Sitemap - 2024 - So Essentially

Apollo for Video Understanding

3D World Generation

PIGs Might Fly

Coconut Thinking

Around the world in 80 steps

Longer is NOT better for VLMs

Universal Soccer Understanding

SOLAMI enters the chat

Video without depth has Depth

AfriMed for African Medicine

For all the Posers

Edit Anyway My Face Generates Away

Star Attention ⭐⭐⭐⭐⭐

Material Anything

Be a Scientific Scholar

Hymba: Hybrid-head by NVIDIA

How can you build trust with AI?

Dimension X

HTML is better than TXT

AutoVFX: New Era of AI-Assisted Visual Content Creation

HelloMeme for Video Memes

OS-Atlas: The Generalist GUI VLM

Going CLEAR 👓

ROCKET-1 can play MineCraft

Optimization of Compound AI

Self Steering Optimizations

Democratizing Medical LLMs

Duo Attention Heads allow 3.3M wins!

Apple research questions OpenAI's claims about o1's reasoning

Superpositional LLMs

Crafting Physical Commonsense

FurElise for Piano Trajectories

For the Fourier Analysis FANs

GPU gang better watch out!

MedVisionLlama: Doctors without Segmented Borders

Depth in Apple Photos

ComfyGen: Comfortably generate high quality visuals

Run 70B models on the Edge

Apple quietly publishes MM1.5 paper

Molmo and PixMo

Time-MoE: Foundation Model

Yes But ...

OpenAI o1 preview Doctor beating others!

Great At Misleading People

Solo Audio from John Hopkins Released!

Qwen 2.5 Coder is better!

AI Generates Novel Research!

DSBench: AI Data Science Benchmark Verified By Actual Data Scientists

Hi3D for Image to 3D

MEDIC Benchmark for Doctors 👨‍⚕️

SongCreator AI

Kunlun makes FLUX Music

LongLLaVa overflowing!

Political Debate with LLMs

OLMoE: A Fully Open Model

AI can think while seeing and talking

Policies and Laws for MLLMs 👮

Dolphin for Long Context 🐬

WiM helps LLMS read between the lines 📨

LlamaDuo: Seamless Migration from Service LLMs to Small-Scale Local LLMs

AI fails badly in the real world

Sapiens by Meta

FocusLLM for Better Context Understanding ⚡🧠

Cybench For Hacker Cyborgs 🤖

JPEG-LM: LLM to Image Codec 🩻

SHEEP-like Models 🐑

Math Provers 🧮

Designer Proteins from Italy 🧬

No Q* yet but Small Models have R* 🌟

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Sketch Yourself Your Own GTA 6 🖌️🗺️🌎

LLaVA-OneVision 🌋🔥🌋

Greatest Table Tennis Robot In the World 🏓

Run it on your phone 📲

Visionary Doctors, Watch Out! 🔬

Quandary with Quantum Chemistry 🧪

Need a lawyer? Better Call SaulLM 📂

In the spirit of the Olympics and Greece! 🥇

How good are you with visual riddles? 🫥

Latest in Useless AI Skills: Pen Spinning ✍️

Hear about the new AMEX?

Cross Any Terrain with Your RoboDog 🦮

AI Pretends to Play Doctor 👩‍⚕️👨‍⚕️

The Llama 3.1 Paper 🦙📜

Free Music, All the time, Everywhere 🎶

Apple: The pound-for-pound Champ 🥊⚡🍏

Can Language Model Agents get poisoned? ☣️

How fast can you find a needle in a haystack? 🪡👩‍🌾

Talk to the Hand: YouTube-SL-25's Multilingual Mayhem ✋

Your spreadsheets want to talk 💬

RouteLLM: Most Bang for Your Buck💥

LLM⚡CPU wins continued ...

Vision Language Models are surprisingly blind!

LLaMAX for maximal language translation

RedPill with TabReD 💊

CPU Renaissance 🚀

We are going Agentless 🥷

AI Intern for Multimedia Analysis 🤓🎦

Predicting Global World Events 🌎 (Actually)

Over 1,000,000,000 Personas 🫨🤖

Get that Huatuo GPT, know what I mean?

Ink to Incarnate: Consistent 3D Animals with YouDream 🐕🐎🐃🐘

How to DETOX a language? ☣️⚠️🤖

LongRAG with Long Retriever and Long Reader

Stylebreeder clusters AI art 🎨🤖

Ready for Universal Quantum Chemistry? 🔬🧪👩‍🔬

The Devil is in the Details 😈

GeoChat capabilities for Geo Data! 🌎

Now AI can navigate through your apps 📱

Phased Consistency Model

Intro to VLMs

GeoGuessr Rainbolt beaten by PIGEON 🕊️

Become a next level coder with StarCoder2!

New Paradigm with 1 bit LLMs! 🚀🤖🚀

InseRF yourself into 3D Scenes!

A Shocking Amount of the Web is Machine Translated!

Once a Decepticon, always a Decepticon

Google Releases Conversational Diagnostic AI!🧑‍⚕️🤖

You can't HANDLE ✋this model

How to make Vision GPTs more human aligned?

Bend the Rules with Blended Models 🌪️

Stable Diffusion XL Just Leveled Up!

Llama is a Pro? 🤔😎

What You See is What You GAN (In 3D)

TinyLlama is here! 🪩🦙😎

Are you aMUSEd yet?

DocLLM: The Machines Are Reading Your Receipts!

Mind Blowing New Foundational Model in Materials Chemistry! 🧪🤖💥

How are NPCs using LLMs for Open-World Games?