huggingface

14 articles about huggingface in AI news

HuggingFace Launches Daily Papers SKILL.md for AI Agents to Read, Search, and Fetch Research Papers

HuggingFace released Daily Papers SKILL.md, a tool enabling AI agents to read paper content as markdown, search papers, find linked models/datasets, and fetch papers via API.

85% relevant

How AI Agents Are Learning to Scrape the Web and Fine-Tune Models in One Go

A developer has integrated web scraping capabilities into HuggingFace's fine-tuning skill, enabling AI agents to collect data from protected platforms and automatically train custom models. This breakthrough addresses a major bottleneck in AI development workflows.

85% relevant

Steal the 'Long-Running Claude' Scaffolding: CLAUDE.md, CHANGELOG.md, and the Ralph Loop

Anthropic's research reveals a four-part scaffolding—CLAUDE.md, CHANGELOG.md, a test oracle, and the Ralph loop—that lets you give Claude a multi-day task and walk away. Here’s how to apply it.

92% relevant

OpenCSF: A 1.5TB Free Computer Science Library Emerges from Unstructured Web Data

A new open-source dataset called OpenCSF has been compiled, containing 1.5TB of computer science materials scraped from public web sources. It provides a massive, free corpus for AI training and research in software engineering and CS education.

85% relevant

OmniForcing Enables Real-Time Joint Audio-Visual Generation at 25 FPS with 0.7s Latency

Researchers introduced OmniForcing, a method that distills a bidirectional LTX-2 model into a causal streaming generator for joint audio-visual synthesis. It achieves ~25 FPS with 0.7s latency, a 35× speedup over offline diffusion models while maintaining multi-modal fidelity.

92% relevant

NVIDIA NeMo Retriever Achieves #1 on ViDoRe v3 with New Agentic Pipeline

NVIDIA's NeMo Retriever team has developed a generalizable agentic retrieval pipeline that topped the ViDoRe v3 leaderboard and placed second on BRIGHT. The system moves beyond semantic similarity to dynamically adapt search strategies for complex, multi-domain data.

100% relevant

AI Learns to Use Tools Without Expensive Training: The Rise of In-Context Reinforcement Learning

Researchers have developed In-Context Reinforcement Learning (ICRL), a method that teaches large language models to use external tools through demonstration examples during reinforcement learning. This approach eliminates costly supervised fine-tuning while enabling models to gradually transition from few-shot to zero-shot tool usage capabilities.

87% relevant

NVIDIA's Nemotron-Terminal: A Systematic Pipeline for Scaling Terminal-Based AI Agents

NVIDIA researchers introduce Nemotron-Terminal, a comprehensive data engineering pipeline designed to scale terminal-based large language model agents. The system bridges the gap between raw terminal data and high-quality training datasets, addressing key challenges in agent reliability and generalization.

85% relevant

Meshcraft Democratizes 3D Creation: Multi-Engine AI Platform Bridges Text-to-3D Gap

Meshcraft emerges as a web-based platform offering text-to-3D and image-to-3D generation with selectable AI engines. The tool provides both free and premium options, addressing quality bottlenecks in 3D generation through engine optimization rather than image model refinement.

80% relevant

From Prototype to Production: Streamlining LLM Evaluation for Luxury Clienteling & Chatbots

NVIDIA's new NeMo Evaluator Agent Skills dramatically simplifies testing and monitoring of conversational AI agents. For luxury retail, this means faster, more reliable deployment of high-quality clienteling assistants and customer service chatbots.

60% relevant

Utonia AI Breakthrough: A Single Transformer Model Unifies All 3D Point Cloud Data

Researchers have developed Utonia, a single self-supervised transformer that learns unified 3D representations across diverse point cloud data types including LiDAR, CAD models, indoor scans, and video-lifted data. This breakthrough enables unprecedented cross-domain transfer and emergent behaviors in 3D AI.

85% relevant

DeepVision-103K: The Math Dataset That Could Revolutionize AI's Visual Reasoning

Researchers have introduced DeepVision-103K, a comprehensive mathematical dataset with 103,000 verifiable visual instances designed to train multimodal AI models. Covering K-12 topics from geometry to statistics, this dataset addresses critical gaps in AI's visual reasoning capabilities.

85% relevant

DualPath Architecture Shatters KV-Cache Bottleneck, Doubling LLM Throughput for AI Agents

Researchers have developed DualPath, a novel architecture that eliminates the KV-cache storage bottleneck in agentic LLM inference. By implementing dual-path loading with RDMA transfers, the system achieves nearly 2× throughput improvements for both offline and online scenarios.

85% relevant

NVIDIA's Memory Compression Breakthrough: How Forgetting Makes LLMs Smarter

NVIDIA researchers have developed Dynamic Memory Sparsification, a technique that compresses LLM working memory by 8× while improving reasoning capabilities. This counterintuitive approach addresses the critical KV cache bottleneck in long-context AI applications.

85% relevant