AI — Models & Research

The BEST local AI video generator just got BETTER!

Seedance 2.5 : Miracle ou Arnaque ? (crash test)

Seedance 2.5: Miracle or Scam? (Crash Test)

Run Open Models Locally: Nemotron 3 Ultra on DGX Station | Nemotron Labs

Dana Arad: SAEs for Content Control (2026-02-05)

CCN 2026 | GAC: Do World Models Emerge in Neural Networks Trained for Prediction?

Así puedes crear vídeos con IA sin volver a ponerte delante de una cámara

How to create AI videos without ever stepping in front of a camera again

Andrew Lee: Decomposing Query-Key Feature Interactions Using Contrastive Covariances (2026-05-13)

Why Your RAG Agent Is Confidently Wrong: Retrieval Choices That Actually Matter

The Meaning Gap: Your Agent Is Correct. Your Deployment Is Not.

OpenAI’s Secret New Model Makes Fable 5 Look Primitive

MLP Live session (10-08-2026)

MLP Live session (10-08-2026)

INSPIRE: Intent-aware Neural Sponsored Product Retrieval for E-commerce

How to Build a One Person AI Business (Using Claude Code)

Fine-Tuning LLMs for Real-World Tool Calling: Lessons from tau2-bench

Expanding the Capabilities of Tabular Foundation Models

Evaluating Netflix Show Synopses with LLM-as-a-Judge

Enhancing Training Data Pipelines with Lance and the Multimodal Lakehouse

Encrypted inferences over decision trees

Emulating Real-World PII with a Large-Scale Synthetic Dataset to Audit LLM Memorization

Automated and Scalable RAG: Vector Stores, MCP, Clustering

Agentic vs. Vector Search: An Eval-Driven Approach to Coding Agent Performance

Agentic Financial Reasoning with Knowledge Graphs and LLMs

¿Cuál es la mejor IA de vídeo? Seedance 2.5 vs H3 vs Flux 3 vs Grok 1.5 (Ep. 166)

Which is the best video AI? Seedance 2.5 vs H3 vs Flux 3 vs Grok 1.5 (Ep. 166)

AI Is Learning at the Wrong Level of Abstraction — Matthieu Wyart

5 Best Practices for Building AI Agent Skills

Prompt Engineering and RAG - AI Engineering

Personne ne réalise ce que le nouveau ChatGPT peut faire

No one realizes what the new ChatGPT can do

L’appareil d’IA controversé d’OpenAI vient de fuiter… C’est littéralement un donut !

OpenAI's controversial AI device just leaked... It's literally a donut!

Une skill créée en 5 minutes avec Claude - Tuto complet 2026

A skill created in 5 minutes with Claude - Complete tutorial 2026

Research Presentation

Research Discussion

Panel Session

OpenAI’s Controversial AI Device Just Leaked… And It’s Literally a Donut

MLT | Week-8 | Solve with us | Naive Bayes Algorithm

MLT | Week-8 | Solve with us | Naive Bayes Algorithm

La Chine surprend le monde avec une IA de 10 000 milliards de paramètres

China surprises the world with a 10,000 billion parameter AI

Do Multilingual Embedding Models Really Retrieve African Language Content Well? A Yoruba Case Study

Agents That Learn: Building Your First RL Agent with JAX

A computational phase transition for learning-to-sample from Ising models

What Really Separates Autoregression and Diffusion? A Synthesis and Path Beyond

Score-Based Generative Modeling without Diffusion: Langevin MCMC All the Way