Submitted by

taesiri

Submitted by

taesiri

Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices

Monolingual ASR models trained on a balanced mix of high-quality, pseudo-labeled, and synthetic data outperform multilingual models for small model sizes, achieving superior error rates and enabling on-device ASR for underrepresented languages.

Submitted by

evanking

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

OmniLottie

Submitted by

OmniLottie

Submitted by

akhaliq

Submitted by

akhaliq

Utonia: Toward One Encoder for All Point Clouds

Utonia enables cross-domain point cloud representation learning through a unified self-supervised transformer encoder, enhancing perception and supporting embodied and multimodal reasoning tasks.

Utonia: Toward One Encoder for All Point Clouds

Utonia enables cross-domain point cloud representation learning through a unified self-supervised transformer encoder, enhancing perception and supporting embodied and multimodal reasoning tasks.

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

AutoDev: Automated AI-Driven Development

AutoDev is an AI-driven software development framework that automates complex engineering tasks within a secure Docker environment, achieving high performance in code and test generation.

AutoDev: Automated AI-Driven Development

AutoDev is an AI-driven software development framework that automates complex engineering tasks within a secure Docker environment, achieving high performance in code and test generation.

Submitted by

andito

Submitted by

andito

Submitted by

taesiri

Submitted by

taesiri

dLLM: Simple Diffusion Language Modeling

A unified open-source framework is presented that standardizes core components of diffusion language modeling for reproduction, customization, and accessible development of both large and small models.

dLLM: Simple Diffusion Language Modeling

A unified open-source framework is presented that standardizes core components of diffusion language modeling for reproduction, customization, and accessible development of both large and small models.

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Mobile-Agent-v3: Foundamental Agents for GUI Automation

GUI-Owl and Mobile-Agent-v3 are open-source GUI agent models and frameworks that achieve state-of-the-art performance across various benchmarks using innovations in environment infrastructure, agent capabilities, and scalable reinforcement learning.

Mobile-Agent-v3: Foundamental Agents for GUI Automation

GUI-Owl and Mobile-Agent-v3 are open-source GUI agent models and frameworks that achieve state-of-the-art performance across various benchmarks using innovations in environment infrastructure, agent capabilities, and scalable reinforcement learning.

Submitted by

xssstory

Submitted by

xssstory

Submitted by

taesiri

Submitted by

taesiri

Submitted by

akhaliq

Submitted by

akhaliq

Qwen3-TTS Technical Report

The Qwen3-TTS series presents advanced multilingual text-to-speech models with voice cloning and controllable speech generation capabilities, utilizing dual-track LM architecture and specialized speech tokenizers for efficient streaming synthesis.

Qwen · Published on Jan 22, 2026

Qwen3-TTS Technical Report

The Qwen3-TTS series presents advanced multilingual text-to-speech models with voice cloning and controllable speech generation capabilities, utilizing dual-track LM architecture and specialized speech tokenizers for efficient streaming synthesis.

Qwen · Jan 22, 2026

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

Piang

Submitted by

Piang

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

tfwang

Submitted by

tfwang

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

linyq

Submitted by

linyq

MemOS: A Memory OS for AI System

MemOS, a memory operating system for Large Language Models, addresses memory management challenges by unifying plaintext, activation-based, and parameter-level memories, enabling efficient storage, retrieval, and continual learning.

MemOS: A Memory OS for AI System

MemOS, a memory operating system for Large Language Models, addresses memory management challenges by unifying plaintext, activation-based, and parameter-level memories, enabling efficient storage, retrieval, and continual learning.

Self-Supervised Prompt Optimization

A self-supervised framework optimizes prompts for both closed and open-ended tasks by evaluating LLM outputs without external references, reducing costs and required data.

Self-Supervised Prompt Optimization

A self-supervised framework optimizes prompts for both closed and open-ended tasks by evaluating LLM outputs without external references, reducing costs and required data.

Submitted by

YangCaoCS

Submitted by

YangCaoCS

FireRed-OCR Technical Report

FireRed-OCR transforms general vision-language models into specialized OCR systems through structured data synthesis and progressive training strategies.

FireRed-OCR Technical Report

FireRed-OCR transforms general vision-language models into specialized OCR systems through structured data synthesis and progressive training strategies.

Single-stream Policy Optimization

Single-stream Policy Optimization (SPO) improves policy-gradient training for Large Language Models by eliminating group-based issues and providing a stable, low-variance learning signal, leading to better performance and efficiency.

Tencent · Published on Sep 16, 2025

Single-stream Policy Optimization

Single-stream Policy Optimization (SPO) improves policy-gradient training for Large Language Models by eliminating group-based issues and providing a stable, low-variance learning signal, leading to better performance and efficiency.

Submitted by

hanyang-21

Submitted by

hanyang-21

Submitted by

AdinaY

Submitted by

AdinaY

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.

World Action Models are Zero-shot Policies

DreamZero is a World Action Model that leverages video diffusion to enable better generalization of physical motions across novel environments and embodiments compared to vision-language-action models.

World Action Models are Zero-shot Policies

DreamZero is a World Action Model that leverages video diffusion to enable better generalization of physical motions across novel environments and embodiments compared to vision-language-action models.

Submitted by

Falcary

Submitted by

Falcary

Submitted by

parachas

Submitted by

parachas

MNN: A Universal and Efficient Inference Engine

MNN, a universal and efficient deep learning inference engine for mobile devices, addresses model compatibility, device diversity, and resource limitations through pre-inference, kernel optimization, and backend abstraction.

MNN: A Universal and Efficient Inference Engine

MNN, a universal and efficient deep learning inference engine for mobile devices, addresses model compatibility, device diversity, and resource limitations through pre-inference, kernel optimization, and backend abstraction.

Text-to-LoRA: Instant Transformer Adaption

Text-to-LoRA (T2L) is a hypernetwork that dynamically adapts large language models using natural language descriptions, enabling efficient and zero-shot task-specific fine-tuning with minimal computational resources.

Text-to-LoRA: Instant Transformer Adaption

Text-to-LoRA (T2L) is a hypernetwork that dynamically adapts large language models using natural language descriptions, enabling efficient and zero-shot task-specific fine-tuning with minimal computational resources.

Submitted by

GuoxinChen

Submitted by

GuoxinChen

Qwen3-Coder-Next Technical Report

Qwen3-Coder-Next is an 80-billion-parameter language model that activates only 3 billion parameters during inference, achieving strong coding capabilities through agentic training with verifiable task synthesis and reinforcement learning.

Qwen · Published on Feb 28, 2026

Qwen3-Coder-Next Technical Report

Qwen3-Coder-Next is an 80-billion-parameter language model that activates only 3 billion parameters during inference, achieving strong coding capabilities through agentic training with verifiable task synthesis and reinforcement learning.

Qwen · Feb 28, 2026

Submitted by

taesiri

Submitted by

taesiri