many large language models on hard puzzle tasks. TRM uses a single tiny 2-layer network (7M parameters) that recursively improves its answer, eliminating the need for fixed-point theorems, hierarchical…

Alexia Jolicoeur-Martineau

GitHub stars: 6.6K
Citations: 4
Published: Oct 2025

Read summary View on GitHub

35

arXiv.org

Depth Anything 3: Recovering the Visual Space from Any Views

Depth Anything 3 (DA3) is a model that predicts spatially consistent geometry from any number of images, with or without known camera poses. It uses a single plain transformer (e.g., vanilla DINOv2) as backbone, with an input-adaptive cross-view self-attention mechanism and a dual-DPT head that jointly outputs depth and ray maps. A depth-ray representation…

Haotong Lin, Sili Chen, Junhao Liew, Donny Y. Chen, et al.

GitHub stars: 6.1K
Citations: 499
Published: Nov 2025

Read summary View on GitHub

36

arXiv.org

OpenClaw-RL: Train Any Agent Simply by Talking

OpenClaw-RL is a framework that enables online reinforcement learning for LLM-based agents by extracting training signals from the next-state signals that follow each agent action (e.g., user replies, tool outputs, GUI changes). It uses a server–client architecture where the RL server hosts the policy behind an inference API and user terminals stream…

Yinjie Wang, Xuyang Chen, Xiaolong Jin, Mengdi Wang, et al.

GitHub stars: 5.6K
Citations: 66
Published: Mar 2026

Read summary View on GitHub

37

arXiv.org

DFlash: Block Diffusion for Flash Speculative Decoding

DFlash is a speculative decoding framework that uses a lightweight block diffusion model for parallel drafting, addressing the sequential bottleneck of autoregressive LLM decoding. It extracts hidden features from the target LLM and injects them into every draft layer's KV cache, conditioning the draft model to predict future token blocks in parallel. This…

Jian Chen, Yesheng Liang, Zhijian Liu

GitHub stars: 5.6K
Citations: 63
Published: Feb 2026

Read summary View on GitHub

38

arXiv.org

Recursive Language Models

The paper introduces Recursive Language Models (RLMs), an inference-time framework that treats arbitrarily long prompts as part of an external environment, allowing an LLM to programmatically examine, decompose, and recursively call itself over prompt snippets. RLMs use a REPL environment where the prompt is stored as a variable, and the model writes code…

Alex L. Zhang, Tim Kraska, Omar Khattab

GitHub stars: 5.4K
Citations: 64
Published: Dec 2025

Read summary View on GitHub

39

arXiv.org

LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

The paper introduces LLaVA-Critic-R1, a multimodal critic model trained via reinforcement learning (RL) on preference-labeled critic data, which surprisingly also becomes a strong policy model. By reformulating critic data into verifiable tasks and using GRPO with preference and format rewards, the model improves over its base (Qwen-2.5-VL-7B) by +5.7% on…

Xiyao Wang, Chunyuan Li, Jianwei Yang, Kai Zhang, et al.

GitHub stars: 4.7K
Citations: 30
Published: Aug 2025

Read summary View on GitHub

40

arXiv.org

Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization

Youtu-Agent is a modular framework addressing high configuration costs and static capabilities in LLM agents. It decouples environments, toolkits, and agents via a YAML-based system, enabling automated generation through a deterministic Workflow mode and a flexible Meta-Agent mode that synthesizes tools, prompts, and configurations. For continuous…

Yuchen Shi, Yuzheng Cai, Siqi Cai, Zihan Xu, et al.

GitHub stars: 4.6K
Citations: 5
Published: Dec 2025

Read summary View on GitHub

41

DeepSeek

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

The paper introduces Engram, a conditional memory module that augments Mixture-of-Experts (MoE) large language models with static N-gram lookup tables, providing a complementary sparsity axis to conditional computation. Engram uses hashed N-gram embeddings with tokenizer compression, multi-head hashing, and context-aware gating to retrieve static knowledge…

Xin Cheng, Rui Tian, Wangding Zeng, Damai Dai, et al.

GitHub stars: 4.6K
Citations: 63
Published: Jan 2026

Read summary View on GitHub

42

arXiv.org

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

SenseNova-U1 is a native unified multimodal model built on the NEO-unify architecture, designed to overcome the traditional divide between understanding and generation. It operates directly on raw pixels and text, eliminating the need for pretrained vision encoders (VEs) and variational autoencoders (VAEs). The model uses a near-lossless visual interface…

Haiwen Diao, Penghao Wu, Hanming Deng, Jiahao Wang, et al.

GitHub stars: 4.5K
Citations: 12
Published: May 2026

Read summary View on GitHub

43

arXiv.org

WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning

WIDESEEK-R1 explores width scaling for broad information seeking using a lead-agent–subagent framework trained via multi-agent reinforcement learning (MARL). The system uses a shared LLM with isolated contexts and specialized tools, where the lead agent decomposes tasks and delegates subtasks to parallel subagents. Training on a curated 20k dataset of…

Zelai Xu, Zhexuan Xu, Ruize Zhang, Chunyang Zhu, et al.

GitHub stars: 4.5K
Citations: 6
Published: Feb 2026

Read summary View on GitHub

44

arXiv.org

DeepAnalyze: Agentic Large Language Models for Autonomous Data Science

DeepAnalyze-8B is the first agentic large language model designed for autonomous data science, capable of completing the entire pipeline from raw data sources to analyst-grade research reports. It addresses the limitations of previous workflow-based agents by enabling autonomous orchestration and adaptive optimization through a curriculum-based agentic…

Shaolei Zhang, Ju Fan, Meihao Fan, Guoliang Li, et al.

GitHub stars: 4.4K
Citations: 43
Published: Oct 2025

Read summary View on GitHub

45

Z.ai / GLM

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

GLM-4.5 is an open-source Mixture-of-Experts (MoE) large language model with 355B total and 32B activated parameters, developed by Zhipu AI and Tsinghua University. It features a hybrid reasoning method supporting both thinking and direct response modes. Trained on 23T tokens with multi-stage pre-training and mid-training (including repo-level code,…

GLM-4. 5 Team, :, Aohan Zeng, Xin Lv, et al.

GitHub stars: 4.4K
Citations: 409
Published: Aug 2025

Read summary View on GitHub

46

arXiv.org

Advancing Open-source World Models

LingBot-World is an open-source world simulator built from video generation, offering high-fidelity dynamics across diverse environments, minute-level long-term memory, and real-time interactivity with sub-second latency. It uses a three-stage training pipeline: pre-training on a 14B-parameter Wan2.2 model, middle-training with a mixture-of-experts (MoE)…

Robbyant Team, Zelin Gao, Qiuyu Wang, Yanhong Zeng, et al.

GitHub stars: 4.3K
Citations: 87
Published: Jan 2026

Read summary View on GitHub

47

Qwen

Qwen3-Omni Technical Report

Qwen3-Omni is a single multimodal model that achieves state-of-the-art performance across text, image, audio, and video without degradation relative to single-modal counterparts. It matches the performance of same-sized Qwen single-modal models and excels on audio tasks, achieving open-source SOTA on 32 of 36 audio benchmarks and overall SOTA on 22,…

Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, et al.

GitHub stars: 3.9K
Citations: 405
Published: Sep 2025

Read summary View on GitHub

48

arXiv.org

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

TurboDiffusion is a video generation acceleration framework that achieves 100–200× end-to-end speedup while maintaining video quality. It combines four main techniques: low-bit SageAttention for attention acceleration, Sparse-Linear Attention (SLA) for sparse attention, rCM for step distillation, and W8A8 quantization for linear layers. Training involves…

Jintao Zhang, Kaiwen Zheng, Kai Jiang, Haoxu Wang, et al.

GitHub stars: 3.6K
Citations: 28
Published: Dec 2025

Read summary View on GitHub

49

arXiv.org

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

MetaClaw is a continual meta-learning framework that enables deployed LLM agents to evolve through two complementary mechanisms: skill-driven fast adaptation and opportunistic policy optimization. Skill-driven fast adaptation analyzes failure trajectories to synthesize new behavioral instructions, which are immediately injected into the agent's prompt…

Peng Xia, Jianwen Chen, Xinyu Yang, Haoqin Tu, et al.

GitHub stars: 3.5K
Citations: 20
Published: Mar 2026

Read summary View on GitHub

50

Moonshot AI

Attention Residuals

The paper proposes Attention Residuals (AttnRes), replacing fixed unit-weight residual connections in LLMs with learned, input-dependent softmax attention over preceding layer outputs. This addresses PreNorm dilution, where hidden-state magnitudes grow with depth, diluting layer contributions. A scalable variant, Block AttnRes, partitions layers into…

Kimi Team, Guangyu Chen, Yu Zhang, Jianlin Su, et al.

GitHub stars: 3.5K
Citations: 42
Published: Mar 2026

Read summary View on GitHub

51

arXiv.org

The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain

The paper introduces Dragon Hatchling (BDH), a new Large Language Model architecture based on a scale-free, biologically inspired network of n locally-interacting neuron particles. BDH couples strong theoretical foundations and inherent interpretability without sacrificing Transformer-like performance. It is a practical, performant attention-based state…

Adrian Kosowski, Przemysław Uznański, Jan Chorowski, Zuzanna Stamirowska, et al.

GitHub stars: 3.4K
Citations: 5
Published: Sep 2025

Read summary View on GitHub

52

Qwen

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

This technical report introduces the Agentic Learning Ecosystem (ALE), a full-stack infrastructure for developing agentic LLMs, and ROME, an open-source agent model trained within it. ALE comprises three components: ROLL, a scalable RL training framework; ROCK, a sandboxed environment execution engine; and iFlow CLI, an agent framework for context…

Weixun Wang, XiaoXiao Xu, Wanhe An, Fangwen Dai, et al.

GitHub stars: 3.4K
Citations: 23
Published: Dec 2025

Read summary View on GitHub

53

DeepSeek

DeepSeek-OCR 2: Visual Causal Flow

DeepSeek-OCR 2 introduces DeepEncoder V2, a novel vision encoder that replaces the CLIP component with a compact LLM (Qwen2-0.5B) to enable causal reordering of visual tokens, mimicking human visual scanning. The encoder uses a dual attention mask: bidirectional for visual tokens and causal for learnable query tokens, allowing queries to attend to all…

Haoran Wei, Yaofeng Sun, Yukun Li

GitHub stars: 3.2K
Citations: 53
Published: Jan 2026

Read summary View on GitHub

54

arXiv.org

OpenGame: Open Agentic Coding for Games

OpenGame is an open-source agentic framework for end-to-end web game creation from natural-language specifications. It introduces Game Skill, comprising a Template Skill that evolves a library of project skeletons and a Debug Skill that maintains a living protocol of verified fixes, to address cross-file inconsistencies and integration errors. The…

Yilei Jiang, Jinyuan Hu, Qianyin Xiao, Yaozhi Zheng, et al.

GitHub stars: 2.8K
Citations: 5
Published: Apr 2026

Read summary View on GitHub

55

arXiv.org

RAGEN-2: Reasoning Collapse in Agentic RL

RAGEN-2 identifies a failure mode in multi-turn LLM agent reinforcement learning called template collapse, where reasoning appears diverse within inputs but becomes input-agnostic across inputs, invisible to entropy-based metrics. The authors decompose reasoning quality into within-input diversity (conditional entropy) and cross-input distinguishability…

Zihan Wang, Chi Gui, Xing Jin, Qineng Wang, et al.

GitHub stars: 2.8K
Citations: 10
Published: Apr 2026

Read summary View on GitHub

56

arXiv.org

Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

The paper introduces Memento, a learning paradigm for LLM agents that enables continual adaptation without fine-tuning the underlying LLM. It formalizes a Memory-augmented Markov Decision Process (M-MDP) with a neural case-selection policy, storing past experiences in an episodic case bank. The policy is updated via online soft Q-learning, with retrieval…

Huichi Zhou, Yihang Chen, Siyuan Guo, Xue Yan, et al.

GitHub stars: 2.6K
Citations: 87
Published: Aug 2025

Read summary View on GitHub

57

NVIDIA

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

LongLive-2.0 is an NVFP4-based parallel infrastructure for long video generation, co-designing training and inference. For training, it introduces Balanced SP, a sequence-parallel autoregressive (AR) training method that pairs clean-history and noisy-target temporal chunks on each GPU, enabling a natural teacher-forcing mask and SP-aware chunked VAE…

Yukang Chen, Luozhou Wang, Wei Huang, Shuai Yang, et al.

GitHub stars: 2.5K
Citations: 11
Published: May 2026

Read summary View on GitHub

58

arXiv.org

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

HY-World 2.0 is an open-source multi-modal world model framework that unifies 3D world generation and reconstruction. For sparse inputs (text or single-view images), it generates navigable 3D Gaussian Splatting (3DGS) scenes via a four-stage pipeline: panorama generation (HY-Pano 2.0), trajectory planning (WorldNav), world expansion (WorldStereo 2.0), and…

Team HY-World, Chenjie Cao, Xuhui Zuo, Zhenwei Wang, et al.

GitHub stars: 2.5K
Citations: 19
Published: Apr 2026

Read summary View on GitHub

59

arXiv (Cornell University)

Back to Basics: Let Denoising Generative Models Denoise

The paper argues that denoising diffusion models should directly predict clean images (x-prediction) rather than noise (epsilon-prediction) or velocity (v-prediction), as natural data lies on a low-dimensional manifold while noised quantities do not. The authors propose 'Just image Transformers' (JiT), a plain Vision Transformer applied to large pixel…

Tianhong Li, Kaiming He

GitHub stars: 2.5K
Citations: 4
Published: Nov 2025

Read summary View on GitHub

60

arXiv.org

A Survey of Reinforcement Learning for Large Reasoning Models

This survey reviews recent advances in Reinforcement Learning (RL) for Large Reasoning Models (LRMs), focusing on how RL transforms LLMs into LRMs, particularly since DeepSeek-R1. It covers foundational components: reward design (verifiable, generative, dense, unsupervised, and shaping), policy optimization (critic-based, critic-free, off-policy, and…

Kaiyan Zhang, Yuxin Zuo, Bingxiang He, Youbang Sun, et al.

GitHub stars: 2.5K
Citations: 161
Published: Sep 2025

Read summary View on GitHub

61

arXiv.org

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

This survey reviews the emerging paradigm of self-evolving AI agents, which aim to bridge static foundation models with lifelong adaptability. It introduces a unified framework with four components: system inputs, agent system, environment, and optimizers, and proposes 'Three Laws' (Endure, Excel, Evolve) to guide safe and effective evolution. The survey…

Jinyuan Fang, Yanwen Peng, Xi Zhang, Yingxu Wang, et al.

GitHub stars: 2.4K
Citations: 154
Published: Aug 2025

Read summary View on GitHub

62

arXiv.org

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

SkillClaw is a framework for collective skill evolution in multi-user LLM agent ecosystems, addressing the problem of static skills that do not improve with experience. It aggregates interaction trajectories from multiple users, groups them by referenced skills, and uses an agentic evolver to refine existing skills, create new ones, or skip updates based…

Ziyu Ma, Shidong Yang, Yuxiang Ji, Xucong Wang, et al.

GitHub stars: 2.4K
Citations: 48
Published: Apr 2026

Read summary View on GitHub

63

arXiv.org

Paper2Video: Automatic Video Generation from Scientific Papers

The paper introduces Paper2Video, the first benchmark of 101 research papers paired with author-created presentation videos, slides, and speaker metadata, along with four evaluation metrics: Meta Similarity, PresentArena, PresentQuiz, and IP Memory. It also proposes PaperTalker, a multi-agent framework that generates presentation videos from papers,…

Zeyu Zhu, Kevin Qinghong Lin, Mike Zheng Shou

GitHub stars: 2.3K
Citations: 24
Published: Oct 2025

Read summary View on GitHub

64

arXiv.org

Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

Live Avatar is an algorithm-system co-designed framework enabling real-time, streaming, and infinite-length audio-driven avatar generation using a 14-billion-parameter diffusion model. It addresses two key challenges: long-horizon consistency and the real-time-fidelity trade-off. The algorithm side uses a two-stage pipeline (Diffusion Forcing pretraining…

Yubo Huang, Hailong Guo, Fangtai Wu, Weiqiang Wang, et al.

GitHub stars: 2.3K
Citations: 0
Published: Dec 2025

Read summary View on GitHub

65

arXiv.org

Memory in the Age of AI Agents

This survey provides a comprehensive overview of memory systems for foundation model-based AI agents, addressing the fragmentation in the field by proposing a unified taxonomy based on forms, functions, and dynamics. It defines agent memory, distinguishing it from LLM memory, RAG, and context engineering. The survey categorizes memory forms into…

Yuyang Hu, Shichun Liu, Yanwei Yue, Guibin Zhang, et al.

GitHub stars: 2.3K
Citations: 232
Published: Dec 2025

Read summary View on GitHub

66

Moonshot AI

Kimi K2.5: Visual Agentic Intelligence

Kimi K2.5 is an open-source multimodal agentic model that jointly optimizes text and vision through techniques including joint pre-training, zero-vision SFT, and joint reinforcement learning. It introduces Agent Swarm, a parallel agent orchestration framework using Parallel-Agent Reinforcement Learning (PARL) to decompose tasks into heterogeneous…

Kimi Team, Tongtong Bai, Yifan Bai, Yiping Bao, et al.

GitHub stars: 2.3K
Citations: 313
Published: Feb 2026

Read summary View on GitHub

67

AAAI Conference on Artificial Intelligence

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

VLA-Adapter is a novel paradigm for Vision-Language-Action (VLA) models that reduces reliance on large-scale VLMs and extensive pre-training. It systematically analyzes which vision-language (VL) conditions are essential for bridging perception to action, finding that middle-layer raw features and deep-layer ActionQuery features are most effective, and…

Yihao Wang, Pengxiang Ding, Lingxiao Li, Can Cui, et al.

GitHub stars: 2.3K
Citations: 129
Published: Sep 2025

Read summary View on GitHub

68

Independent research

ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes

ResearchStudio-Idea is a suite of three skills for evidence-grounded research ideation in machine learning. It includes Paper-Search for multi-source literature grounding, Scoop-Check for prior-art collision checking, and IdeaSpark, an end-to-end skill that composes evidence grounding, pattern-guided generation, collision retrieval, audit, and idea-card…

Qihao Zhao, Yangyu Huang, Yalun Dai, Lingao Xiao, et al.

GitHub stars: 2.1K
Citations: 1
Published: Jul 2026

Read summary View on GitHub

69

arXiv.org

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

daVinci-MagiHuman is an open-source audio-video generative foundation model for human-centric generation, jointly producing synchronized video and audio via a single-stream Transformer that processes text, video, and audio in a unified token sequence using self-attention only. This design avoids multi-stream complexity and supports multilingual generation…

SII-GAIR, Sand. ai, :, Ethan Chern, et al.

GitHub stars: 2.1K
Citations: 12
Published: Mar 2026

Read summary View on GitHub

70

Independent research

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Step 3.5 Flash is a sparse Mixture-of-Experts (MoE) language model with 196B total parameters and 11B active parameters, designed to deliver frontier-level agentic intelligence with high computational efficiency. Its architecture uses a 3:1 interleaved Sliding Window/Full Attention layout, head-wise gated attention, and Multi-Token Prediction (MTP-3) to…

Ailin Huang, Ang Li, Aobo Kong, Bin Wang, et al.

GitHub stars: 2.1K
Citations: 25
Published: Feb 2026

Read summary View on GitHub

71

Qwen

Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

Qwen-Image-Layered is an end-to-end diffusion model that decomposes a single RGB image into multiple semantically disentangled RGBA layers, enabling consistent image editing where each layer can be independently manipulated. The model introduces three key components: an RGBA-VAE that unifies latent representations for RGB and RGBA images, a VLD-MMDiT…

Shengming Yin, Zekai Zhang, Zecheng Tang, Kaiyuan Gao, et al.

GitHub stars: 2.1K
Citations: 24
Published: Dec 2025

Read summary View on GitHub

72

arXiv.org

DreamOmni2: Multimodal Instruction-based Editing and Generation

DreamOmni2 introduces two new tasks: multimodal instruction-based editing and generation, which accept both text and image instructions and support concrete objects as well as abstract attributes (e.g., texture, pose, style). The authors propose a three-stage data synthesis pipeline: (1) a feature mixing scheme in attention to generate paired images…

Bin Xia, Bohao Peng, Yuechen Zhang, Junjia Huang, et al.

GitHub stars: 2K
Citations: 34
Published: Oct 2025

Read summary View on GitHub

73

arXiv.org

Helios: Real Real-Time Long Video Generation Model

Helios is a 14B autoregressive diffusion model for video generation that achieves 19.5 FPS on a single NVIDIA H100 GPU, enabling minute-scale generation without common anti-drifting heuristics (e.g., self-forcing, error-banks) or standard acceleration techniques (e.g., KV-cache, quantization). It unifies T2V, I2V, and V2V tasks via a unified input…

Shenghai Yuan, Yuanyang Yin, Zongjian Li, Xinwei Huang, et al.

GitHub stars: 2K
Citations: 33
Published: Mar 2026

Read summary View on GitHub

74

arXiv.org

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use

The paper introduces AGENTFLOW, a trainable agentic framework for planning and tool use that coordinates four specialized modules—planner, executor, verifier, and generator—through an evolving memory. Unlike monolithic tool-integrated reasoning models, AGENTFLOW optimizes its planner on-policy within the multi-turn loop. To address long-horizon credit…

Zhuofeng Li, Haoxiang Zhang, Seungju Han, Sheng Liu, et al.

GitHub stars: 2K
Citations: 51
Published: Oct 2025

Read summary View on GitHub

75

arXiv.org

Diffusion Transformers with Representation Autoencoders

The paper introduces Representation Autoencoders (RAEs), which replace the traditional VAE in latent diffusion models with a frozen pretrained representation encoder (e.g., DINOv2, SigLIP2, MAE) paired with a trained decoder. RAEs provide both high-quality reconstructions and semantically rich latent spaces, outperforming SD-VAE in reconstruction FID…

Boyang Zheng, Nanye Ma, Shengbang Tong, Saining Xie

GitHub stars: 2K
Citations: 221
Published: Oct 2025

Read summary View on GitHub

76

arXiv.org

VOID: Video Object and Interaction Deletion

VOID is a video object removal framework that generates physically plausible counterfactual videos when an object is removed, addressing limitations of existing methods that only handle photometric effects like shadows. It uses a two-pass approach: first, a video diffusion model (CogVideoX) synthesizes a counterfactual trajectory guided by a quadmask,…

Saman Motamed, William Harvey, Benjamin Klein, Luc Van Gool, et al.

GitHub stars: 2K
Citations: 4
Published: Apr 2026

Read summary View on GitHub

77

arXiv.org

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

DataFlex is a unified data-centric dynamic training framework built on LLaMA-Factory, designed to treat data as a first-class optimization variable. It integrates three paradigms—data selection, data mixture optimization, and data reweighting—through modular trainer abstractions (Select, Mix, Weight Trainers) and pluggable components (selectors, mixers,…

Hao Liang, Zhengyang Zhao, Meiyi Qiang, Mingrui Chen, et al.

GitHub stars: 1.9K
Citations: 3
Published: Mar 2026

Read summary View on GitHub

78

arXiv.org

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

This survey formalizes Agentic Reinforcement Learning (Agentic RL), a paradigm where LLMs are treated as learnable policies in sequential decision-making loops, contrasting it with conventional single-step LLM RL. It proposes a twofold taxonomy: one based on core agentic capabilities (planning, tool use, memory, reasoning, self-improvement, perception) and…

Guibin Zhang, Hejia Geng, Xiaohang Yu, Zhenfei Yin, et al.

GitHub stars: 1.9K
Citations: 182
Published: Sep 2025

Read summary View on GitHub

79

arXiv.org

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

SimpleVLA-RL is an efficient reinforcement learning (RL) framework for Vision-Language-Action (VLA) models, built on veRL, that addresses data scarcity and poor generalization in robotic manipulation. It uses interactive trajectory sampling, parallel multi-environment rendering, and outcome-based rewards (1 for success, 0 for failure) with GRPO, enhanced…

Haozhan Li, Yuxin Zuo, Jiale Yu, Yuhao Zhang, et al.

GitHub stars: 1.8K
Citations: 130
Published: Sep 2025

Read summary View on GitHub

80

arXiv.org

HRM-Text: Efficient Pretraining Beyond Scaling

HRM-Text introduces a Hierarchical Recurrent Model (HRM) that decouples computation into slow strategic and fast execution layers, inspired by biological multi-timescale processing. Trained from scratch on only 40B unique tokens (60B total with repetition) and a $1,500 budget, a 1B-parameter model achieves 60.7% on MMLU, 81.9% on ARC-C, 82.2% on DROP,…

Guan Wang, Changling Liu, Chenyu Wang, Cai Zhou, et al.

GitHub stars: 1.8K
Citations: 3
Published: May 2026

Read summary View on GitHub

81

Independent research

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

ABot-World-0 is an action-conditioned video world model for real-time, long-horizon closed-loop interaction, deployable on a single NVIDIA RTX 5090 GPU. It uses raw keyboard inputs as a unified control interface for both scene roaming and third-person character control, with reference-character memory for identity consistency. The model is trained on…

Fan Jiang, Zhaoxu Sun, Mengchao Wang, Ziyu Zhu, et al.

GitHub stars: 1.8K
Citations: 0
Published: Jul 2026

Read summary View on GitHub

82

Independent research

JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence

JoyAI-VL-Interaction introduces a paradigm shift from turn-based to proactive, streaming interaction for vision-language models. The authors release an 8B-scale, vision-first model that continuously watches live video and decides each second to stay silent, respond, or delegate complex tasks to a background model. Built on JoyAI-VL 1.0 with AdaCodec for…

Dingyu Yao, Junhao Zhou, Chenxu Yang, Chuanyu Qin, et al.

GitHub stars: 1.7K
Citations: 2
Published: Jun 2026

Read summary View on GitHub

83

DeepSeek

DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning

DeepSeekMath-V2 is a large language model for natural-language theorem proving, built on DeepSeek-V3.2-Exp-Base, that achieves self-verifiable mathematical reasoning. The authors argue that final-answer rewards are insufficient because correct answers do not guarantee correct reasoning and are inapplicable to theorem proving. They train a verifier using…

Zhihong Shao, Yuxiang Luo, Chengda Lu, Z. Z. Ren, et al.

GitHub stars: 1.6K
Citations: 60
Published: Nov 2025

Read summary View on GitHub

84

arXiv.org

WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

WorldPlay is a real-time interactive world model that generates streaming 720p video at 24 FPS while maintaining long-term geometric consistency. It addresses the trade-off between speed and memory in existing methods. The model uses three key components: Dual Action Representation combining discrete keys and continuous camera poses for robust control;…

Wenqiang Sun, Haiyu Zhang, Haoyuan Wang, Junta Wu, et al.

GitHub stars: 1.6K
Citations: 97
Published: Dec 2025

Read summary View on GitHub

85

Moonshot AI

Kimi Linear: An Expressive, Efficient Attention Architecture

Kimi Linear is a hybrid linear attention architecture that outperforms full attention under fair comparisons across short-context, long-context, and reinforcement learning (RL) scaling regimes. Its core, Kimi Delta Attention (KDA), extends Gated DeltaNet with a finer-grained, channel-wise gating mechanism, improving memory control and enabling efficient…

Kimi Team, Yu Zhang, Zongyu Lin, Xingcheng Yao, et al.

GitHub stars: 1.6K
Citations: 116
Published: Oct 2025

Read summary View on GitHub

86

arXiv.org

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

This technical report from Sina Weibo Inc. introduces VibeThinker-1.5B, a 1.5B-parameter dense model that challenges the assumption that small models lack robust reasoning capabilities. Developed with a post-training methodology based on the 'Spectrum-to-Signal Principle (SSP)', the approach decouples SFT and RL objectives: the SFT 'Spectrum Phase' uses…

Sen Xu, Yi Zhou, Wei Wang, Jixin Min, et al.

GitHub stars: 1.5K
Citations: 8
Published: Nov 2025

Read summary View on GitHub

87

Independent research

VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models

VibeThinker-3B is a 3B-parameter dense model from Sina Weibo Inc. that achieves frontier-level performance on verifiable reasoning tasks, matching or exceeding much larger models. Built on Qwen2.5-Coder-3B, it uses a post-training pipeline with curriculum SFT, multi-domain RL (math, code, STEM), Long2Short Math RL for efficiency, offline self-distillation,…

Sen Xu, Shixi Liu, Wei Wang, Jixin Min, et al.

GitHub stars: 1.5K
Citations: 1
Published: Jun 2026

Read summary View on GitHub

88

arXiv.org

Emu3.5: Native Multimodal Models are World Learners

Emu3.5 is a large-scale multimodal world model from BAAI that natively predicts the next state across vision and language. It is pre-trained end-to-end with a unified next-token prediction objective on over 10 trillion tokens from interleaved vision-language data, primarily derived from internet videos. The model accepts and generates interleaved…

Yufeng Cui, Honghao Chen, Haoge Deng, Xu Huang, et al.

GitHub stars: 1.5K
Citations: 109
Published: Oct 2025

Read summary View on GitHub

89

arXiv.org

Memento-Skills: Let Agents Design Agents

Memento-Skills is a generalist LLM agent system that functions as an agent-designing agent, autonomously constructing, adapting, and improving task-specific agents through experience. It uses a memory-based reinforcement learning framework with stateful prompts, where reusable skills stored as structured markdown files serve as persistent, evolving memory.…

Huichi Zhou, Siyuan Guo, Anjie Liu, Zhongwei Yu, et al.

GitHub stars: 1.5K
Citations: 39
Published: Mar 2026

Read summary View on GitHub

90

arXiv.org

Detect Anything via Next Point Prediction

Rex-Omni is a 3B-parameter multimodal large language model (MLLM) that unifies object detection and other visual perception tasks under a next-point prediction framework. It uses quantized relative coordinates represented by 1,000 special tokens, reducing token usage per bounding box to four. Training combines supervised fine-tuning on 22 million samples…

Qing Jiang, Junan Huo, Xingyu Chen, Yuda Xiong, et al.

GitHub stars: 1.5K
Citations: 60
Published: Oct 2025

Read summary View on GitHub

91

The Web Conference

PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

PaperDebugger is an in-editor, multi-agent, plugin-based academic writing assistant that integrates directly into Overleaf via a Chrome extension, eliminating copy-paste workflows. It addresses the challenge of external LLM assistants by providing bidirectional synchronization, version control, secure state management, and multi-agent scheduling. The…

Junyi Hou, Andre Lin Huikai, Nuo Chen, Yiwei Gong, et al.

GitHub stars: 1.5K
Citations: 9
Published: Dec 2025

Read summary View on GitHub

92

arXiv.org

Ovis2.5 Technical Report

Ovis2.5 is a multimodal large language model from Alibaba Group, succeeding Ovis2. It introduces native-resolution visual perception using a NaViT vision transformer, which processes images at their original resolutions to preserve fine details and global layout, crucial for complex charts. The model also adds an optional 'thinking mode' for deep…

Shiyin Lu, Yang Li, Yu Xia, Yuwei Hu, et al.

GitHub stars: 1.5K
Citations: 81
Published: Aug 2025

Read summary View on GitHub

93

arXiv.org

Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

The paper introduces M3-Agent, a multimodal agent framework with long-term memory that processes real-time video and audio to build episodic and semantic memories, organized in an entity-centric multimodal graph. It uses reinforcement learning for multi-turn reasoning and iterative memory retrieval. The authors also present M3-Bench, a long-video question…

Lin Long, Yichen He, Wentao Ye, Yiyuan Pan, et al.

GitHub stars: 1.4K
Citations: 64
Published: Aug 2025

Read summary View on GitHub

94

arXiv.org

rStar2-Agent: Agentic Reasoning Technical Report

rStar2-Agent is a 14B math reasoning model trained with agentic reinforcement learning (RL) to achieve frontier-level performance, rivaling or surpassing DeepSeek-R1 (671B). It uses Python coding tools within a dedicated environment, enabling advanced cognitive behaviors like careful tool use and reflection on execution feedback. Key innovations include an…

Ning Shang, Yifei Liu, Yi Zhu, Li Lyna Zhang, et al.

GitHub stars: 1.4K
Citations: 45
Published: Aug 2025

Read summary View on GitHub

95

Independent research

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

InternAgent-1.5 is a unified agentic framework for long-horizon autonomous scientific discovery, developed by the InternScience Team at Shanghai Artificial Intelligence Laboratory. It addresses limitations of existing AI Scientist systems, such as domain-specific designs and limited long-horizon operation, by integrating three coordinated subsystems:…

Shiyang Feng, Runmin Ma, Xiangchao Yan, Yue Fan, et al.

GitHub stars: 1.4K
Citations: 20
Published: Feb 2026

Read summary View on GitHub

96

arXiv.org

Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives

Idea2Story is a framework for autonomous scientific discovery that shifts literature understanding from online reasoning to offline knowledge construction. It builds a structured methodological knowledge graph from peer-reviewed papers (about 13,000 from NeurIPS and ICLR over three years) and their review feedback, extracting reusable method units and…

Tengyue Xu, Zhuoyang Qian, Gaoge Liu, Li Ling, et al.

GitHub stars: 1.4K
Citations: 5
Published: Jan 2026

Read summary View on GitHub

97

arXiv.org

QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining

QuantaAlpha is an evolutionary alpha mining framework that treats each end-to-end mining run as a trajectory and improves factors via trajectory-level mutation and crossover. It addresses limitations in existing agentic systems, such as fragile controllability, limited trustworthiness, and constrained exploration, by localizing suboptimal steps for…

Jun Han, Shuo Zhang, Wei Li, Yifan Dong, et al.

GitHub stars: 1.4K
Citations: 7
Published: Feb 2026

Read summary View on GitHub

98

Qwen

Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking

The report introduces Qwen3-VL-Embedding and Qwen3-VL-Reranker, a unified framework for multimodal retrieval built on the Qwen3-VL foundation model. The embedding model uses a multi-stage training pipeline (contrastive pre-training, multi-task contrastive learning, and reranker distillation) to produce high-dimensional vectors, supporting Matryoshka…

Mingxin Li, Yanzhao Zhang, Dingkun Long, Keqin Chen, et al.

GitHub stars: 1.3K
Citations: 167
Published: Jan 2026

Read summary View on GitHub

99

arXiv.org

Agentic Reasoning for Large Language Models

This survey introduces agentic reasoning, a paradigm shift where large language models (LLMs) act as autonomous agents that plan, act, and learn through continual interaction with their environment, rather than passively generating sequences. The authors organize agentic reasoning along three complementary dimensions: foundational agentic reasoning (core…

Tianxin Wei, Ting-Wei Li, Zhining Liu, Xuying Ning, et al.

GitHub stars: 1.3K
Citations: 34
Published: Jan 2026

Read summary View on GitHub

100

arXiv.org

Lance: Unified Multimodal Modeling by Multi-Task Synergy

Lance is a lightweight native unified multimodal model from ByteDance that supports understanding, generation, and editing for both images and videos. It uses a dual-stream mixture-of-experts architecture on shared interleaved multimodal sequences, combining autoregressive language modeling for understanding with flow matching for generation. A…

Fengyi Fu, Mengqi Huang, Shaojin Wu, Yunsheng Jiang, et al.

GitHub stars: 1.3K
Citations: 3
Published: May 2026

Read summary View on GitHub