Trending Papers - Hugging Face (original) (raw)

new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Subscribe

byAK and the research community

Submitted by

unilm

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

unilm

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

BradyFU

Submitted by

BradyFU

Submitted by

taesiri

Submitted by

taesiri

Submitted by

chengtim

VOID: Video Object and Interaction Deletion

VOID is a video object removal framework that uses vision-language models and video diffusion models to generate physically plausible scenes by leveraging causal reasoning and counterfactual reasoning.

Submitted by

chengtim

VOID: Video Object and Interaction Deletion

VOID is a video object removal framework that uses vision-language models and video diffusion models to generate physically plausible scenes by leveraging causal reasoning and counterfactual reasoning.

Submitted by

AaronHuangWei

Submitted by

AaronHuangWei

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.

· Published on Aug 2, 2025

Submitted by

WENGSYX

Submitted by

WENGSYX

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.

· Published on Oct 8, 2024

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

Tyrannosaurus

Submitted by

Tyrannosaurus

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.

· Published on Apr 28, 2025

Submitted by

akhaliq

Submitted by

taesiri

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.

· Published on Feb 17, 2026

Submitted by

taesiri

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

yyamada

Submitted by

yyamada

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.

· Published on Mar 13, 2024

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

taesiri

Submitted by

taesiri

Submitted by

jarridrb

Submitted by

jarridrb

Submitted by

rubenohana

Submitted by

rubenohana

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

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.

· Published on Jul 25, 2024

Submitted by

akhaliq

Submitted by

taesiri

Submitted by

taesiri

Submitted by

wangzx1994

Generative World Renderer

A large-scale dynamic dataset derived from AAA games is introduced to improve generative inverse and forward rendering, featuring high-resolution synchronized RGB and G-buffer data alongside a novel VLM-based evaluation method that correlates well with human judgment.

Submitted by

wangzx1994

Generative World Renderer

A large-scale dynamic dataset derived from AAA games is introduced to improve generative inverse and forward rendering, featuring high-resolution synchronized RGB and G-buffer data alongside a novel VLM-based evaluation method that correlates well with human judgment.

Submitted by

Virgilllll

Submitted by

Virgilllll

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

Rbin

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

Rbin

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

Submitted by

jianchen0311

DFlash: Block Diffusion for Flash Speculative Decoding

DFlash is a speculative decoding framework that uses a lightweight block diffusion model for parallel token drafting, achieving significant speedup over existing autoregressive methods while maintaining high-quality outputs.

z-lab Z Lab

· Published on Feb 5, 2026

Submitted by

jianchen0311

DFlash: Block Diffusion for Flash Speculative Decoding

DFlash is a speculative decoding framework that uses a lightweight block diffusion model for parallel token drafting, achieving significant speedup over existing autoregressive methods while maintaining high-quality outputs.

Submitted by

vinthony

Submitted by

vinthony

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

ethanchern

Submitted by

ethanchern

Submitted by

taesiri

Submitted by

taesiri

Submitted by

quao627

Submitted by

quao627

Submitted by

Jiabin99

Submitted by

Jiabin99

Submitted by

taesiri

Memory Intelligence Agent

Memory Intelligence Agent framework integrates non-parametric and parametric memory systems with reinforcement learning to enable efficient reasoning and autonomous evolution in open-world environments.

· Published on Apr 6, 2026

Submitted by

taesiri

Memory Intelligence Agent

Memory Intelligence Agent framework integrates non-parametric and parametric memory systems with reinforcement learning to enable efficient reasoning and autonomous evolution in open-world environments.

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.

· Published on Feb 7, 2025

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

Jeff-Wang

GigaWorld-Policy: An Efficient Action-Centered World--Action Model

GigaWorld-Policy introduces an action-centered World-Action Model that improves robotic policy learning by decoupling visual and motion representations, enabling faster inference and better task performance through dual supervision from action prediction and video generation.

open-gigaai GigaAI

· Published on Mar 18, 2026

Submitted by

Jeff-Wang

GigaWorld-Policy: An Efficient Action-Centered World--Action Model

GigaWorld-Policy introduces an action-centered World-Action Model that improves robotic policy learning by decoupling visual and motion representations, enabling faster inference and better task performance through dual supervision from action prediction and video generation.

Submitted by

hao-li

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.

· Published on Nov 17, 2025

Submitted by

hao-li

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.

· Nov 17, 2025

Submitted by

groundhogLLM

Submitted by

groundhogLLM

Efficient Universal Perception Encoder

Efficient Universal Perception Encoder (EUPE) improves edge device performance by distilling knowledge from multiple vision encoders through a two-stage scaling approach, achieving superior representation quality compared to previous methods.

· Published on Mar 23, 2026

Efficient Universal Perception Encoder

Efficient Universal Perception Encoder (EUPE) improves edge device performance by distilling knowledge from multiple vision encoders through a two-stage scaling approach, achieving superior representation quality compared to previous methods.

· Mar 23, 2026

Submitted by

yxl66666

Submitted by

yxl66666

Submitted by

taesiri

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 Qwen

· Published on Jan 22, 2026

Submitted by

taesiri

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

taesiri

In-Place Test-Time Training

In-Place Test-Time Training enables large language models to adapt parameters during inference by modifying the final projection matrix in MLP blocks with a task-aligned objective and efficient update mechanism.

· Published on Apr 7, 2026

Submitted by

taesiri

In-Place Test-Time Training

In-Place Test-Time Training enables large language models to adapt parameters during inference by modifying the final projection matrix in MLP blocks with a task-aligned objective and efficient update mechanism.

· Apr 7, 2026