BestHub
Sign in
DataFunTalk
DataFunTalk
Nov 7, 2025 · Artificial Intelligence

Training-Free GRPO: Low‑Cost Reinforcement Learning for Large Language Models

Training-Free GRPO, proposed by Tencent Youtu Lab, eliminates parameter updates by iteratively building an experience knowledge base, enabling cost‑effective reinforcement learning for large language models, dramatically reducing training expenses from thousands of dollars to under $20 while maintaining strong performance across math reasoning and web search tasks.

AIReinforcement learningTraining-Free
0 likes · 6 min read
Training-Free GRPO: Low‑Cost Reinforcement Learning for Large Language Models
AI Frontier Lectures
AI Frontier Lectures
Jul 26, 2025 · Artificial Intelligence

Training-Free Universal Virtual Try-On: OmniVTON’s Multi-Person Breakthrough

OmniVTON introduces a training‑free universal virtual try‑on framework that decouples garment texture and human pose, achieving high‑fidelity results across both in‑shop and in‑the‑wild scenarios, and uniquely supporting multi‑person virtual dressing, as demonstrated by extensive quantitative and qualitative experiments.

Artificial IntelligenceMulti-PersonTraining-Free
0 likes · 9 min read
Training-Free Universal Virtual Try-On: OmniVTON’s Multi-Person Breakthrough
Baobao Algorithm Notes
Baobao Algorithm Notes
Dec 18, 2024 · Artificial Intelligence

How STAR Enables Training‑Free Recommendations with Large Language Models

The article reviews the STAR framework, a training‑free recommendation approach that leverages large language model embeddings and collaborative co‑occurrence scores to retrieve and rank items, and evaluates its performance, hyper‑parameter effects, and ablation studies against existing LLM‑based recommender methods.

Artificial IntelligenceInformation RetrievalLLM
0 likes · 10 min read
How STAR Enables Training‑Free Recommendations with Large Language Models