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

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

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

taesiri

Submitted by

taesiri

HeartMuLa: A Family of Open Sourced Music Foundation Models

A suite of open-source music foundation models is introduced, featuring components for audio-text alignment, lyric recognition, music coding, and large language model-based song generation with controllable attributes and scalable parameterization.

HeartMuLa: A Family of Open Sourced Music Foundation Models

A suite of open-source music foundation models is introduced, featuring components for audio-text alignment, lyric recognition, music coding, and large language model-based song generation with controllable attributes and scalable parameterization.

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.

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

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.

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

Submitted by

daixufang

Submitted by

daixufang

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

taesiri

Submitted by

taesiri

Submitted by

LakshyAAAgrawal

Submitted by

LakshyAAAgrawal

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.

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

richardxp888

Submitted by

richardxp888

UI-Venus-1.5 Technical Report

UI-Venus-1.5 is a unified GUI agent with improved performance through mid-training stages, online reinforcement learning, and model merging techniques.

UI-Venus-1.5 Technical Report

UI-Venus-1.5 is a unified GUI agent with improved performance through mid-training stages, online reinforcement learning, and model merging techniques.

GPT-4 Technical Report

GPT-4, a multimodal Transformer-based model, achieves human-level performance on professional and academic benchmarks through pre-training and post-training alignment.

GPT-4 Technical Report

GPT-4, a multimodal Transformer-based model, achieves human-level performance on professional and academic benchmarks through pre-training and post-training alignment.

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

akhaliq

Submitted by

akhaliq

Recursive Language Models

We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive Language Models (RLMs), a general inference strategy that treats long prompts as part of an external environment and allows the LLM to programmatically examine, decompose, and recursively call itself over snippets of the prompt. We find that RLMs successfully handle inputs up to two orders of magnitude beyond model context windows and, even for shorter prompts, dramatically outperform the quality of base LLMs and common long-context scaffolds across four diverse long-context tasks, while having comparable (or cheaper) cost per query.

Recursive Language Models

We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive Language Models (RLMs), a general inference strategy that treats long prompts as part of an external environment and allows the LLM to programmatically examine, decompose, and recursively call itself over snippets of the prompt. We find that RLMs successfully handle inputs up to two orders of magnitude beyond model context windows and, even for shorter prompts, dramatically outperform the quality of base LLMs and common long-context scaffolds across four diverse long-context tasks, while having comparable (or cheaper) cost per query.

TimeGPT-1

TimeGPT, a foundation model for time series analysis, surpasses traditional methods in zero-shot prediction accuracy and efficiency by leveraging deep learning advancements.

TimeGPT-1

TimeGPT, a foundation model for time series analysis, surpasses traditional methods in zero-shot prediction accuracy and efficiency by leveraging deep learning advancements.

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.

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

xdotli

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

SkillsBench evaluates agent skills across 86 tasks and finds that curated skills improve performance significantly but inconsistently, while self-generated skills offer no benefit, indicating that models struggle to create useful procedural knowledge despite benefiting from curated versions.

DeepCode: Open Agentic Coding

DeepCode, a fully autonomous framework, addresses the challenges of document-to-codebase synthesis by optimizing information flow through source compression, structured indexing, knowledge injection, and error correction, achieving state-of-the-art performance and surpassing human experts.

DeepCode: Open Agentic Coding

DeepCode, a fully autonomous framework, addresses the challenges of document-to-codebase synthesis by optimizing information flow through source compression, structured indexing, knowledge injection, and error correction, achieving state-of-the-art performance and surpassing human experts.

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.

LTX-2: Efficient Joint Audio-Visual Foundation Model

LTX-2 is an open-source audiovisual diffusion model that generates synchronized video and audio content using a dual-stream transformer architecture with cross-modal attention and classifier-free guidance.

Submitted by

taesiri

Submitted by

March07

Submitted by

March07

Continuous Audio Language Models

Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy codecs with a limited bitrate. As a consequence, increasing audio quality requires generating more tokens, which imposes a trade-off between fidelity and computational cost. We address this issue by studying Continuous Audio Language Models (CALM). These models instantiate a large Transformer backbone that produces a contextual embedding at every timestep. This sequential information then conditions an MLP that generates the next continuous frame of an audio VAE through consistency modeling. By avoiding lossy compression, CALM achieves higher quality at lower computational cost than their discrete counterpart. Experiments on speech and music demonstrate improved efficiency and fidelity over state-of-the-art discrete audio language models, facilitating lightweight, high-quality audio generation. Samples are available at https://continuous-audio-language-models.github.io

Continuous Audio Language Models

Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy codecs with a limited bitrate. As a consequence, increasing audio quality requires generating more tokens, which imposes a trade-off between fidelity and computational cost. We address this issue by studying Continuous Audio Language Models (CALM). These models instantiate a large Transformer backbone that produces a contextual embedding at every timestep. This sequential information then conditions an MLP that generates the next continuous frame of an audio VAE through consistency modeling. By avoiding lossy compression, CALM achieves higher quality at lower computational cost than their discrete counterpart. Experiments on speech and music demonstrate improved efficiency and fidelity over state-of-the-art discrete audio language models, facilitating lightweight, high-quality audio generation. Samples are available at https://continuous-audio-language-models.github.io

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

Evaluating and Aligning CodeLLMs on Human Preference

A human-curated benchmark (CodeArena) and a large synthetic instruction corpus (SynCode-Instruct) are introduced to evaluate code LLMs based on human preference alignment, revealing performance differences between open-source and proprietary models.

Evaluating and Aligning CodeLLMs on Human Preference

A human-curated benchmark (CodeArena) and a large synthetic instruction corpus (SynCode-Instruct) are introduced to evaluate code LLMs based on human preference alignment, revealing performance differences between open-source and proprietary models.

SimpleMem: Efficient Lifelong Memory for LLM Agents

To support reliable long-term interaction in complex environments, LLM agents require memory systems that efficiently manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to substantial redundancy, or rely on iterative reasoning to filter noise, incurring high token costs. To address this challenge, we introduce SimpleMem, an efficient memory framework based on semantic lossless compression. We propose a three-stage pipeline designed to maximize information density and token utilization: (1) Semantic Structured Compression, which applies entropy-aware filtering to distill unstructured interactions into compact, multi-view indexed memory units; (2) Recursive Memory Consolidation, an asynchronous process that integrates related units into higher-level abstract representations to reduce redundancy; and (3) Adaptive Query-Aware Retrieval, which dynamically adjusts retrieval scope based on query complexity to construct precise context efficiently. Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost, achieving an average F1 improvement of 26.4% while reducing inference-time token consumption by up to 30-fold, demonstrating a superior balance between performance and efficiency. Code is available at https://github.com/aiming-lab/SimpleMem.

SimpleMem: Efficient Lifelong Memory for LLM Agents

To support reliable long-term interaction in complex environments, LLM agents require memory systems that efficiently manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to substantial redundancy, or rely on iterative reasoning to filter noise, incurring high token costs. To address this challenge, we introduce SimpleMem, an efficient memory framework based on semantic lossless compression. We propose a three-stage pipeline designed to maximize information density and token utilization: (1) Semantic Structured Compression, which applies entropy-aware filtering to distill unstructured interactions into compact, multi-view indexed memory units; (2) Recursive Memory Consolidation, an asynchronous process that integrates related units into higher-level abstract representations to reduce redundancy; and (3) Adaptive Query-Aware Retrieval, which dynamically adjusts retrieval scope based on query complexity to construct precise context efficiently. Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost, achieving an average F1 improvement of 26.4% while reducing inference-time token consumption by up to 30-fold, demonstrating a superior balance between performance and efficiency. Code is available at https://github.com/aiming-lab/SimpleMem.

Multi-Agent Collaboration via Evolving Orchestration

A centralized orchestrator dynamically directs LLM agents via reinforcement learning, achieving superior multi-agent collaboration in varying tasks with reduced computational costs.

Multi-Agent Collaboration via Evolving Orchestration

A centralized orchestrator dynamically directs LLM agents via reinforcement learning, achieving superior multi-agent collaboration in varying tasks with reduced computational costs.

Submitted by

Paper99

Submitted by

Paper99

RynnBrain: Open Embodied Foundation Models

RynnBrain is an open-source spatiotemporal foundation model for embodied intelligence that unifies perception, reasoning, and planning capabilities across multiple scales and task-specific variants.

RynnBrain: Open Embodied Foundation Models

RynnBrain is an open-source spatiotemporal foundation model for embodied intelligence that unifies perception, reasoning, and planning capabilities across multiple scales and task-specific variants.

Submitted by

xw-eric

Submitted by

xw-eric