Trending Papers - Hugging Face

Submitted by

andy-yang

Submitted by

andy-yang

Submitted by

oriuta

Submitted by

oriuta

Submitted by

janchorowski

Submitted by

janchorowski

Prime Agent: A Self-Improving RLM Harness

Prime Agent is an open-source harness that uses recursive subagents, persistent computation, and agent-to-agent coordination to extend language models' long-horizon capabilities across coding and reasoning tasks.

Prime Agent: A Self-Improving RLM Harness

Prime Agent is an open-source harness that uses recursive subagents, persistent computation, and agent-to-agent coordination to extend language models' long-horizon capabilities across coding and reasoning tasks.

Submitted by

krahets

Submitted by

krahets

Submitted by

Zonghao2025

Submitted by

Zonghao2025

LLM-as-a-Verifier: A General-Purpose Verification Framework

LLM-as-a-Verifier introduces a probabilistic verification framework that scales across multiple dimensions to improve solution correctness assessment and agent performance across various benchmarks.

Submitted by

taesiri

LongCat-Video Technical Report

LongCat-Video, a 13.6B parameter video generation model based on the Diffusion Transformer framework, excels in efficient and high-quality long video generation across multiple tasks using unified architecture, coarse-to-fine generation, and block sparse attention.

LongCat

· Published on Oct 25, 2025

LongCat-Video Technical Report

LongCat-Video, a 13.6B parameter video generation model based on the Diffusion Transformer framework, excels in efficient and high-quality long video generation across multiple tasks using unified architecture, coarse-to-fine generation, and block sparse attention.

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

Leon1207

Submitted by

Leon1207

Submitted by

jasonrqh

Submitted by

jasonrqh

Submitted by

seashell11

Submitted by

seashell11

Submitted by

Paranioar

Submitted by

Paranioar

Submitted by

taesiri

Submitted by

taesiri

Submitted by

akhaliq

Submitted by

akhaliq

Very Large-Scale Multi-Agent Simulation in AgentScope

Enhancements to the AgentScope platform improve scalability, efficiency, and ease of use for large-scale multi-agent simulations through distributed mechanisms, flexible environments, and user-friendly tools.

Submitted by

akhaliq

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Submitted by

RuofengYang

Submitted by

RuofengYang

Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Mem0, a memory-centric architecture with graph-based memory, enhances long-term conversational coherence in LLMs by efficiently extracting, consolidating, and retrieving information, outperforming existing memory systems in terms of accuracy and computational efficiency.

Submitted by

akhaliq

Unlimited OCR Works

Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.

BAIDU

· Published on Jun 22, 2026

Unlimited OCR Works

Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.

Submitted by

VictorKai1996NUS

Submitted by

VictorKai1996NUS

Submitted by

andito

Submitted by

andito

Kronos: A Foundation Model for the Language of Financial Markets

Kronos, a specialized pre-training framework for financial K-line data, outperforms existing models in forecasting and synthetic data generation through a unique tokenizer and autoregressive pre-training on a large dataset.

Submitted by

eric-xiang

Submitted by

eric-xiang

Submitted by

daixufang

Submitted by

daixufang

Submitted by

ChengCui

Submitted by

ChengCui

Submitted by

Xin64

Submitted by

Xin64

EchoWM: Open and Enterable Omnimodal World Models

EchoWM is an omnimodal world model that generates synchronized high-resolution video, sound, music, and speech while following continuous 6-DoF navigation trajectories across first- and third-person views.

EchoWM: Open and Enterable Omnimodal World Models

EchoWM is an omnimodal world model that generates synchronized high-resolution video, sound, music, and speech while following continuous 6-DoF navigation trajectories across first- and third-person views.

Submitted by

lhmd

Submitted by

lhmd

Submitted by

CuiLong7

Submitted by

CuiLong7

Submitted by

MatrAIx

Submitted by

MatrAIx

ReWorld: An Interactive World Model with Long-Horizon Memory

ReWorld separates short-horizon control and long-horizon memory during training, then bounds both at inference via mixed attention windows, a pose-indexed landmark bank, and distribution-matching LoRA distillation to enable real-time interactive world modeling with strong action fidelity and long-range recall.

ReWorld: An Interactive World Model with Long-Horizon Memory

ReWorld separates short-horizon control and long-horizon memory during training, then bounds both at inference via mixed attention windows, a pose-indexed landmark bank, and distribution-matching LoRA distillation to enable real-time interactive world modeling with strong action fidelity and long-range recall.

VibeVoice Technical Report

VibeVoice synthesizes long-form multi-speaker speech using next-token diffusion and a highly efficient continuous speech tokenizer, achieving superior performance and fidelity.

VibeVoice Technical Report

VibeVoice synthesizes long-form multi-speaker speech using next-token diffusion and a highly efficient continuous speech tokenizer, achieving superior performance and fidelity.

Submitted by

taesiri

Submitted by

taesiri

Submitted by

1e12Leon

Submitted by

1e12Leon

Submitted by

manchery

Submitted by

manchery

Submitted by

liangjiaqing

Submitted by

liangjiaqing

Submitted by

nielsr

Submitted by

nielsr

MAI-UI Technical Report: Real-World Centric Foundation GUI Agents

The development of GUI agents could revolutionize the next generation of human-computer interaction. Motivated by this vision, we present MAI-UI, a family of foundation GUI agents spanning the full spectrum of sizes, including 2B, 8B, 32B, and 235B-A22B variants. We identify four key challenges to realistic deployment: the lack of native agent-user interaction, the limits of UI-only operation, the absence of a practical deployment architecture, and brittleness in dynamic environments. MAI-UI addresses these issues with a unified methodology: a self-evolving data pipeline that expands the navigation data to include user interaction and MCP tool calls, a native device-cloud collaboration system routes execution by task state, and an online RL framework with advanced optimizations to scale parallel environments and context length. MAI-UI establishes new state-of-the-art across GUI grounding and mobile navigation. On grounding benchmarks, it reaches 73.5% on ScreenSpot-Pro, 91.3% on MMBench GUI L2, 70.9% on OSWorld-G, and 49.2% on UI-Vision, surpassing Gemini-3-Pro and Seed1.8 on ScreenSpot-Pro. On mobile GUI navigation, it sets a new SOTA of 76.7% on AndroidWorld, surpassing UI-Tars-2, Gemini-2.5-Pro and Seed1.8. On MobileWorld, MAI-UI obtains 41.7% success rate, significantly outperforming end-to-end GUI models and competitive with Gemini-3-Pro based agentic frameworks. Our online RL experiments show significant gains from scaling parallel environments from 32 to 512 (+5.2 points) and increasing environment step budget from 15 to 50 (+4.3 points). Finally, the native device-cloud collaboration system improves on-device performance by 33%, reduces cloud model calls by over 40%, and preserves user privacy.

MAI-UI Technical Report: Real-World Centric Foundation GUI Agents

The development of GUI agents could revolutionize the next generation of human-computer interaction. Motivated by this vision, we present MAI-UI, a family of foundation GUI agents spanning the full spectrum of sizes, including 2B, 8B, 32B, and 235B-A22B variants. We identify four key challenges to realistic deployment: the lack of native agent-user interaction, the limits of UI-only operation, the absence of a practical deployment architecture, and brittleness in dynamic environments. MAI-UI addresses these issues with a unified methodology: a self-evolving data pipeline that expands the navigation data to include user interaction and MCP tool calls, a native device-cloud collaboration system routes execution by task state, and an online RL framework with advanced optimizations to scale parallel environments and context length. MAI-UI establishes new state-of-the-art across GUI grounding and mobile navigation. On grounding benchmarks, it reaches 73.5% on ScreenSpot-Pro, 91.3% on MMBench GUI L2, 70.9% on OSWorld-G, and 49.2% on UI-Vision, surpassing Gemini-3-Pro and Seed1.8 on ScreenSpot-Pro. On mobile GUI navigation, it sets a new SOTA of 76.7% on AndroidWorld, surpassing UI-Tars-2, Gemini-2.5-Pro and Seed1.8. On MobileWorld, MAI-UI obtains 41.7% success rate, significantly outperforming end-to-end GUI models and competitive with Gemini-3-Pro based agentic frameworks. Our online RL experiments show significant gains from scaling parallel environments from 32 to 512 (+5.2 points) and increasing environment step budget from 15 to 50 (+4.3 points). Finally, the native device-cloud collaboration system improves on-device performance by 33%, reduces cloud model calls by over 40%, and preserves user privacy.

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

SkillOpt introduces a systematic text-space optimizer for agent skills that trains skills as external agent state with stable updates and zero deployment inference overhead, achieving superior performance across multiple benchmarks and execution environments.

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

SkillOpt introduces a systematic text-space optimizer for agent skills that trains skills as external agent state with stable updates and zero deployment inference overhead, achieving superior performance across multiple benchmarks and execution environments.

LightRAG: Simple and Fast Retrieval-Augmented Generation

LightRAG improves Retrieval-Augmented Generation by integrating graph structures for enhanced contextual awareness and efficient information retrieval, achieving better accuracy and response times.