Trending Papers - Hugging Face

Submitted by

jt-zhang

Submitted by

jt-zhang

Submitted by

amael-apple

Submitted by

amael-apple

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

andito

Submitted by

andito

Step-DeepResearch Technical Report

Step-DeepResearch, an end-to-end agent enhanced with a data synthesis strategy and progressive training, achieves expert-level capabilities in deep research scenarios, outperforming established models.

StepFun · Published on Dec 23, 2025

Step-DeepResearch Technical Report

Step-DeepResearch, an end-to-end agent enhanced with a data synthesis strategy and progressive training, achieves expert-level capabilities in deep research scenarios, outperforming established models.

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.

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

Paper99

Submitted by

Paper99

Submitted by

Cxxs

Submitted by

Cxxs

Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding

A novel framework, Robust-R1, enhances multimodal large language models' robustness to visual degradations through explicit modeling, supervised fine-tuning, reward-driven alignment, and dynamic reasoning depth scaling, achieving state-of-the-art performance on real-world degradation benchmarks.

Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding

A novel framework, Robust-R1, enhances multimodal large language models' robustness to visual degradations through explicit modeling, supervised fine-tuning, reward-driven alignment, and dynamic reasoning depth scaling, achieving state-of-the-art performance on real-world degradation benchmarks.

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

taesiri

Submitted by

taesiri

Submitted by

zbhpku

Submitted by

zbhpku

Submitted by

taesiri

Submitted by

taesiri

Submitted by

wanderkid

Submitted by

wanderkid

SAM Audio: Segment Anything in Audio

SAM Audio, a diffusion transformer-based foundation model, achieves superior performance in general audio separation using unified text, visual, and temporal span prompts across various audio types.

SAM Audio: Segment Anything in Audio

SAM Audio, a diffusion transformer-based foundation model, achieves superior performance in general audio separation using unified text, visual, and temporal span prompts across various audio types.

Submitted by

akhaliq

Submitted by

akhaliq

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

Submitted by

taesiri

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

akhaliq

Submitted by

akhaliq

SAM 3: Segment Anything with Concepts

Segment Anything Model 3 achieves state-of-the-art performance in promptable concept segmentation and tracking by leveraging a unified model architecture with decoupled recognition and localization.

SAM 3: Segment Anything with Concepts

Segment Anything Model 3 achieves state-of-the-art performance in promptable concept segmentation and tracking by leveraging a unified model architecture with decoupled recognition and localization.

Submitted by

taesiri

Submitted by

taesiri

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.

Submitted by

Keh0t0

Submitted by

Keh0t0

DINOv3

DINOv3, a self-supervised learning model, achieves superior performance across various vision tasks by scaling datasets and models, addressing dense feature degradation, and enhancing flexibility with post-hoc strategies.

DINOv3

DINOv3, a self-supervised learning model, achieves superior performance across various vision tasks by scaling datasets and models, addressing dense feature degradation, and enhancing flexibility with post-hoc strategies.

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

xianbao

Submitted by

xianbao

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

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

xw-eric

Submitted by

xw-eric

Spatia: Video Generation with Updatable Spatial Memory

Spatia, a spatial memory-aware video generation framework, maintains long-term spatial and temporal consistency by preserving and updating a 3D scene point cloud, enabling realistic video generation and interactive editing.

Spatia: Video Generation with Updatable Spatial Memory

Spatia, a spatial memory-aware video generation framework, maintains long-term spatial and temporal consistency by preserving and updating a 3D scene point cloud, enabling realistic video generation and interactive editing.

Submitted by

taesiri

Submitted by

taesiri

Submitted by

Weiyun1025

Submitted by

Weiyun1025

Submitted by

xw-eric

Submitted by

xw-eric

Submitted by

dyyyyyyyy

Submitted by

dyyyyyyyy

HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming

High-resolution video generation, while crucial for digital media and film, is computationally bottlenecked by the quadratic complexity of diffusion models, making practical inference infeasible. To address this, we introduce HiStream, an efficient autoregressive framework that systematically reduces redundancy across three axes: i) Spatial Compression: denoising at low resolution before refining at high resolution with cached features; ii) Temporal Compression: a chunk-by-chunk strategy with a fixed-size anchor cache, ensuring stable inference speed; and iii) Timestep Compression: applying fewer denoising steps to subsequent, cache-conditioned chunks. On 1080p benchmarks, our primary HiStream model (i+ii) achieves state-of-the-art visual quality while demonstrating up to 76.2x faster denoising compared to the Wan2.1 baseline and negligible quality loss. Our faster variant, HiStream+, applies all three optimizations (i+ii+iii), achieving a 107.5x acceleration over the baseline, offering a compelling trade-off between speed and quality, thereby making high-resolution video generation both practical and scalable.

HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming

High-resolution video generation, while crucial for digital media and film, is computationally bottlenecked by the quadratic complexity of diffusion models, making practical inference infeasible. To address this, we introduce HiStream, an efficient autoregressive framework that systematically reduces redundancy across three axes: i) Spatial Compression: denoising at low resolution before refining at high resolution with cached features; ii) Temporal Compression: a chunk-by-chunk strategy with a fixed-size anchor cache, ensuring stable inference speed; and iii) Timestep Compression: applying fewer denoising steps to subsequent, cache-conditioned chunks. On 1080p benchmarks, our primary HiStream model (i+ii) achieves state-of-the-art visual quality while demonstrating up to 76.2x faster denoising compared to the Wan2.1 baseline and negligible quality loss. Our faster variant, HiStream+, applies all three optimizations (i+ii+iii), achieving a 107.5x acceleration over the baseline, offering a compelling trade-off between speed and quality, thereby making high-resolution video generation both practical and scalable.

The Unreasonable Effectiveness of Scaling Agents for Computer Use

Behavior Best-of-N (bBoN) improves the reliability and success rates of computer-use agents by generating and selecting among multiple rollouts using behavior narratives, achieving state-of-the-art performance on OSWorld and strong generalization to different operating systems.

Simular · Published on Oct 2, 2025

The Unreasonable Effectiveness of Scaling Agents for Computer Use

Behavior Best-of-N (bBoN) improves the reliability and success rates of computer-use agents by generating and selecting among multiple rollouts using behavior narratives, achieving state-of-the-art performance on OSWorld and strong generalization to different operating systems.

Submitted by

Jeff-Wang

Submitted by

Jeff-Wang

HunyuanVideo 1.5 Technical Report

HunyuanVideo 1.5 is a lightweight video generation model with state-of-the-art visual quality and motion coherence, using a DiT architecture with SSTA and an efficient video super-resolution network.

HunyuanVideo 1.5 Technical Report

HunyuanVideo 1.5 is a lightweight video generation model with state-of-the-art visual quality and motion coherence, using a DiT architecture with SSTA and an efficient video super-resolution network.

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

AaronHuangWei

Submitted by

AaronHuangWei

Submitted by

taesiri

Submitted by

taesiri

Submitted by

jedyang97

Submitted by

jedyang97

Submitted by

JDihlmann

Submitted by

JDihlmann