#GRPO algorithm

41 related articles

Jul 30, 2026·4 min

Freesolo Flash: Deep Dive into the Full-Stack Platform for Enterprise Small Model Training

Freesolo Flash is a full-stack platform for enterprise small language model (SLM) training that commoditizes reinforcement learning, enabling teams to train specialized AI models at low cost.

Jul 28, 2026·4 min

Kimi K2/K3 Technical Speculation: Deep Dive into RL Hyperparameters and Multi-Teacher Distillation

Deep analysis of RL hyperparameter tuning challenges and 9-policy multi-teacher distillation in Kimi K2/K3 training, exploring the shift from scale to training craft.

Jul 24, 2026·7 min

DeepSeek's Mysteriously Retracted Paper: Breaking AI's Multimodal Reasoning Bottleneck with Visual Primitives

DeepSeek's paper 'Thinking with Visual Primitives' was online for just 4 hours before being pulled. It uses bounding boxes and points as reasoning primitives, letting models 'point at' images to outperform GPT, Gemini, and Claude on maze navigation and counting.

Jul 22, 2026·3 min

Beware of 'Free GPT' Scams: How to Spot AI Traffic-Baiting Schemes and Their Risks

Videos on Bilibili claiming free access to GPT-5.6 and Claude are traffic scams. Learn how to spot fake AI offers, understand the real risks, and find safe alternatives.

Jul 22, 2026·4 min

UK Sovereign AI: How Cosine AI Is Punching Above Its Weight Against American Compute Dominance

Cosine AI founder reveals how the UK's first sovereign LLM is being built — from government compute grants and RL credit attribution to multi-agent orchestration and synthetic data pipelines.

Jul 22, 2026·3 min

Qwen's Six-Generation Evolution: A Complete Breakdown from Architecture Innovations to the Reasoning Race

From Qwen1 to Qwen3-2507: a complete breakdown of six generations of evolution over two years — GQA, MoE, GRPO, dynamic thinking, and the core shift from architecture to reasoning.

Jul 21, 2026·2 min

Zhipu GLM New Model Coming Soon: Decoding the Founder's Teaser

Zhipu AI's Z.ai founder teases a new GLM model just one month after GLM 5.2. We decode the announcement, explore likely upgrade directions, and analyze China's LLM iteration pace.

Jul 19, 2026·2 min

Ollama Modelfile in Practice: Deploy Your Own Custom DeepSeek-R1 Model Locally

Step-by-step guide to wrapping DeepSeek-R1 with an Ollama Modelfile — set temperature, system prompts, and run fully offline for privacy and flexibility.

Jul 19, 2026·2 min

AI Agent Development Roadmap: A Four-Stage Guide from Zero to Production

A four-stage AI Agent development roadmap: from core theory and ReAct paradigm to multi-agent collaboration and production deployment. Covers DeepSeek, Coze, Dify, and more.

Jul 17, 2026·3 min

AI Large Language Models for Beginners: Core Concepts and Chinese Model Landscape

New to AI? This guide clarifies AI, machine learning, deep learning, and LLMs, traces milestones from Deep Blue to DeepSeek, and maps out China's LLM landscape.

Three Core Gaps in Multimodal LLMs: Fr…

Jul 16, 2026·4 min

Three Core Gaps in Multimodal LLMs: Frontier Research from Microsoft Research India

Microsoft Research India reveals three core gaps in multimodal LLMs: visual perception blindspots, cognitive hallucination, and architectural limitations. Explores Faithful GRPO, behavior modeling, and model alignment breakthroughs.

Jul 16, 2026·2 min

The Reasoning Trap in Diffusion Language Models: A One-Line Fix for the 'Flexibility' Flaw

ICML Outstanding Paper 'The Flexibility Trap' reveals how dLLMs' arbitrary-order generation bypasses logical connectives, breaking reasoning. JustGRPO fixes this with autoregressive training + parallel inference, achieving 89.1% on GSM8K in under 60 lines of code.

Jul 16, 2026·3 min

Can Open Source Topple ChatGPT? CSDN Founder Jiang Tao Breaks Down DeepSeek's Game-Changing Strategy

CSDN founder Jiang Tao analyzes how DeepSeek uses open source to challenge ChatGPT's dominance — from technical transparency to national AI strategy.

Jul 15, 2026·4 min

RAM: First-Principles Approach to 50x Faster RL Post-Training for Diffusion Models

RAM (Reinforce Adjoint Matching) achieves 50x faster RL post-training for diffusion models by discarding path costs, combining ODE sampling with decorrelated training objectives. A deep dive into RAM's core principles and experiments vs. Flow-GRPO.

Jul 13, 2026·2 min

iFLYTEK T30 Lite Learning Tablet In-Depth Review: Dual AI Engines + 12.5-Inch Eye-Care Display

The iFLYTEK T30 Lite learning tablet features the Spark large model and DeepSeek dual AI engines, a 12.5-inch eye-care display, and 8GB+512GB storage. This in-depth review analyzes its hardware, AI learning capabilities, and buying advice for K12 families.

Jul 12, 2026·3 min

The Four-Stage Learning Path for AI Agent Development: A Complete Guide from Beginner to Practitioner

A systematic guide to the four-stage AI Agent development path: core concepts, principle paradigms like ReAct, RL and multi-agent optimization, and real-world projects. Mastering Agent development is the true hardcore edge in today's LLM field.

Jul 11, 2026·7 min

50 AI Research Job Applications to FAANG, 0 Replies? Unpacking the Truth Behind the Job Search Struggle

An AI research engineer with 3 years of experience sent 50 applications to FAANG with zero replies. This article breaks down the hidden barriers of top-tech AI roles, the truth about LinkedIn ghost jobs, and the MLE vs. Research Engineer divide.

Jul 10, 2026·4 min

AI Agent Learning Path for Beginners: From Theory to Real-World Practice

A complete AI Agent learning roadmap covering BDI theory, core components (Perception/Planning/Execution), AutoGen multi-agent frameworks, and DeepSeek RAG projects for beginners.

Jul 10, 2026·4 min

Kun: An Open-Source AI Coding Agent Deeply Optimized for DeepSeek

Kun is an open-source AI coding agent optimized for DeepSeek and domestic users, with nearly 5,000 GitHub stars. Features include requirements drafting, inline diffs, cost visualization, and mobile monitoring. Real-world cache hit rates reached 97%, keeping costs extremely low.

Jul 10, 2026·3 min

Visualize and Edit AI Reasoning Chains: Making LLM Thinking Transparent and Controllable

A new web tool visualizes and lets users edit AI chain-of-thought reasoning. Explore how it works, its use cases, and the limits of LLM interpretability.