Nibaldo

ML Engineer | Master in Advanced & Applied AI | MSc Statistics | MSc Full Stack Web Developer | Math Teacher | Bachelor Engineering Sciences | From 🇪🇸🇨🇱

[Classic arts & Wallpapers 🥷 @Classisco123]

Dragon Ball Z | Tap Hold Load 4k

[MOON LOVER @M1ONLOVER]

Full Moon

[Sebastian Raschka @rasbt]

I (finally) put together a new LLM Architecture Gallery that collects the architecture figures all in one place!
https://t.co/NO7z6XSRHS

[𝘾𝙖𝙧𝙣𝙖𝙫𝙖𝙡𝙖𝙙𝙞𝙘𝙩𝙤𝙨 @Carnavaladictos]

Última cuarteta chirigota Ssshhhhh
@ChirigotaBizc8

[Iciar 🌸 @ichiar_]

Ay, ay, ay que cuando llega febrero ❤️‍🩹
@ChirigotaBizc8

[C҉r҉a҉z҉y҉ ҉3҉x҉4҉ 🎭 @crazy3x4]

Y a ti, por qué te gusta el carnaval??
Pues... 👇

[Oscar Arias @OACerebro]

Enjoy!

https://t.co/RKCakL3TQR

[MiniMax (official) @MiniMax_AI]

MiniMax M2.1 is officially live🚀
Built for real-world coding and AI-native organizations — from vibe builds to serious workflows.

A SOTA 10B-activated OSS coding & agent model, scoring 72.5% on SWE-multilingual and 88.6% on our newly open-sourced VIBE-bench, exceeding leading closed-source models like Gemini 3 Pro and Claude 4.5 Sonnet.

The most powerful OSS model for the agentic era is here.

[Chao Huang @huang_chao4969]

🚀 Paper2Slides is now open source! Transform research papers & technical reports into professional presentations with ONE click!

We've generated stunning presentation slides from the latest DeepSeek V3.2 paper in diverse styles - check them out and share your feedback!

🔥 Core Features:
- 📄 Multi-format support - PDF, Word, Excel, PowerPoint & more
- 🎯 Smart content understanding - Captures key insights, figures, formulas, tables & data points.
- 🎨 Custom styling - Professional themes with full personalization.
- ⚡ Lightning fast - High-quality PPT generation in minutes.

GitHub: https://t.co/zNxlFifDU3

Never build slides from scratch again! ✨ Come play with it ⭐!

#Paper2Slides #AIPPT

[Google for Developers @googledevs]

📈 Metrax is the evaluation metrics library for JAX. It's fast, scales well, and fully open source.

Learn how it works in your training loop → https://t.co/7CqvDPgImE

[NotebookLM @NotebookLM]

We spent all night wondering what you were "actually" waiting for, and we finally have it:

Images as sources!!! Whether it's a photo of handwritten notes, a screenshot of a textbook or graphs on a web page, @NotebookLM can synthesize the information and produce outputs from it.

[Google for Developers @googledevs]

Google Colab is officially coming to @code! ⚡️

You can now connect VS Code notebooks directly to @GoogleColab runtimes. Get the best of both worlds: the editor you love, powered by the compute (GPUs/TPUs) you need. → https://t.co/prgImNfEd2

[Deedy @deedydas]

DeepSeek-OCR is the best OCR ever.

It parses this extremely hard to read handwritten letter written by mathematician Ramanujan in 1913 with a frightening degree of accuracy.

Not perfect, but beats former best dots ocr. Bonus points if you can spot the errors.

Try it here:

[Ray Fernando @RayFernando1337]

This is the JPEG moment for AI.

Optical compression doesn't just make context cheaper. It makes AI memory architectures viable.

Training data bottlenecks? Solved.
- 200k pages/day on ONE GPU
- 33M pages/day on 20 nodes
- Every multimodal model is data-constrained. Not anymore.

Agent memory problem? Solved.
- The #1 blocker: agents forget
- Progressive compression = natural forgetting curve
- Agents can now run indefinitely without context collapse

RAG might be obsolete.
- Why chunk and retrieve if you can compress entire libraries into context?
- A 10,000-page corpus = 10M text tokens OR 1M vision tokens
- You just fit the whole thing in context

Multimodal training data generation: 10x more efficient
- If you're OpenAI/Anthropic/Google and you DON'T integrate this, you're 10x slower
- This is a Pareto improvement: better AND faster

Real-time AI becomes economically viable
- Live document analysis
- Streaming OCR for accessibility
- Real-time translation with visual context
- All were too expensive. Not anymore.

[elvis @omarsar0]

Agentic Context Engineering

Great paper on agentic context engineering.

The recipe:

Treat your system prompts and agent memory as a living playbook.

Log trajectories, reflect to extract actionable bullets (strategies, tool schemas, failure modes), then merge as append-only deltas with periodic semantic de-dupe.

Use execution signals and unit tests as supervision. Start offline to warm up a seed playbook, then continue online to self-improve.

On AppWorld, ACE consistently beats strong baselines in both offline and online adaptation. Example: ReAct+ACE (offline) lifts average score to 59.4% vs 46.0–46.4% for ICL/GEPA. Online, ReAct+ACE reaches 59.5% vs 51.9% for Dynamic Cheatsheet.

Paper: https://t.co/AZRZe0axlI

[DeepSeek @deepseek_ai]

🚀 Introducing DeepSeek-V3.2-Exp — our latest experimental model!

✨ Built on V3.1-Terminus, it debuts DeepSeek Sparse Attention(DSA) for faster, more efficient training & inference on long context.
👉 Now live on App, Web, and API.
💰 API prices cut by 50%+!

1/n

[Qwen @Alibaba_Qwen]

🚀 Introducing Qwen3-LiveTranslate-Flash — Real‑Time Multimodal Interpretation — See It, Hear It, Speak It！

🌐 Wide language coverage — Understands 18 languages & 6 dialects, speaks 10 languages.
👁️ Vision‑Enhanced Comprehension — Reads lips, gestures, on‑screen text and real‑world entities, robust in noise.
⚡ 3s Latency — Near‑instant real-time translation.
🎯 Lossless Interpretation — Offline‑level translation accuracy.
🎙️ Natural, expressive voices.

Connect with the world face-to-face, in real time.
🔗 Blog: https://t.co/EkoJjsU6E7
💻 Dashscope: https://t.co/7wmHANamLY
🤗 Demo: https://t.co/Evfwaj66Z6

[DailyPapers @HuggingPapers]

Microsoft introduces Latent Zoning Network (LZN)

A unified principle for generative modeling, representation learning, and classification. LZN uses a shared Gaussian latent space and modular encoders/decoders to tackle all three core ML problems at once!

[Qwen @Alibaba_Qwen]

🚀 Introducing Qwen3-Next-80B-A3B — the FUTURE of efficient LLMs is here!

🔹 80B params, but only 3B activated per token → 10x cheaper training, 10x faster inference than Qwen3-32B.(esp. @ 32K+ context!)
🔹Hybrid Architecture: Gated DeltaNet + Gated Attention → best of speed & recall
🔹 Ultra-sparse MoE: 512 experts, 10 routed + 1 shared
🔹 Multi-Token Prediction → turbo-charged speculative decoding
🔹 Beats Qwen3-32B in perf, rivals Qwen3-235B in reasoning & long-context

🧠 Qwen3-Next-80B-A3B-Instruct approaches our 235B flagship.
🧠 Qwen3-Next-80B-A3B-Thinking outperforms Gemini-2.5-Flash-Thinking.

Try it now: https://t.co/V7RmqMaVNZ
Blog: https://t.co/qhzjBv6dEH
Huggingface: https://t.co/zHHNBB2l5X
ModelScope: https://t.co/mld9lp8QjK
Kaggle: https://t.co/GeTStgaMlu
Alibaba Cloud API: https://t.co/RdmUF5m6JA

[Sebastian Raschka @rasbt]

Updated & turned my Big LLM Architecture Comparison article into a narrated video lecture.

The 11 LLM architectures covered in this video:
1. DeepSeek V3/R1
2. OLMo 2
3. Gemma 3
4. Mistral Small 3.1
5. Llama 4
6. Qwen3
7. SmolLM3
8. Kimi 2
9. GPT-OSS
10. Grok 2.5
11. GLM-4.5