The AI Timeline

Follow The Latest Cutting Edge AI Research in 5 minutes a week.

Connect

Featured Posts

Jan 28, 2025

DeepSeek-R1 Explained

Plus more about Transformer2 and Kimi k1.5

by cloud

Nov 19, 2024

Top 3 Rated ICLR 2025 Papers - LoRA Done RITE, IC-Light, HyCoCLIP

#32 | Latest AI Research Explained Simply

by cloud

Premium InsightsPremium Insights

May 19, 2025

How DeepSeek Made The Best Math Prover Ever (+500% vs prev. SoTA)

Premium Insights: A closer look into the DeepSeek Prover series

by cloud, +1

Jun 03, 2025

A Shocking RLVR Revelation For LLM Just Dropped

Read about "Rethinking Training Signals in RLVR", why LLMs are headless chickens, and "Learning to Reason without External Rewards"

by cloud

Premium InsightsPremium Insights

Jun 06, 2025

May 2025 Research Trend Report

Premium Insights: A recap of popular AI research papers and research trends in May 2025

by cloud

Jun 17, 2025

LLM That Can Modify Itself?

Plus more about "The Diffusion Duality" and "Reinforcement Pre-Training"

by cloud

Pre-training under infinite compute

Plus more about Discovery of Unstable Singularities and AToken: A Unified Tokenizer for Vision

by cloud

Sep 16, 2025

Defeating Nondeterminism in LLM Inference

Plus more about Analog in-memory computing attention mechanism for fast and energy-efficient large language models, and the Majority is not always right: RL training for solution aggregation

Naman, +1

Sep 09, 2025

Why Do MLLMs Struggle with Spatial Understanding?

Plus more about Small Language Models are the Future of Agentic AI and Why Online Reinforcement Learning Forgets Less

Naman, +1

Sep 03, 2025

Prophesy in LLMs: DIFFUSION LANGUAGE MODELS KNOW THE ANSWER BEFORE DECODING

Plus more about StepWiser: Stepwise Generative Judges for Wiser Reasoning and Predicting the Order of Upcoming Tokens Improves Language Modeling

by cloud

Aug 26, 2025

Has GPT-5 Achieved Spatial Intelligence?

Plus more about Reinforcement Learning with Rubric Anchors and DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

Naman, +1

Aug 19, 2025

How AI is Learning to Reason: RL Tricks, Policy Optimization, and the New WebWatcher Agent

In this article, we will analyze the use of Reinforcement Learning for LLM reasoning, a new policy optimization method for more concise outputs, and the groundbreaking WebWatcher vision-language research agent.

by cloud

Aug 12, 2025

Smarter AI Agents, Realistic Virtual Try-Ons, and Better Memory

How AI is Learning to Reason, Dress, and Remember: A Look at GLM-4.5, Voost, and Memp

by cloud

Aug 05, 2025

How LLMs Pass the Math Olympiad and Why Models Like Grok Can Be Manipulated to Praise Hitler

Understanding the genius and the ghost in the machine: how breakthroughs like Seed-Prover create AIs that can ace logic puzzles, while Persona Vectors reveal how their very character can be hijacked.

by cloud

Jul 30, 2025

"AlphaGo Moment" for Model Architecture Discovery...?

Plus more on Group Sequence Policy Optimization and Autoregressive models in Data-Constrained Settings

by cloud

Jul 22, 2025

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

Dive into the latest AI research and industry news, featuring limit testing how many instructions LLMs can follow at once, Mixture-of-Recursions, and monitoring LLM using their CoT

by cloud

Jul 16, 2025

Dynamic Chunking, Small Batch Size Training, and more...

Dive into the latest AI research and industry news, featuring Pollen Robotics' Reachy Mini, Grok 4's launch, and groundbreaking developments in open-source robotics and AI technologies.

by cloud