BestHub
Sign in
Baobao Algorithm Notes
Author

Baobao Algorithm Notes

Author of the BaiMian large model, offering technology and industry insights.

296
Articles
0
Likes
713
Views
0
Comments
Recent Articles

Latest from Baobao Algorithm Notes

100 recent articles max
Baobao Algorithm Notes
Baobao Algorithm Notes
Dec 7, 2025 · Artificial Intelligence

Can RL Really Boost LLM Reasoning? A Critical Review of Recent Findings

This article critically examines recent RL‑for‑LLM studies, revealing that reinforcement learning improves search efficiency but does not extend the intrinsic reasoning capabilities of base models, and explores the underlying model‑conditioned optimization bias, comparisons with SFT distillation, and the trade‑off with catastrophic forgetting.

LLMModel OptimizationSFT
0 likes · 11 min read
Can RL Really Boost LLM Reasoning? A Critical Review of Recent Findings
Baobao Algorithm Notes
Baobao Algorithm Notes
Nov 20, 2025 · Artificial Intelligence

Why Reinforcement Learning Preserves LLM Generality Better Than Supervised Fine‑Tuning

The article analyzes why reinforcement learning (RL) fine‑tuning retains a large language model's general abilities better than supervised fine‑tuning (SFT), explaining the off‑policy distribution shift of SFT and the on‑policy data consistency, KL penalty, and trust‑region mechanisms that give RL its anti‑forgetting properties.

LLMOn-Policy DataSupervised Fine‑Tuning
0 likes · 8 min read
Why Reinforcement Learning Preserves LLM Generality Better Than Supervised Fine‑Tuning
Baobao Algorithm Notes
Baobao Algorithm Notes
Nov 18, 2025 · Industry Insights

Google Gemini 3 Pro Beats GPT‑5.1 on Top AGI Benchmarks – What the Results Reveal

Google's Gemini 3 and Gemini 3 Pro launch topped major AGI benchmarks such as The Human Last Exam and ARC‑AGI‑2, outperformed GPT‑5.1 in a complex 3‑D gear visualization task, and even generated a functional cloud‑OS prototype, signaling a notable shift toward true artificial general intelligence.

AGI benchmarksAI competitionGoogle Gemini
0 likes · 5 min read
Google Gemini 3 Pro Beats GPT‑5.1 on Top AGI Benchmarks – What the Results Reveal
Baobao Algorithm Notes
Baobao Algorithm Notes
Nov 13, 2025 · Artificial Intelligence

Introducing UNO‑Bench: The First Unified Omni‑Modal LLM Evaluation Suite

UNO‑Bench, an open‑source benchmark from Meituan’s LongCat team, provides the first high‑quality, low‑redundancy unified evaluation framework for omni‑modal large language models, featuring 1,250 manually annotated cross‑modal samples and 2,480 enhanced single‑modal samples covering 44 fine‑grained tasks and five modality combinations.

AI Scaling LawData PipelineMultimodal LLM
0 likes · 15 min read
Introducing UNO‑Bench: The First Unified Omni‑Modal LLM Evaluation Suite
Baobao Algorithm Notes
Baobao Algorithm Notes
Nov 11, 2025 · Artificial Intelligence

Why Redesign the Training Stack? Inside Olmo‑Thinking’s Open‑Source RL Journey

This article provides a detailed technical analysis of the Olmo‑Thinking project, covering why a new open‑source LLM was built, the challenges of reinforcement learning at scale, data‑mix optimization, architectural bottlenecks such as missing GQA and QK‑Norm, and the post‑training techniques used to improve reasoning and long‑context capabilities.

Open-source ModelsPost-TrainingRLVR
0 likes · 20 min read
Why Redesign the Training Stack? Inside Olmo‑Thinking’s Open‑Source RL Journey
Baobao Algorithm Notes
Baobao Algorithm Notes
Nov 7, 2025 · Artificial Intelligence

Kimi K2-Thinking: 1T‑Parameter Agent Model Beats GPT‑5 on Humanity’s Last Exam

Kimi's open‑source K2‑Thinking model, a 1‑trillion‑parameter agent with native INT4 quantization and 256k context, achieves SOTA performance on benchmarks like Humanity’s Last Exam, BrowseComp and SEAL‑0, outperforms GPT‑5 and Grok‑4, and demonstrates complex tool‑driven reasoning through real‑world examples.

AIAgent ModelK2-Thinking
0 likes · 6 min read
Kimi K2-Thinking: 1T‑Parameter Agent Model Beats GPT‑5 on Humanity’s Last Exam
Baobao Algorithm Notes
Baobao Algorithm Notes
Oct 31, 2025 · Artificial Intelligence

How Risk‑Sensitive Reinforcement Learning Improves LLM Pass@K Performance

This article analyzes why standard reinforcement learning can degrade Pass@K metrics after fine‑tuning large language models, introduces a risk‑sensitive RL objective that reshapes the advantage estimator, and demonstrates through bandit and mathematical‑reasoning experiments that the RS‑GRPO method consistently boosts diversity and overall Pass@K scores across multiple LLMs.

Exploration-ExploitationLLM fine-tuningRS-GRPO
0 likes · 12 min read
How Risk‑Sensitive Reinforcement Learning Improves LLM Pass@K Performance
Baobao Algorithm Notes
Baobao Algorithm Notes
Oct 31, 2025 · Artificial Intelligence

Unlocking LLM RL Scaling: The Best Practices from Meta’s New Study

Meta’s recent paper reveals a sigmoid‑shaped scaling law for LLM reinforcement learning, presents extensive 40‑k GPU‑hour experiments, compares various RL designs such as PPO‑off‑policy‑k and Pipeline‑RL‑k, and distills the findings into a practical “ScaleRL” recipe that improves performance and efficiency.

LLMRL Optimizationreinforcement learning
0 likes · 10 min read
Unlocking LLM RL Scaling: The Best Practices from Meta’s New Study