Trending Papers - Hugging Face

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.

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

liangjiaqing

Submitted by

liangjiaqing

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

taesiri

Submitted by

taesiri

Submitted by

akhaliq

Submitted by

akhaliq

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

Representation Fréchet Loss for Visual Generation

Fréchet Distance can be effectively optimized as a training objective when decoupling population size from batch size, leading to improved generator quality and alternative evaluation metrics.

Representation Fréchet Loss for Visual Generation

Fréchet Distance can be effectively optimized as a training objective when decoupling population size from batch size, leading to improved generator quality and alternative evaluation metrics.

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

andito

Submitted by

andito

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

akhaliq

Submitted by

akhaliq

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Recursive Multi-Agent Systems

RecursiveMAS extends recursive scaling principles from single models to multi-agent systems, enabling collaborative reasoning through iterative latent-space computations with improved efficiency and accuracy.

Recursive Multi-Agent Systems

RecursiveMAS extends recursive scaling principles from single models to multi-agent systems, enabling collaborative reasoning through iterative latent-space computations with improved efficiency and accuracy.

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.

MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons

A fully end-to-end framework for arbitrary-skeleton motion capture that jointly optimizes video-to-pose and pose-to-rotation prediction while addressing rotation ambiguity through reference pose-rotation pairs and skeleton-aware attention mechanisms.

MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons

A fully end-to-end framework for arbitrary-skeleton motion capture that jointly optimizes video-to-pose and pose-to-rotation prediction while addressing rotation ambiguity through reference pose-rotation pairs and skeleton-aware attention mechanisms.

OpenGame: Open Agentic Coding for Games

OpenGame is an open-source agentic framework for end-to-end web game creation that uses specialized code models and evaluation benchmarks to overcome challenges in interactive application development.

OpenGame: Open Agentic Coding for Games

OpenGame is an open-source agentic framework for end-to-end web game creation that uses specialized code models and evaluation benchmarks to overcome challenges in interactive application development.

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

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

akhaliq

Submitted by

akhaliq

Submitted by

Haihao

Submitted by

Haihao

MolmoAct2: Action Reasoning Models for Real-world Deployment

MolmoAct2 presents an open-action reasoning model for robotics that improves upon previous systems through specialized vision-language-model backbones, new datasets, open-weight action tokenizers, architectural redesign for continuous-action prediction, and adaptive reasoning for reduced latency.

Ai2

· Published on May 4, 2026

MolmoAct2: Action Reasoning Models for Real-world Deployment

MolmoAct2 presents an open-action reasoning model for robotics that improves upon previous systems through specialized vision-language-model backbones, new datasets, open-weight action tokenizers, architectural redesign for continuous-action prediction, and adaptive reasoning for reduced latency.

Ai2

· May 4, 2026

Submitted by

mervenoyan

Submitted by

mervenoyan

Submitted by

xw-eric

Submitted by

xw-eric

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

Submitted by

lhmd

Submitted by

lhmd

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.

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

hongyyyyy

Submitted by

hongyyyyy

Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems

The study analyzes Claude Code's architecture, identifying five motivating human values and tracing them through thirteen design principles to specific implementation choices, including a core while-loop architecture and supporting systems for safety, context management, and extensibility.

Submitted by

taesiri

DeepSeek-V3 Technical Report

DeepSeek-V3 is a parameter-efficient Mixture-of-Experts language model using MLA and DeepSeekMoE architectures, achieving high performance with efficient training and minimal computational cost.

DeepSeek-V3 Technical Report

DeepSeek-V3 is a parameter-efficient Mixture-of-Experts language model using MLA and DeepSeekMoE architectures, achieving high performance with efficient training and minimal computational cost.

Submitted by

jordanlin

Submitted by

jordanlin

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.

Submitted by

ssz1111

Submitted by

ssz1111