Trending Papers - Hugging Face

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

taesiri

Submitted by

taesiri

Geometric Context Transformer for Streaming 3D Reconstruction

LingBot-Map is a feed-forward 3D foundation model that reconstructs scenes from video streams using a geometric context transformer architecture with specialized attention mechanisms for coordinate grounding, dense geometric cues, and long-range drift correction, achieving stable real-time performance at 20 FPS.

Geometric Context Transformer for Streaming 3D Reconstruction

LingBot-Map is a feed-forward 3D foundation model that reconstructs scenes from video streams using a geometric context transformer architecture with specialized attention mechanisms for coordinate grounding, dense geometric cues, and long-range drift correction, achieving stable real-time performance at 20 FPS.

Submitted by

akhaliq

Submitted by

akhaliq

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.

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

ChengCui

Submitted by

ChengCui

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

GLM-5: from Vibe Coding to Agentic Engineering

GLM-5 advances foundation models with DSA for cost reduction, asynchronous reinforcement learning for improved alignment, and enhanced coding capabilities for real-world software engineering.

GLM-5: from Vibe Coding to Agentic Engineering

GLM-5 advances foundation models with DSA for cost reduction, asynchronous reinforcement learning for improved alignment, and enhanced coding capabilities for real-world software engineering.

Submitted by

zbhpku

Submitted by

zbhpku

Submitted by

sY713

Submitted by

sY713

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.

RAG-Anything: All-in-One RAG Framework

RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks.

RAG-Anything: All-in-One RAG Framework

RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks.

Submitted by

Xingyu-Zheng

Submitted by

Xingyu-Zheng

Submitted by

iieycx

Submitted by

iieycx

Submitted by

zhenyupan

Submitted by

zhenyupan

Submitted by

RuofengYang

Submitted by

RuofengYang

Submitted by

akhaliq

Submitted by

akhaliq

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.

Submitted by

nielsr

Submitted by

nielsr

Kairos: A Native World Model Stack for Physical AI

Kairos is a world model framework that learns from diverse experiences, maintains persistent states through hybrid temporal attention mechanisms, and operates efficiently across different hardware platforms for physical AI applications.

Kairos: A Native World Model Stack for Physical AI

Kairos is a world model framework that learns from diverse experiences, maintains persistent states through hybrid temporal attention mechanisms, and operates efficiently across different hardware platforms for physical AI applications.

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.

Agent READMEs: An Empirical Study of Context Files for Agentic Coding

Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write or execute the actual code with minimal human intervention. Central to this process are agent context files ("READMEs for agents") that provide persistent, project-level instructions. In this paper, we conduct the first large-scale empirical study of 2,303 agent context files from 1,925 repositories to characterize their structure, maintenance, and content. We find that these files are not static documentation but complex, difficult-to-read artifacts that evolve like configuration code, maintained through frequent, small additions. Our content analysis of 16 instruction types shows that developers prioritize functional context, such as build and run commands (62.3%), implementation details (69.9%), and architecture (67.7%). We also identify a significant gap: non-functional requirements like security (14.5%) and performance (14.5%) are rarely specified. These findings indicate that while developers use context files to make agents functional, they provide few guardrails to ensure that agent-written code is secure or performant, highlighting the need for improved tooling and practices.

Agent READMEs: An Empirical Study of Context Files for Agentic Coding

Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write or execute the actual code with minimal human intervention. Central to this process are agent context files ("READMEs for agents") that provide persistent, project-level instructions. In this paper, we conduct the first large-scale empirical study of 2,303 agent context files from 1,925 repositories to characterize their structure, maintenance, and content. We find that these files are not static documentation but complex, difficult-to-read artifacts that evolve like configuration code, maintained through frequent, small additions. Our content analysis of 16 instruction types shows that developers prioritize functional context, such as build and run commands (62.3%), implementation details (69.9%), and architecture (67.7%). We also identify a significant gap: non-functional requirements like security (14.5%) and performance (14.5%) are rarely specified. These findings indicate that while developers use context files to make agents functional, they provide few guardrails to ensure that agent-written code is secure or performant, highlighting the need for improved tooling and practices.

Submitted by

youganglyu

Submitted by

youganglyu

Submitted by

huohua325

Submitted by

huohua325

Cosmos 3: Omnimodal World Models for Physical AI

Cosmos 3 is an omnimodal world model that processes and generates multiple data types through a unified mixture-of-transformers architecture, achieving state-of-the-art performance in various understanding and generation tasks.

NVIDIA

· Published on Jun 1, 2026

Cosmos 3: Omnimodal World Models for Physical AI

Cosmos 3 is an omnimodal world model that processes and generates multiple data types through a unified mixture-of-transformers architecture, achieving state-of-the-art performance in various understanding and generation tasks.

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

AdinaY

Submitted by

AdinaY

Submitted by

taesiri

Submitted by

taesiri

Submitted by

kpzhang996

Submitted by

kpzhang996

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

jasonrqh

Submitted by

jasonrqh

Submitted by

MoeinAbtahi

Submitted by

MoeinAbtahi

Submitted by

taesiri

Submitted by

taesiri

Submitted by

xssstory

Submitted by

xssstory